| 1068 |
2024-03-05 |
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis |
link |
Patrick Esser, Sumith Kulal,..., Robin Rombach |
| 708 |
2024-01-17 |
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State
Space Model |
link |
Lianghui Zhu, Bencheng Liao,..., Xinggang Wang |
| 607 |
2023-08-04 |
MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities |
link |
Weihao Yu, Zhengyuan Yang,..., Lijuan Wang |
| 602 |
2023-05-23 |
Improving Factuality and Reasoning in Language Models through Multiagent
Debate |
link |
Yilun Du, Shuang Li,..., Igor Mordatch |
| 481 |
2024-03-07 |
Chatbot Arena: An Open Platform for Evaluating LLMs by
Human Preference |
link |
Wei-Lin Chiang, Lianmin Zheng,..., Ion Stoica |
| 454 |
2023-09-11 |
NExT-GPT: Any-to-Any Multimodal LLM |
link |
Shengqiong Wu, Hao Fei,..., Tat-Seng Chua |
| 424 |
2024-05-31 |
Transformers are SSMs: Generalized Models and Efficient Algorithms Through
Structured State Space Duality |
link |
Tri Dao, Albert Gu |
| 361 |
2023-10-02 |
ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback |
link |
Ganqu Cui, Lifan Yuan,..., Maosong Sun |
| 340 |
2024-02-14 |
DoRA: Weight-Decomposed Low-Rank Adaptation |
link |
Shih-yang Liu, Chien-Yi Wang,..., Min-Hung Chen |
| 313 |
2024-02-06 |
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming
and Robust Refusal |
link |
Mantas Mazeika, Long Phan,..., Dan Hendrycks |
| 310 |
2023-09-01 |
RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback
with AI Feedback |
link |
Harrison Lee, Samrat Phatale,..., Sushant Prakash |
| 298 |
2024-01-18 |
Self-Rewarding Language Models |
link |
Weizhe Yuan, Richard Yuanzhe Pang,..., Jason E Weston |
| 275 |
2024-01-02 |
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language
Models |
link |
Zixiang Chen, Yihe Deng,..., Quanquan Gu |
| 258 |
2023-12-14 |
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision |
link |
Collin Burns, Pavel Izmailov,..., Jeffrey Wu |
| 253 |
2023-05-22 |
How Language Model Hallucinations Can Snowball |
link |
Muru Zhang, Ofir Press,..., Noah A. Smith |
| 247 |
2024-01-19 |
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding
Heads |
link |
Tianle Cai, Yuhong Li,..., Tri Dao |
| 237 |
2023-12-21 |
VideoPoet: A Large Language Model for Zero-Shot Video Generation |
link |
Dan Kondratyuk, Lijun Yu,..., Lu Jiang |
| 207 |
2024-01-03 |
GPT-4V(ision) is a Generalist Web Agent, if Grounded |
link |
Boyuan Zheng, Boyu Gou,..., Yu Su |
| 200 |
2024-01-16 |
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance
in Machine Translation |
link |
Haoran Xu, Amr Sharaf,..., Young Jin Kim |
| 188 |
2023-10-14 |
A decoder-only foundation model for time-series forecasting |
link |
Abhimanyu Das, Weihao Kong,..., Yichen Zhou |
| 186 |
2024-02-06 |
LESS: Selecting Influential Data for Targeted Instruction Tuning |
link |
Mengzhou Xia, Sadhika Malladi,..., Danqi Chen |
| 183 |
2023-10-06 |
Language Agent Tree Search Unifies Reasoning, Acting, and Planning
in Language Models |
link |
Andy Zhou, Kai Yan,..., Yu-Xiong Wang |
| 179 |
2023-09-28 |
Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution |
link |
Chrisantha Fernando, Dylan Sunil Banarse,..., Tim Rocktäschel |
| 173 |
2024-03-06 |
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection |
link |
Jiawei Zhao, Zhenyu Zhang,..., Yuandong Tian |
| 167 |
2023-06-13 |
SqueezeLLM: Dense-and-Sparse Quantization |
link |
Sehoon Kim, Coleman Richard Charles Hooper,..., Kurt Keutzer |
| 165 |
2024-02-04 |
Unified Training of Universal Time Series Forecasting Transformers |
link |
Gerald Woo, Chenghao Liu,..., Doyen Sahoo |
| 161 |
2024-02-05 |
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache |
link |
Zirui Liu, Jiayi Yuan,..., Xia Hu |
| 157 |
2023-12-18 |
Iterative Preference Learning from Human Feedback: Bridging Theory and
Practice for RLHF under KL-constraint |
link |
Wei Xiong, Hanze Dong,..., Tong Zhang |
| 152 |
2023-09-29 |
AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and
Training |
link |
Ziyu Wan, Xidong Feng,..., Jun Wang |
| 144 |
2024-02-23 |
Genie: Generative Interactive Environments |
link |
Jake Bruce, Michael D Dennis,..., Tim Rocktäschel |
| 143 |
2024-03-05 |
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and
Diffusion Models |
link |
Zeqian Ju, Yuancheng Wang,..., sheng zhao |
| 142 |
2023-12-11 |
Gated Linear Attention Transformers with Hardware-Efficient Training |
link |
Songlin Yang, Bailin Wang,..., Yoon Kim |
| 141 |
2024-02-19 |
LoRA+: Efficient Low Rank Adaptation of Large Models |
link |
Soufiane Hayou, Nikhil Ghosh, Bin Yu |
| 140 |
2024-02-03 |
Break the Sequential Dependency of LLM Inference Using Lookahead
Decoding |
link |
Yichao Fu, Peter Bailis,..., Hao Zhang |
| 139 |
2023-04-19 |
Fundamental Limitations of Alignment in Large Language Models |
link |
Yotam Wolf, Noam Wies,..., Amnon Shashua |
| 136 |
2023-11-07 |
The Linear Representation Hypothesis and the Geometry of Large
Language Models |
link |
Kiho Park, Yo Joong Choe, Victor Veitch |
| 136 |
2023-11-18 |
An Embodied Generalist Agent in 3D World |
link |
Jiangyong Huang, Silong Yong,..., Siyuan Huang |
| 134 |
2024-04-16 |
Is DPO Superior to PPO for LLM Alignment? A
Comprehensive Study |
link |
Shusheng Xu, Wei Fu,..., Yi Wu |
| 132 |
2024-02-21 |
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens |
link |
Yiran Ding, Li Lyna Zhang,..., Mao Yang |
| 128 |
2024-02-01 |
Executable Code Actions Elicit Better LLM Agents |
link |
Xingyao Wang, Yangyi Chen,..., Heng Ji |
| 127 |
2023-09-25 |
Physics of Language Models: Part 3.1, Knowledge Storage and
Extraction |
link |
Zeyuan Allen-Zhu, Yuanzhi Li |
| 127 |
2024-02-02 |
TravelPlanner: A Benchmark for Real-World Planning with Language Agents |
link |
Jian Xie, Kai Zhang,..., Yu Su |
| 124 |
2023-12-01 |
Nash Learning from Human Feedback |
link |
Remi Munos, Michal Valko,..., Bilal Piot |
| 122 |
2024-02-15 |
Data Engineering for Scaling Language Models to 128K Context |
link |
Yao Fu, Rameswar Panda,..., Hao Peng |
| 121 |
2024-01-26 |
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty |
link |
Yuhui Li, Fangyun Wei,..., Hongyang Zhang |
| 114 |
2024-01-22 |
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal
LLMs |
link |
Ling Yang, Zhaochen Yu,..., Bin CUI |
| 111 |
2024-02-06 |
MOMENT: A Family of Open Time-series Foundation Models |
link |
Mononito Goswami, Konrad Szafer,..., Artur Dubrawski |
| 109 |
2024-02-08 |
SPHINX-X: Scaling Data and Parameters for a Family of
Multi-modal Large Language Models |
link |
Dongyang Liu, Renrui Zhang,..., Peng Gao |
| 106 |
2024-04-22 |
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data |
link |
Fahim Tajwar, Anikait Singh,..., Aviral Kumar |
| 101 |
2024-02-07 |
Fast Timing-Conditioned Latent Audio Diffusion |
link |
Zach Evans, CJ Carr,..., Jordi Pons |
| 101 |
2024-01-02 |
LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning |
link |
Hongye Jin, Xiaotian Han,..., Xia Hu |
| 100 |
2023-10-11 |
In-Context Unlearning: Language Models as Few-Shot Unlearners |
link |
Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju |
| 98 |
2024-02-12 |
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language
Models |
link |
Siddharth Karamcheti, Suraj Nair,..., Dorsa Sadigh |
| 98 |
2023-11-02 |
RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning
via Generative Simulation |
link |
Yufei Wang, Zhou Xian,..., Chuang Gan |
| 96 |
2024-02-07 |
Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with
Applications to Protein Co-Design |
link |
Andrew Campbell, Jason Yim,..., Tommi Jaakkola |
| 95 |
2024-01-03 |
A Mechanistic Understanding of Alignment Algorithms: A Case Study
on DPO and Toxicity |
link |
Andrew Lee, Xiaoyan Bai,..., Rada Mihalcea |
| 95 |
2024-02-06 |
QuIP$#$: Even Better LLM Quantization with Hadamard Incoherence and
Lattice Codebooks |
link |
Albert Tseng, Jerry Chee,..., Christopher De Sa |
| 94 |
2024-02-09 |
Debating with More Persuasive LLMs Leads to More Truthful
Answers |
link |
Akbir Khan, John Hughes,..., Ethan Perez |
| 94 |
2024-01-08 |
A Minimaximalist Approach to Reinforcement Learning from Human Feedback |
link |
Gokul Swamy, Christoph Dann,..., Alekh Agarwal |
| 93 |
2024-01-22 |
WARM: On the Benefits of Weight Averaged Reward Models |
link |
Alexandre Rame, Nino Vieillard,..., Johan Ferret |
| 92 |
2024-02-07 |
AlphaFold Meets Flow Matching for Generating Protein Ensembles |
link |
Bowen Jing, Bonnie Berger, Tommi Jaakkola |
| 92 |
2024-04-30 |
Better & Faster Large Language Models via Multi-token Prediction |
link |
Fabian Gloeckle, Badr Youbi Idrissi,..., Gabriel Synnaeve |
| 92 |
2023-12-04 |
Magicoder: Empowering Code Generation with OSS-Instruct |
link |
Yuxiang Wei, Zhe Wang,..., LINGMING ZHANG |
| 92 |
2024-02-12 |
PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs |
link |
Soroush Nasiriany, Fei Xia,..., brian ichter |
| 91 |
2024-02-07 |
MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark |
link |
Dongping Chen, Ruoxi Chen,..., Lichao Sun |
| 91 |
2024-01-05 |
CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution |
link |
Alex Gu, Baptiste Roziere,..., Sida Wang |
| 90 |
2024-01-11 |
Extreme Compression of Large Language Models via Additive Quantization |
link |
Vage Egiazarian, Andrei Panferov,..., Dan Alistarh |
| 90 |
2024-03-14 |
3D-VLA: A 3D Vision-Language-Action Generative World Model |
link |
Haoyu Zhen, Xiaowen Qiu,..., Chuang Gan |
| 88 |
2024-02-08 |
Generalized Preference Optimization: A Unified Approach to Offline Alignment |
link |
Yunhao Tang, Zhaohan Daniel Guo,..., Bilal Piot |
| 87 |
2024-01-29 |
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models |
link |
Fuzhao Xue, Zian Zheng,..., Yang You |
| 87 |
2024-01-11 |
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of
Language Models |
link |
Asma Ghandeharioun, Avi Caciularu,..., Mor Geva |
| 85 |
2023-07-20 |
SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language
Models |
link |
Xiaoxuan Wang, Ziniu Hu,..., Wei Wang |
| 85 |
2024-04-24 |
MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language
Models Towards Multitask AGI |
link |
Kaining Ying, Fanqing Meng,..., Wenqi Shao |
| 84 |
2024-03-11 |
Monitoring AI-Modified Content at Scale: A Case Study on
the Impact of ChatGPT on AI Conference Peer Reviews |
link |
Weixin Liang, Zachary Izzo,..., James Y. Zou |
| 83 |
2023-11-11 |
In-context Vectors: Making In Context Learning More Effective and
Controllable Through Latent Space Steering |
link |
Sheng Liu, Haotian Ye,..., James Y. Zou |
| 82 |
2024-01-22 |
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text |
link |
Abhimanyu Hans, Avi Schwarzschild,..., Tom Goldstein |
| 79 |
2024-03-05 |
Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling |
link |
Yair Schiff, Chia Hsiang Kao,..., Volodymyr Kuleshov |
| 79 |
2024-02-07 |
Assessing the Brittleness of Safety Alignment via Pruning and
Low-Rank Modifications |
link |
Boyi Wei, Kaixuan Huang,..., Peter Henderson |
| 78 |
2023-09-01 |
Image Hijacks: Adversarial Images can Control Generative Models at
Runtime |
link |
Luke Bailey, Euan Ong,..., Scott Emmons |
| 78 |
2024-02-01 |
Repeat After Me: Transformers are Better than State Space
Models at Copying |
link |
Samy Jelassi, David Brandfonbrener,..., eran malach |
| 78 |
2023-10-08 |
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce
for Pruning LLMs to High Sparsity |
link |
Lu Yin, You Wu,..., Shiwei Liu |
| 78 |
2023-10-29 |
Language Agents with Reinforcement Learning for Strategic Play in
the Werewolf Game |
link |
Zelai Xu, Chao Yu,..., Yi Wu |
| 76 |
2024-02-22 |
tinyBenchmarks: evaluating LLMs with fewer examples |
link |
Felipe Maia Polo, Lucas Weber,..., Mikhail Yurochkin |
| 75 |
2024-06-16 |
QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference |
link |
Jiaming Tang, Yilong Zhao,..., Song Han |
| 75 |
2024-02-22 |
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use
Cases |
link |
Zechun Liu, Changsheng Zhao,..., Vikas Chandra |
| 73 |
2024-02-02 |
Audio Flamingo: A Novel Audio Language Model with Few-Shot
Learning and Dialogue Abilities |
link |
Zhifeng Kong, Arushi Goel,..., Bryan Catanzaro |
| 71 |
2023-12-07 |
Chain of Code: Reasoning with a Language Model-Augmented Code
Emulator |
link |
Chengshu Li, Jacky Liang,..., brian ichter |
| 71 |
2024-03-11 |
Stealing part of a production language model |
link |
Nicholas Carlini, Daniel Paleka,..., Florian Tramèr |
| 69 |
2023-12-31 |
Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling
Laws |
link |
Nikhil Sardana, Jacob Portes,..., Jonathan Frankle |
| 69 |
2024-02-13 |
COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability |
link |
Xingang Guo, Fangxu Yu,..., Bin Hu |
| 69 |
2024-02-06 |
Can Mamba Learn How To Learn? A Comparative Study
on In-Context Learning Tasks |
link |
Jongho Park, Jaeseung Park,..., Dimitris Papailiopoulos |
| 69 |
2024-02-06 |
BiLLM: Pushing the Limit of Post-Training Quantization for LLMs |
link |
Wei Huang, Yangdong Liu,..., XIAOJUAN QI |
| 69 |
2023-10-25 |
Controlled Decoding from Language Models |
link |
Sidharth Mudgal, Jong Lee,..., Ahmad Beirami |
| 67 |
2024-02-15 |
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference
Adjustment |
link |
Rui Yang, Xiaoman Pan,..., Jianshu Chen |
| 67 |
2023-10-05 |
MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation |
link |
Qian Huang, Jian Vora,..., Jure Leskovec |
| 66 |
2023-09-12 |
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts |
link |
Zhi-Yi Chin, Chieh Ming Jiang,..., Wei-Chen Chiu |
| 65 |
2024-05-07 |
Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition |
link |
Hao Fei, Shengqiong Wu,..., Wynne Hsu |
| 65 |
2024-03-05 |
Behavior Generation with Latent Actions |
link |
Seungjae Lee, Yibin Wang,..., Lerrel Pinto |
| 64 |
2023-10-25 |
Discrete Diffusion Modeling by Estimating the Ratios of the
Data Distribution |
link |
Aaron Lou, Chenlin Meng, Stefano Ermon |
| 64 |
2024-02-13 |
IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D
Generation |
link |
Luke Melas-Kyriazi, Iro Laina,..., Filippos Kokkinos |
| 62 |
2024-02-28 |
Simple linear attention language models balance the recall-throughput tradeoff |
link |
Simran Arora, Sabri Eyuboglu,..., Christopher Re |
| 62 |
2023-11-04 |
Position: Levels of AGI for Operationalizing Progress on the
Path to AGI |
link |
Meredith Ringel Morris, Jascha Sohl-Dickstein,..., Shane Legg |
| 62 |
2023-08-20 |
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large
Language Models |
link |
Bilgehan Sel, Ahmad Tawaha,..., Ming Jin |
| 62 |
2024-02-10 |
A Tale of Tails: Model Collapse as a Change
of Scaling Laws |
link |
Elvis Dohmatob, Yunzhen Feng,..., Julia Kempe |
| 60 |
2024-02-15 |
QuRating: Selecting High-Quality Data for Training Language Models |
link |
Alexander Wettig, Aatmik Gupta,..., Danqi Chen |
| 60 |
2024-03-13 |
Human Alignment of Large Language Models through Online Preference
Optimisation |
link |
Daniele Calandriello, Zhaohan Daniel Guo,..., Bilal Piot |
| 60 |
2024-03-11 |
The Pitfalls of Next-Token Prediction |
link |
Gregor Bachmann, Vaishnavh Nagarajan |
| 59 |
2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue |
link |
Xing Han Lu, Zdeněk Kasner, Siva Reddy |
| 59 |
2023-12-07 |
An LLM Compiler for Parallel Function Calling |
link |
Sehoon Kim, Suhong Moon,..., Amir Gholami |
| 59 |
2024-03-05 |
MathScale: Scaling Instruction Tuning for Mathematical Reasoning |
link |
Zhengyang Tang, Xingxing Zhang,..., Furu Wei |
| 59 |
2023-10-08 |
In-context Convergence of Transformers |
link |
Yu Huang, Yuan Cheng, Yingbin Liang |
| 58 |
None |
Position: LLMs Can’t Plan, But Can Help Planning in
LLM-Modulo Frameworks |
link |
Subbarao Kambhampati, Karthik Valmeekam,..., Anil B Murthy |
| 57 |
2024-03-01 |
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding |
link |
Zhaorun Chen, Zhuokai Zhao,..., Jiawei Zhou |
| 57 |
2024-02-03 |
Safety Fine-Tuning at (Almost) No Cost: A Baseline for
Vision Large Language Models |
link |
Yongshuo Zong, Ondrej Bohdal,..., Timothy Hospedales |
| 56 |
2024-03-06 |
Stop Regressing: Training Value Functions via Classification for Scalable
Deep RL |
link |
Jesse Farebrother, Jordi Orbay,..., Rishabh Agarwal |
| 55 |
2024-01-04 |
Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using
Large Language Model |
link |
Fei Liu, Tong Xialiang,..., Qingfu Zhang |
| 55 |
2024-03-01 |
Provably Robust DPO: Aligning Language Models with Noisy Feedback |
link |
Sayak Ray Chowdhury, Anush Kini, Nagarajan Natarajan |
| 55 |
2023-06-09 |
Prodigy: An Expeditiously Adaptive Parameter-Free Learner |
link |
Konstantin Mishchenko, Aaron Defazio |
| 54 |
2024-02-03 |
BetterV: Controlled Verilog Generation with Discriminative Guidance |
link |
Zehua PEI, Huiling Zhen,..., Bei Yu |
| 54 |
2024-02-13 |
LLaGA: Large Language and Graph Assistant |
link |
Runjin Chen, Tong Zhao,..., Zhangyang Wang |
| 54 |
2024-02-11 |
GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative
Gaussian Splatting |
link |
Xiaoyu Zhou, Xingjian Ran,..., Ming-Hsuan Yang |
| 53 |
2024-03-12 |
WorkArena: How Capable are Web Agents at Solving Common
Knowledge Work Tasks? |
link |
Alexandre Drouin, Maxime Gasse,..., Alexandre Lacoste |
| 53 |
2024-02-12 |
Scaling Laws for Fine-Grained Mixture of Experts |
link |
Jan Ludziejewski, Jakub Krajewski,..., Sebastian Jaszczur |
| 51 |
2024-02-11 |
ODIN: Disentangled Reward Mitigates Hacking in RLHF |
link |
Lichang Chen, Chen Zhu,..., Bryan Catanzaro |
| 51 |
2023-11-08 |
NExT-Chat: An LMM for Chat, Detection and Segmentation |
link |
Ao Zhang, Yuan Yao,..., Tat-Seng Chua |
| 50 |
2023-07-31 |
Learning to Model the World With Language |
link |
Jessy Lin, Yuqing Du,..., Anca Dragan |
| 50 |
2024-04-05 |
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion
Models for One-Step Generation |
link |
Mingyuan Zhou, Huangjie Zheng,..., Hai Huang |
| 50 |
2024-02-06 |
RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback |
link |
Yufei Wang, Zhanyi Sun,..., Zackory Erickson |
| 50 |
2024-02-22 |
How Transformers Learn Causal Structure with Gradient Descent |
link |
Eshaan Nichani, Alex Damian, Jason D. Lee |
| 50 |
2024-03-14 |
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference |
link |
Piotr Nawrot, Adrian Łańcucki,..., Edoardo Ponti |
| 50 |
2024-02-13 |
GLoRe: When, Where, and How to Improve LLM Reasoning
via Global and Local Refinements |
link |
Alexander Havrilla, Sharath Chandra Raparthy,..., Roberta Raileanu |
| 50 |
2024-02-29 |
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL |
link |
Yifei Zhou, Andrea Zanette,..., Aviral Kumar |
| 50 |
2023-10-11 |
Online Speculative Decoding |
link |
Xiaoxuan Liu, Lanxiang Hu,..., Hao Zhang |
| 49 |
2024-02-14 |
Get More with LESS: Synthesizing Recurrence with KV Cache
Compression for Efficient LLM Inference |
link |
Harry Dong, Xinyu Yang,..., Beidi Chen |
| 49 |
2023-11-18 |
MagicPose: Realistic Human Poses and Facial Expressions Retargeting with
Identity-aware Diffusion |
link |
Di Chang, Yichun Shi,..., Mohammad Soleymani |
| 48 |
2023-11-15 |
Decomposing Uncertainty for Large Language Models through Input Clarification
Ensembling |
link |
Bairu Hou, Yujian Liu,..., Yang Zhang |
| 48 |
2024-01-21 |
Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers |
link |
Katherine Crowson, Stefan Andreas Baumann,..., Enrico Shippole |
| 48 |
2024-02-13 |
Agent Smith: A Single Image Can Jailbreak One Million
Multimodal LLM Agents Exponentially Fast |
link |
Xiangming Gu, Xiaosen Zheng,..., Min Lin |
| 47 |
2023-07-17 |
Do Models Explain Themselves? Counterfactual Simulatability of Natural Language
Explanations |
link |
Yanda Chen, Ruiqi Zhong,..., Kathleen McKeown |
| 47 |
2024-01-23 |
DsDm: Model-Aware Dataset Selection with Datamodels |
link |
Logan Engstrom, Axel Feldmann, Aleksander Madry |
| 47 |
2024-02-14 |
MaxMin-RLHF: Alignment with Diverse Human Preferences |
link |
Souradip Chakraborty, Jiahao Qiu,..., Mengdi Wang |
| 47 |
2023-10-16 |
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method
for Aligning Large Language Models |
link |
Ziniu Li, Tian Xu,..., Zhi-Quan Luo |
| 47 |
2024-01-31 |
On Prompt-Driven Safeguarding for Large Language Models |
link |
Chujie Zheng, Fan Yin,..., Nanyun Peng |
| 47 |
2024-02-18 |
Momentor: Advancing Video Large Language Model with Fine-Grained Temporal
Reasoning |
link |
Long Qian, Juncheng Li,..., Siliang Tang |
| 46 |
2023-06-30 |
Stay on Topic with Classifier-Free Guidance |
link |
Guillaume Sanchez, Alexander Spangher,..., Stella Biderman |
| 46 |
2024-02-27 |
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for
Generative Recommendations |
link |
Jiaqi Zhai, Lucy Liao,..., Yu Shi |
| 46 |
2024-05-13 |
Localizing Task Information for Improved Model Merging and Compression |
link |
Ke Wang, Nikolaos Dimitriadis,..., Pascal Frossard |
| 46 |
2023-12-08 |
SparQ Attention: Bandwidth-Efficient LLM Inference |
link |
Luka Ribar, Ivan Chelombiev,..., Douglas Orr |
| 46 |
2024-02-08 |
Dirichlet Flow Matching with Applications to DNA Sequence Design |
link |
Hannes Stark, Bowen Jing,..., Tommi Jaakkola |
| 46 |
2022-09-30 |
Differentially Private Bias-Term Fine-tuning of Foundation Models |
link |
Zhiqi Bu, Yu-Xiang Wang,..., George Karypis |
| 45 |
2024-02-19 |
FiT: Flexible Vision Transformer for Diffusion Model |
link |
Zeyu Lu, ZiDong Wang,..., LEI BAI |
| 45 |
2023-10-11 |
InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining |
link |
Boxin Wang, Wei Ping,..., Bryan Catanzaro |
| 45 |
2024-02-18 |
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark |
link |
Yihua Zhang, Pingzhi Li,..., Tianlong Chen |
| 44 |
2024-02-07 |
Long Is More for Alignment: A Simple but Tough-to-Beat
Baseline for Instruction Fine-Tuning |
link |
Hao Zhao, Maksym Andriushchenko,..., Nicolas Flammarion |
| 43 |
2024-04-12 |
The Illusion of State in State-Space Models |
link |
William Merrill, Jackson Petty, Ashish Sabharwal |
| 43 |
2024-02-02 |
Boximator: Generating Rich and Controllable Motions for Video Synthesis |
link |
Jiawei Wang, Yuchen Zhang,..., Hang Li |
| 43 |
2024-02-28 |
Evaluating Quantized Large Language Models |
link |
Shiyao Li, Xuefei Ning,..., Yu Wang |
| 42 |
2024-02-05 |
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization |
link |
Yang Jin, Zhicheng Sun,..., Yadong MU |
| 42 |
2024-04-18 |
Token-level Direct Preference Optimization |
link |
Yongcheng Zeng, Guoqing Liu,..., Jun Wang |
| 42 |
2023-06-05 |
InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models |
link |
Lichang Chen, Jiuhai Chen,..., Tianyi Zhou |
| 41 |
2024-01-23 |
In-Context Language Learning: Architectures and Algorithms |
link |
Ekin Akyürek, Bailin Wang,..., Jacob Andreas |
| 41 |
2024-02-09 |
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities |
link |
Tara Akhound-Sadegh, Jarrid Rector-Brooks,..., Alexander Tong |
| 41 |
2024-01-10 |
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks |
link |
Xueyu Hu, Ziyu Zhao,..., Fei Wu |
| 40 |
2024-02-04 |
Transolver: A Fast Transformer Solver for PDEs on General
Geometries |
link |
Haixu Wu, Huakun Luo,..., Mingsheng Long |
| 40 |
2024-02-01 |
Merging Multi-Task Models via Weight-Ensembling Mixture of Experts |
link |
Anke Tang, Li Shen,..., Dacheng Tao |
| 40 |
2024-01-30 |
Proactive Detection of Voice Cloning with Localized Watermarking |
link |
Robin San Roman, Pierre Fernandez,..., Tuan Tran |
| 40 |
2023-10-02 |
Prompt-tuning Latent Diffusion Models for Inverse Problems |
link |
Hyungjin Chung, Jong Chul Ye,..., Mauricio Delbracio |
| 39 |
2024-02-02 |
Challenges in Training PINNs: A Loss Landscape Perspective |
link |
Pratik Rathore, Weimu Lei,..., Madeleine Udell |
| 39 |
2024-02-05 |
Large Language Models are Geographically Biased |
link |
Rohin Manvi, Samar Khanna,..., Stefano Ermon |
| 39 |
2024-02-05 |
Flora: Low-Rank Adapters Are Secretly Gradient Compressors |
link |
Yongchang Hao, Yanshuai Cao, Lili Mou |
| 38 |
2023-12-12 |
AI Control: Improving Safety Despite Intentional Subversion |
link |
Ryan Greenblatt, Buck Shlegeris,..., Fabien Roger |
| 38 |
2024-03-19 |
RigorLLM: Resilient Guardrails for Large Language Models against Undesired
Content |
link |
Zhuowen Yuan, Zidi Xiong,..., Bo Li |
| 37 |
2024-02-19 |
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for
Robust Large Vision-Language Models |
link |
Christian Schlarmann, Naman Deep Singh,..., Matthias Hein |
| 37 |
2024-02-08 |
Accurate LoRA-Finetuning Quantization of LLMs via Information Retention |
link |
Haotong Qin, Xudong Ma,..., Michele Magno |
| 37 |
2024-02-06 |
AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls |
link |
Yu Du, Fangyun Wei, Hongyang Zhang |
| 37 |
2024-02-05 |
Representation Surgery for Multi-Task Model Merging |
link |
Enneng Yang, Li Shen,..., Dacheng Tao |
| 36 |
2024-05-02 |
SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters |
link |
Shengsheng Lin, Weiwei Lin,..., Junjie Yang |
| 36 |
2024-02-02 |
A Dynamical Model of Neural Scaling Laws |
link |
Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan |
| 36 |
2024-04-12 |
TSLANet: Rethinking Transformers for Time Series Representation Learning |
link |
Emadeldeen Eldele, Mohamed Ragab,..., Xiaoli Li |
| 36 |
2023-09-13 |
Auto-Regressive Next-Token Predictors are Universal Learners |
link |
eran malach |
| 35 |
2024-02-05 |
Decoding-time Realignment of Language Models |
link |
Tianlin Liu, Shangmin Guo,..., Mathieu Blondel |
| 35 |
2024-02-07 |
Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation |
link |
Luca Beurer-Kellner, Marc Fischer, Martin Vechev |
| 35 |
2024-02-14 |
Feature Reuse and Scaling: Understanding Transfer Learning with Protein
Language Models |
link |
Francesca-Zhoufan Li, Ava P Amini,..., Alex Xijie Lu |
| 35 |
2024-03-17 |
MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of
Data |
link |
Paul Steven Scotti, Mihir Tripathy,..., Tanishq Mathew Abraham |
| 35 |
2024-02-05 |
Guidance with Spherical Gaussian Constraint for Conditional Diffusion |
link |
Lingxiao Yang, Shutong Ding,..., Ye Shi |
| 35 |
2023-12-11 |
Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions
In Context |
link |
Xiang Cheng, Yuxin Chen, Suvrit Sra |
| 34 |
2024-03-28 |
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions |
link |
Kai Zhang, Yi Luan,..., Ming-Wei Chang |
| 34 |
2023-12-06 |
Low-Cost High-Power Membership Inference Attacks |
link |
Sajjad Zarifzadeh, Philippe Liu, Reza Shokri |
| 34 |
2024-04-23 |
NExT: Teaching Large Language Models to Reason about Code
Execution |
link |
Ansong Ni, Miltiadis Allamanis,..., Pengcheng Yin |
| 34 |
2024-02-27 |
Training-Free Long-Context Scaling of Large Language Models |
link |
Chenxin An, Fei Huang,..., Lingpeng Kong |
| 34 |
None |
Position: Will we run out of data? Limits of
LLM scaling based on human-generated data |
link |
Pablo Villalobos, Anson Ho,..., Marius Hobbhahn |
| 34 |
2024-02-07 |
On Computational Limits of Modern Hopfield Models: A Fine-Grained
Complexity Analysis |
link |
Jerry Yao-Chieh Hu, Thomas Lin,..., Han Liu |
| 33 |
2024-01-22 |
DITTO: Diffusion Inference-Time T-Optimization for Music Generation |
link |
Zachary Novack, Julian McAuley,..., Nicholas J. Bryan |
| 33 |
2022-10-10 |
Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score
Based Diffusion Models |
link |
Louis Sharrock, Jack Simons,..., Mark Beaumont |
| 33 |
2024-03-04 |
Differentially Private Synthetic Data via Foundation Model APIs 2:
Text |
link |
Chulin Xie, Zinan Lin,..., Sergey Yekhanin |
| 33 |
2024-02-12 |
Rolling Diffusion Models |
link |
David Ruhe, Jonathan Heek,..., Emiel Hoogeboom |
| 33 |
2024-06-07 |
FlowMM: Generating Materials with Riemannian Flow Matching |
link |
Benjamin Kurt Miller, Ricky T. Q. Chen,..., Brandon M Wood |
| 33 |
2024-02-15 |
Language Models with Conformal Factuality Guarantees |
link |
Christopher Mohri, Tatsunori Hashimoto |
| 33 |
2024-02-23 |
Fast Adversarial Attacks on Language Models In One GPU
Minute |
link |
Vinu Sankar Sadasivan, Shoumik Saha,..., Soheil Feizi |
| 33 |
2024-02-28 |
CogBench: a large language model walks into a psychology
lab |
link |
Julian Coda-Forno, Marcel Binz,..., Eric Schulz |
| 33 |
2024-02-28 |
Diffusion Language Models Are Versatile Protein Learners |
link |
Xinyou Wang, Zaixiang Zheng,..., Quanquan Gu |
| 32 |
2024-02-20 |
A Touch, Vision, and Language Dataset for Multimodal Alignment |
link |
Letian Fu, Gaurav Datta,..., Ken Goldberg |
| 32 |
2024-02-15 |
DE-COP: Detecting Copyrighted Content in Language Models Training Data |
link |
André Vicente Duarte, Xuandong Zhao,..., Lei Li |
| 32 |
2023-05-17 |
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling |
link |
Weijia Xu, Andrzej Banburski, Nebojsa Jojic |
| 32 |
2023-12-11 |
Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication
Cost under 18 Kilobytes |
link |
Zhen Qin, Daoyuan Chen,..., Shuiguang Deng |
| 31 |
2024-04-26 |
Probabilistic Inference in Language Models via Twisted Sequential Monte
Carlo |
link |
Stephen Zhao, Rob Brekelmans,..., Roger Baker Grosse |
| 31 |
2024-05-18 |
Towards Modular LLMs by Building and Reusing a Library
of LoRAs |
link |
Oleksiy Ostapenko, Zhan Su,..., Alessandro Sordoni |
| 31 |
2024-02-01 |
Dense Reward for Free in Reinforcement Learning from Human
Feedback |
link |
Alex James Chan, Hao Sun,..., Mihaela van der Schaar |
| 31 |
2023-02-26 |
Diffusion Model-Augmented Behavioral Cloning |
link |
Shang-Fu Chen, Hsiang-Chun Wang,..., Shao-Hua Sun |
| 31 |
2023-12-08 |
EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language
Models with 3D Parallelism |
link |
Yanxi Chen, Xuchen Pan,..., Jingren Zhou |
| 30 |
2024-02-29 |
Watermark Stealing in Large Language Models |
link |
Nikola Jovanović, Robin Staab, Martin Vechev |
| 30 |
2023-10-23 |
DOGE: Domain Reweighting with Generalization Estimation |
link |
Simin Fan, Matteo Pagliardini, Martin Jaggi |
| 30 |
2024-02-08 |
How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis |
link |
Federico Bianchi, Patrick John Chia,..., James Zou |
| 29 |
2023-10-05 |
Stochastic Interpolants with Data-Dependent Couplings |
link |
Michael Samuel Albergo, Mark Goldstein,..., Eric Vanden-Eijnden |
| 29 |
2024-02-14 |
Transformers, parallel computation, and logarithmic depth |
link |
Clayton Sanford, Daniel Hsu, Matus Telgarsky |
| 29 |
2024-02-13 |
Mixtures of Experts Unlock Parameter Scaling for Deep RL |
link |
Johan Samir Obando Ceron, Ghada Sokar,..., Pablo Samuel Castro |
| 29 |
2024-04-18 |
RoboDreamer: Learning Compositional World Models for Robot Imagination |
link |
Siyuan Zhou, Yilun Du,..., Chuang Gan |
| 29 |
2024-02-15 |
A Human-Inspired Reading Agent with Gist Memory of Very
Long Contexts |
link |
Kuang-Huei Lee, Xinyun Chen,..., Ian Fischer |
| 29 |
2024-03-06 |
Accelerating Convergence of Score-Based Diffusion Models, Provably |
link |
Gen Li, Yu Huang,..., Yuxin Chen |
| 29 |
2024-06-28 |
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation |
link |
Danny Halawi, Alexander Wei,..., Jacob Steinhardt |
| 28 |
2024-02-08 |
Self-Alignment of Large Language Models via Monopolylogue-based Social Scene
Simulation |
link |
Xianghe Pang, Shuo Tang,..., Siheng Chen |
| 28 |
2024-02-03 |
GliDe with a CaPE: A Low-Hassle Method to Accelerate
Speculative Decoding |
link |
Cunxiao Du, Jing Jiang,..., Yang You |
| 28 |
2024-01-11 |
DiffDA: a Diffusion model for weather-scale Data Assimilation |
link |
Langwen Huang, Lukas Gianinazzi,..., Torsten Hoefler |
| 28 |
2024-03-11 |
Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical
Knowledge Enhancement |
link |
Che Liu, Zhongwei Wan,..., Rossella Arcucci |
| 28 |
2024-04-04 |
Uniform Memory Retrieval with Larger Capacity for Modern Hopfield
Models |
link |
Dennis Wu, Jerry Yao-Chieh Hu,..., Han Liu |
| 28 |
2024-04-16 |
Position: Social Choice Should Guide AI Alignment in Dealing
with Diverse Human Feedback |
link |
Vincent Conitzer, Rachel Freedman,..., William S. Zwicker |
| 28 |
2024-02-03 |
A Closer Look at the Limitations of Instruction Tuning |
link |
Sreyan Ghosh, Chandra Kiran Reddy Evuru,..., Dinesh Manocha |
| 27 |
2024-01-09 |
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation |
link |
Mahdi Nikdan, Soroush Tabesh,..., Dan Alistarh |
| 27 |
2023-10-26 |
Codebook Features: Sparse and Discrete Interpretability for Neural Networks |
link |
Alex Tamkin, Mohammad Taufeeque, Noah Goodman |
| 27 |
2024-02-28 |
CLLMs: Consistency Large Language Models |
link |
Siqi Kou, Lanxiang Hu,..., Hao Zhang |
| 27 |
2024-02-26 |
Asymmetry in Low-Rank Adapters of Foundation Models |
link |
Jiacheng Zhu, Kristjan Greenewald,..., Justin Solomon |
| 27 |
2024-02-27 |
DS-Agent: Automated Data Science by Empowering Large Language Models
with Case-Based Reasoning |
link |
Siyuan Guo, Cheng Deng,..., Jun Wang |
| 27 |
2024-02-01 |
Position: Bayesian Deep Learning is Needed in the Age
of Large-Scale AI |
link |
Theodore Papamarkou, Maria Skoularidou,..., Ruqi Zhang |
| 26 |
2024-04-15 |
All-in-one simulation-based inference |
link |
Manuel Gloeckler, Michael Deistler,..., Jakob H. Macke |
| 26 |
2024-03-15 |
Repoformer: Selective Retrieval for Repository-Level Code Completion |
link |
Di Wu, Wasi Uddin Ahmad,..., Xiaofei Ma |
| 26 |
2024-02-03 |
Position: Graph Foundation Models Are Already Here |
link |
Haitao Mao, Zhikai Chen,..., Jiliang Tang |
| 26 |
2024-02-14 |
Premise Order Matters in Reasoning with Large Language Models |
link |
Xinyun Chen, Ryan Andrew Chi,..., Denny Zhou |
| 26 |
2024-02-29 |
Dual Operating Modes of In-Context Learning |
link |
Ziqian Lin, Kangwook Lee |
| 26 |
2024-02-09 |
Feedback Loops With Language Models Drive In-Context Reward Hacking |
link |
Alexander Pan, Erik Jones,..., Jacob Steinhardt |
| 26 |
2023-09-18 |
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts |
link |
Jiang-Xin Shi, Tong Wei,..., Yu-Feng Li |
| 26 |
2024-05-16 |
LLM and Simulation as Bilevel Optimizers: A New Paradigm
to Advance Physical Scientific Discovery |
link |
Pingchuan Ma, Tsun-Hsuan Wang,..., Wojciech Matusik |
| 26 |
2024-02-05 |
The Benefits of Reusing Batches for Gradient Descent in
Two-Layer Networks: Breaking the Curse of Information and Leap Exponents |
link |
Yatin Dandi, Emanuele Troiani,..., Florent Krzakala |
| 26 |
2024-02-14 |
Position: Topological Deep Learning is the New Frontier for
Relational Learning |
link |
Theodore Papamarkou, Tolga Birdal,..., Ghada Zamzmi |
| 25 |
2024-04-10 |
What needs to go right for an induction head?
A mechanistic study of in-context learning circuits and their formation |
link |
Aaditya K Singh, Ted Moskovitz,..., Andrew M Saxe |
| 25 |
2024-02-09 |
Particle Denoising Diffusion Sampler |
link |
Angus Phillips, Hai-Dang Dau,..., Arnaud Doucet |
| 25 |
2024-02-08 |
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers |
link |
Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi,..., Wojciech Samek |
| 25 |
2024-03-21 |
Protein Conformation Generation via Force-Guided SE(3) Diffusion Models |
link |
YanWang, Lihao Wang,..., Quanquan Gu |
| 25 |
2023-12-19 |
Curated LLM: Synergy of LLMs and Data Curation for
tabular augmentation in low-data regimes |
link |
Nabeel Seedat, Nicolas Huynh,..., Mihaela van der Schaar |
| 25 |
2024-04-04 |
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models |
link |
Jerry Yao-Chieh Hu, Pei-Hsuan Chang,..., Han Liu |
| 25 |
2024-01-29 |
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in
RLHF |
link |
Banghua Zhu, Michael Jordan, Jiantao Jiao |
| 25 |
2023-10-09 |
Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and
Binding Site Design |
link |
Hannes Stark, Bowen Jing,..., Tommi Jaakkola |
| 25 |
2023-06-07 |
Don't trust your eyes: on the (un)reliability of feature
visualizations |
link |
Robert Geirhos, Roland S. Zimmermann,..., Been Kim |
| 25 |
2024-05-05 |
Parameter-Efficient Fine-Tuning with Discrete Fourier Transform |
link |
Ziqi Gao, Qichao Wang,..., Jia Li |
| 24 |
2024-03-02 |
SceneCraft: An LLM Agent for Synthesizing 3D Scenes as
Blender Code |
link |
Ziniu Hu, Ahmet Iscen,..., Alireza Fathi |
| 24 |
2023-10-26 |
CompeteAI: Understanding the Competition Dynamics of Large Language Model-based
Agents |
link |
Qinlin Zhao, Jindong Wang,..., Xing Xie |
| 24 |
2024-02-26 |
Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning |
link |
Michael Matthews, Michael Beukman,..., Jakob Nicolaus Foerster |
| 24 |
2024-03-04 |
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving |
link |
Foteini Strati, Sara McAllister,..., Ana Klimovic |
| 24 |
2023-10-05 |
Agent Instructs Large Language Models to be General Zero-Shot
Reasoners |
link |
Nicholas Crispino, Kyle Montgomery,..., Chenguang Wang |
| 24 |
2024-03-06 |
On the Origins of Linear Representations in Large Language
Models |
link |
Yibo Jiang, Goutham Rajendran,..., Victor Veitch |
| 24 |
2024-02-21 |
D-Flow: Differentiating through Flows for Controlled Generation |
link |
Heli Ben-Hamu, Omri Puny,..., Yaron Lipman |
| 24 |
2024-03-18 |
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs
Under Compression |
link |
Junyuan Hong, Jinhao Duan,..., Bo Li |
| 24 |
2024-04-22 |
Align Your Steps: Optimizing Sampling Schedules in Diffusion Models |
link |
Amirmojtaba Sabour, Sanja Fidler, Karsten Kreis |
| 24 |
None |
CaM: Cache Merging for Memory-efficient LLMs Inference |
link |
Yuxin Zhang, Yuxuan Du,..., Rongrong Ji |
| 24 |
2024-01-05 |
VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model |
link |
Pengying Wu, Yao Mu,..., Chang Liu |
| 23 |
2024-01-07 |
The Stronger the Diffusion Model, the Easier the Backdoor:
Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline |
link |
Haonan Wang, Qianli Shen,..., Kenji Kawaguchi |
| 23 |
2024-06-05 |
Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large
Language Models |
link |
Peijie Dong, Lujun Li,..., Xiaowen Chu |
| 23 |
None |
The Emergence of Reproducibility and Consistency in Diffusion Models |
link |
Huijie Zhang, Jinfan Zhou,..., Qing Qu |
| 23 |
2024-02-08 |
In-Context Principle Learning from Mistakes |
link |
Tianjun Zhang, Aman Madaan,..., Uri Alon |
| 23 |
2023-10-02 |
FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language
Models |
link |
Jingwei Sun, Ziyue Xu,..., Holger R Roth |
| 23 |
2024-03-03 |
Theoretical insights for diffusion guidance: A case study for
Gaussian mixture models |
link |
Yuchen Wu, Minshuo Chen,..., Yuting Wei |
| 23 |
2023-10-09 |
Generalized Neural Collapse for a Large Number of Classes |
link |
Jiachen Jiang, Jinxin Zhou,..., Zhihui Zhu |
| 23 |
2024-01-24 |
Can AI Assistants Know What They Don't Know? |
link |
Qinyuan Cheng, Tianxiang Sun,..., Xipeng Qiu |
| 22 |
2024-02-15 |
SAMformer: Unlocking the Potential of Transformers in Time Series
Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention |
link |
Romain Ilbert, Ambroise Odonnat,..., Ievgen Redko |
| 22 |
2024-02-08 |
Memory Consolidation Enables Long-Context Video Understanding |
link |
Ivana Balazevic, Yuge Shi,..., Olivier J Henaff |
| 22 |
2024-02-27 |
Variational Learning is Effective for Large Deep Networks |
link |
Yuesong Shen, Nico Daheim,..., Thomas Möllenhoff |
| 22 |
2024-02-02 |
Online conformal prediction with decaying step sizes |
link |
Anastasios Nikolas Angelopoulos, Rina Barber, Stephen Bates |
| 22 |
2024-02-13 |
A Dense Reward View on Aligning Text-to-Image Diffusion with
Preference |
link |
Shentao Yang, Tianqi Chen, Mingyuan Zhou |
| 22 |
2024-02-15 |
OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large
Language Models |
link |
Ali AhmadiTeshnizi, Wenzhi Gao, Madeleine Udell |
| 22 |
2024-03-06 |
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training |
link |
Zhongkai Hao, Chang Su,..., Jun Zhu |
| 22 |
2023-10-04 |
Assessing Large Language Models on Climate Information |
link |
Jannis Bulian, Mike S. Schäfer,..., Nadine Strauss |
| 22 |
2024-01-18 |
Improving fine-grained understanding in image-text pre-training |
link |
Ioana Bica, Anastasija Ilic,..., Jovana Mitrovic |
| 22 |
2024-03-21 |
An Analysis of Linear Time Series Forecasting Models |
link |
William Toner, Luke Nicholas Darlow |
| 22 |
2024-06-22 |
video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models |
link |
Guangzhi Sun, Wenyi Yu,..., Chao Zhang |
| 22 |
None |
Position: TrustLLM: Trustworthiness in Large Language Models |
link |
Yue Huang, Lichao Sun,..., Yue Zhao |
| 22 |
2023-10-11 |
A Resilient and Accessible Distribution-Preserving Watermark for Large Language
Models |
link |
Yihan Wu, Zhengmian Hu,..., Heng Huang |
| 22 |
2024-02-19 |
Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language
Models |
link |
Didi Zhu, Zhongyisun Sun,..., Kun Kuang |
| 22 |
2023-05-27 |
CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers |
link |
Dachuan Shi, Chaofan Tao,..., Jiaqi Wang |
| 21 |
2024-02-22 |
Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion |
link |
Yujia Huang, Adishree Ghatare,..., Yisong Yue |
| 21 |
2024-03-30 |
Linguistic Calibration of Long-Form Generations |
link |
Neil Band, Xuechen Li,..., Tatsunori Hashimoto |
| 21 |
None |
R2E: Turning any Github Repository into a Programming Agent
Environment |
link |
Naman Jain, Manish Shetty,..., Ion Stoica |
| 21 |
2024-02-22 |
A Language Model’s Guide Through Latent Space |
link |
Dimitri von Rütte, Sotiris Anagnostidis,..., Thomas Hofmann |
| 21 |
2024-03-26 |
Mechanistic Design and Scaling of Hybrid Architectures |
link |
Michael Poli, Armin W Thomas,..., Stefano Massaroli |
| 21 |
2024-02-26 |
Feedback Efficient Online Fine-Tuning of Diffusion Models |
link |
Masatoshi Uehara, Yulai Zhao,..., Tommaso Biancalani |
| 21 |
2024-05-28 |
AI Alignment with Changing and Influenceable Reward Functions |
link |
Micah Carroll, Davis Foote,..., Anca Dragan |
| 21 |
2024-02-25 |
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis |
link |
Yao Mu, Junting Chen,..., Ping Luo |
| 21 |
2023-12-06 |
Generalization to New Sequential Decision Making Tasks with In-Context
Learning |
link |
Sharath Chandra Raparthy, Eric Hambro,..., Roberta Raileanu |
| 21 |
2024-03-03 |
In-Context Sharpness as Alerts: An Inner Representation Perspective for
Hallucination Mitigation |
link |
Shiqi Chen, Miao Xiong,..., Junxian He |
| 21 |
2024-05-21 |
How Universal Polynomial Bases Enhance Spectral Graph Neural Networks:
Heterophily, Over-smoothing, and Over-squashing |
link |
Keke Huang, Yu Guang Wang,..., Pietro Lio |
| 21 |
2024-02-03 |
Improving Diffusion Models for Inverse Problems Using Optimal Posterior
Covariance |
link |
Xinyu Peng, Ziyang Zheng,..., Hongkai Xiong |
| 21 |
2024-02-06 |
Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains |
link |
Junhong Shen, Neil Tenenholtz,..., Nicolo Fusi |
| 21 |
2023-10-10 |
Conformal Prediction for Deep Classifier via Label Ranking |
link |
Jianguo Huang, HuaJun Xi,..., Hongxin Wei |
| 21 |
2023-10-20 |
Equivariant Deep Weight Space Alignment |
link |
Aviv Navon, Aviv Shamsian,..., Haggai Maron |
| 21 |
2024-02-07 |
A Sober Look at LLMs for Material Discovery: Are
They Actually Good for Bayesian Optimization Over Molecules? |
link |
Agustinus Kristiadi, Felix Strieth-Kalthoff,..., Geoff Pleiss |
| 21 |
2023-02-04 |
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction
tasks |
link |
Shashank Agnihotri, Steffen Jung, Margret Keuper |
| 20 |
2024-03-19 |
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data
Flow and Per-Block Quantization |
link |
Haocheng Xi, Yuxiang Chen,..., Jun Zhu |
| 20 |
2024-03-05 |
Time Weaver: A Conditional Time Series Generation Model |
link |
Sai Shankar Narasimhan, Shubhankar Agarwal,..., Sandeep P. Chinchali |
| 20 |
2024-03-06 |
Conformal prediction for multi-dimensional time series by ellipsoidal sets |
link |
Chen Xu, Hanyang Jiang, Yao Xie |
| 20 |
2024-02-23 |
Minimax Optimality of Score-based Diffusion Models: Beyond the Density
Lower Bound Assumptions |
link |
Kaihong Zhang, Heqi Yin,..., Jingbo Liu |
| 20 |
2024-06-22 |
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language
Models without Training through Attention Calibration |
link |
Zhongzhi Yu, Zheng Wang,..., Yingyan Celine Lin |
| 20 |
2024-03-20 |
Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models
with Noisy Data |
link |
Giannis Daras, Alex Dimakis, Constantinos Costis Daskalakis |
| 20 |
2024-02-04 |
Selecting Large Language Model to Fine-tune via Rectified Scaling
Law |
link |
Haowei Lin, Baizhou Huang,..., Yitao Liang |
| 20 |
2024-02-08 |
Training Large Language Models for Reasoning through Reverse Curriculum
Reinforcement Learning |
link |
Zhiheng Xi, Wenxiang Chen,..., Xuanjing Huang |
| 20 |
2023-11-29 |
Should we be going MAD? A Look at Multi-Agent
Debate Strategies for LLMs |
link |
Andries Petrus Smit, Nathan Grinsztajn,..., Arnu Pretorius |
| 20 |
2023-04-03 |
Chain-of-Thought Predictive Control |
link |
Zhiwei Jia, Vineet Thumuluri,..., Hao Su |
| 20 |
2020-11-29 |
Scaling Down Deep Learning with MNIST-1D |
link |
Samuel James Greydanus, Dmitry Kobak |
| 20 |
2024-02-05 |
C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models |
link |
Mintong Kang, Nezihe Merve Gürel,..., Bo Li |
| 20 |
2024-02-01 |
Efficient Exploration for LLMs |
link |
Vikranth Dwaracherla, Seyed Mohammad Asghari,..., Benjamin Van Roy |
| 20 |
2024-02-01 |
Getting the most out of your tokenizer for pre-training
and domain adaptation |
link |
Gautier Dagan, Gabriel Synnaeve, Baptiste Roziere |
| 20 |
2024-02-14 |
SLEB: Streamlining LLMs through Redundancy Verification and Elimination of
Transformer Blocks |
link |
Jiwon Song, Kyungseok Oh,..., jae-joon kim |
| 20 |
2024-02-26 |
Disentangled 3D Scene Generation with Layout Learning |
link |
Dave Epstein, Ben Poole,..., Aleksander Holynski |
| 20 |
2023-12-28 |
Non-Vacuous Generalization Bounds for Large Language Models |
link |
Sanae Lotfi, Marc Anton Finzi,..., Andrew Gordon Wilson |
| 19 |
None |
DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of
Diffusion Generated Images |
link |
Baoying Chen, Jishen Zeng,..., Rui Yang |
| 19 |
2024-07-08 |
Scaling Exponents Across Parameterizations and Optimizers |
link |
Katie E Everett, Lechao Xiao,..., Jeffrey Pennington |
| 19 |
2024-02-23 |
Deep Networks Always Grok and Here is Why |
link |
Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk |
| 19 |
2024-02-28 |
Characterizing Truthfulness in Large Language Model Generations with Local
Intrinsic Dimension |
link |
Fan Yin, Jayanth Srinivasa, Kai-Wei Chang |
| 19 |
2022-06-10 |
Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone
Inclusion |
link |
Yang Cai, Argyris Oikonomou, Weiqiang Zheng |
| 19 |
2024-04-30 |
Modeling Caption Diversity in Contrastive Vision-Language Pretraining |
link |
Samuel Lavoie, Polina Kirichenko,..., Nicolas Ballas |
| 19 |
2023-08-14 |
Position: Key Claims in LLM Research Have a Long
Tail of Footnotes |
link |
Anna Rogers, Sasha Luccioni |
| 19 |
2024-05-16 |
IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency |
link |
Linshan Hou, Ruili Feng,..., Yiming Li |
| 19 |
2024-01-23 |
TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic
Tasks |
link |
Zhiruo Wang, Graham Neubig, Daniel Fried |
| 19 |
2023-10-11 |
A Theory of Non-Linear Feature Learning with One Gradient
Step in Two-Layer Neural Networks |
link |
Behrad Moniri, Donghwan Lee,..., Edgar Dobriban |
| 19 |
2022-11-09 |
Few-Shot Character Understanding in Movies as an Assessment to
Meta-Learning of Theory-of-Mind |
link |
Mo Yu, Qiujing Wang,..., Jie Zhou |
| 19 |
2023-08-25 |
Learning to Intervene on Concept Bottlenecks |
link |
David Steinmann, Wolfgang Stammer,..., Kristian Kersting |
| 19 |
2024-02-26 |
Neural Operators with Localized Integral and Differential Kernels |
link |
Miguel Liu-Schiaffini, Julius Berner,..., Anima Anandkumar |
| 19 |
2023-02-07 |
Graph Generation with Diffusion Mixture |
link |
Jaehyeong Jo, Dongki Kim, Sung Ju Hwang |
| 19 |
2024-04-04 |
BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized
Sparse Modern Hopfield Model |
link |
Chenwei Xu, Yu-Chao Huang,..., Han Liu |
| 18 |
2024-02-02 |
Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics
on the Attention Landscape |
link |
Juno Kim, Taiji Suzuki |
| 18 |
2023-09-28 |
Discovering Environments with XRM |
link |
Mohammad Pezeshki, Diane Bouchacourt,..., David Lopez-Paz |
| 18 |
2024-09-03 |
Interpreting and Improving Large Language Models in Arithmetic Calculation |
link |
Wei Zhang, Chaoqun Wan,..., Jieping Ye |
| 18 |
2024-04-02 |
Test-Time Model Adaptation with Only Forward Passes |
link |
Shuaicheng Niu, Chunyan Miao,..., Peilin Zhao |
| 18 |
2023-12-02 |
Second-Order Uncertainty Quantification: A Distance-Based Approach |
link |
Yusuf Sale, Viktor Bengs,..., Eyke Hüllermeier |
| 18 |
2024-02-14 |
Copyright Traps for Large Language Models |
link |
Matthieu Meeus, Igor Shilov,..., Yves-Alexandre de Montjoye |
| 18 |
2024-02-07 |
Causal Representation Learning from Multiple Distributions: A General Setting |
link |
Kun Zhang, Shaoan Xie,..., Yujia Zheng |
| 18 |
2024-04-17 |
Learning with 3D rotations, a hitchhiker's guide to SO(3) |
link |
Andreas René Geist, Jonas Frey,..., Georg Martius |
| 18 |
2024-02-27 |
Case-Based or Rule-Based: How Do Transformers Do the Math? |
link |
Yi Hu, Xiaojuan Tang,..., Muhan Zhang |
| 18 |
2024-05-13 |
PARDEN, Can You Repeat That? Defending against Jailbreaks via
Repetition |
link |
Ziyang Zhang, Qizhen Zhang, Jakob Nicolaus Foerster |
| 18 |
2024-03-18 |
Larimar: Large Language Models with Episodic Memory Control |
link |
Payel Das, Subhajit Chaudhury,..., Pin-Yu Chen |
| 18 |
2024-02-13 |
Hybrid Inverse Reinforcement Learning |
link |
Juntao Ren, Gokul Swamy,..., Sanjiban Choudhury |
| 18 |
2023-10-02 |
Fool Your (Vision and) Language Model with Embarrassingly Simple
Permutations |
link |
Yongshuo Zong, Tingyang Yu,..., Timothy Hospedales |
| 18 |
2024-02-05 |
Distinguishing the Knowable from the Unknowable with Language Models |
link |
Gustaf Ahdritz, Tian Qin,..., Benjamin L. Edelman |
| 18 |
2024-02-19 |
In value-based deep reinforcement learning, a pruned network is
a good network |
link |
Johan Samir Obando Ceron, Aaron Courville, Pablo Samuel Castro |
| 18 |
2024-04-18 |
MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space |
link |
Yanru Qu, Keyue Qiu,..., Wei-Ying Ma |
| 18 |
2024-01-25 |
Adaptive Text Watermark for Large Language Models |
link |
Yepeng Liu, Yuheng Bu |
| 18 |
2024-03-16 |
SelfIE: Self-Interpretation of Large Language Model Embeddings |
link |
Haozhe Chen, Carl Vondrick, Chengzhi Mao |
| 18 |
2023-10-11 |
Language Models as Semantic Indexers |
link |
Bowen Jin, Hansi Zeng,..., Xianfeng Tang |
| 18 |
2024-01-28 |
An Information-Theoretic Analysis of In-Context Learning |
link |
Hong Jun Jeon, Jason D. Lee,..., Benjamin Van Roy |
| 18 |
2024-01-24 |
Conformal Prediction Sets Improve Human Decision Making |
link |
Jesse C. Cresswell, Yi Sui,..., Noël Vouitsis |
| 18 |
2024-02-23 |
Foundation Policies with Hilbert Representations |
link |
Seohong Park, Tobias Kreiman, Sergey Levine |
| 18 |
2024-02-03 |
Image Fusion via Vision-Language Model |
link |
Zixiang Zhao, Lilun Deng,..., Luc Van Gool |
| 17 |
2024-05-22 |
Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam
Generation |
link |
Gauthier Guinet, Behrooz Omidvar-Tehrani,..., Laurent Callot |
| 17 |
2024-01-22 |
APT: Adaptive Pruning and Tuning Pretrained Language Models for
Efficient Training and Inference |
link |
Bowen Zhao, Hannaneh Hajishirzi, Qingqing Cao |
| 17 |
2024-05-03 |
Auto-Encoding Morph-Tokens for Multimodal LLM |
link |
Kaihang Pan, Siliang Tang,..., Hanwang Zhang |
| 17 |
2024-03-01 |
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson
of Reinforcement Learning |
link |
Michal Nauman, Michał Bortkiewicz,..., Marek Cygan |
| 17 |
2024-10-10 |
Can Looped Transformers Learn to Implement Multi-step Gradient Descent
for In-context Learning? |
link |
Khashayar Gatmiry, Nikunj Saunshi,..., Sanjiv Kumar |
| 17 |
2024-02-21 |
Privacy-Preserving Instructions for Aligning Large Language Models |
link |
Da Yu, Peter Kairouz,..., Zheng Xu |
| 17 |
2023-08-31 |
On the Implicit Bias of Adam |
link |
Matias D. Cattaneo, Jason Matthew Klusowski, Boris Shigida |
| 17 |
2023-05-18 |
Emergent Representations of Program Semantics in Language Models Trained
on Programs |
link |
Charles Jin, Martin Rinard |
| 17 |
2024-02-21 |
Do Efficient Transformers Really Save Computation? |
link |
Kai Yang, Jan Ackermann,..., Liwei Wang |
| 17 |
2024-02-07 |
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay |
link |
Natasha Butt, Blazej Manczak,..., Taco Cohen |
| 17 |
2024-02-21 |
From Self-Attention to Markov Models: Unveiling the Dynamics of
Generative Transformers |
link |
Muhammed Emrullah Ildiz, Yixiao HUANG,..., Samet Oymak |
| 17 |
2024-06-03 |
A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization |
link |
Sebastian Sanokowski, Sepp Hochreiter, Sebastian Lehner |
| 17 |
2024-05-14 |
Compositional Text-to-Image Generation with Dense Blob Representations |
link |
Weili Nie, Sifei Liu,..., Arash Vahdat |
| 17 |
2024-04-22 |
A Multimodal Automated Interpretability Agent |
link |
Tamar Rott Shaham, Sarah Schwettmann,..., Antonio Torralba |
| 17 |
2023-10-16 |
A Computational Framework for Solving Wasserstein Lagrangian Flows |
link |
Kirill Neklyudov, Rob Brekelmans,..., Alireza Makhzani |
| 17 |
2024-02-25 |
Equivariant Frames and the Impossibility of Continuous Canonicalization |
link |
Nadav Dym, Hannah Lawrence, Jonathan W. Siegel |
| 17 |
2024-01-20 |
Make-A-Shape: a Ten-Million-scale 3D Shape Model |
link |
Ka-Hei Hui, Aditya Sanghi,..., Chi-Wing Fu |
| 17 |
2024-05-18 |
AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models
via Watermark LoRA |
link |
Weitao Feng, Wenbo Zhou,..., Nenghai Yu |
| 17 |
2024-05-03 |
PICLe: Eliciting Diverse Behaviors from Large Language Models with
Persona In-Context Learning |
link |
Hyeong Kyu Choi, Yixuan Li |
| 16 |
2023-02-23 |
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand
Binding Site Prediction |
link |
yang zhang, Zhewei Wei,..., Wenbing Huang |
| 16 |
2024-02-16 |
Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs |
link |
Yeonhong Park, Jake Hyun,..., Jae W. Lee |
| 16 |
2024-02-07 |
Asymptotics of feature learning in two-layer networks after one
gradient-step |
link |
Hugo Cui, Luca Pesce,..., Bruno Loureiro |
| 16 |
2024-02-14 |
Instruction Tuning for Secure Code Generation |
link |
Jingxuan He, Mark Vero,..., Martin Vechev |
| 16 |
2024-10-29 |
Cell2Sentence: Teaching Large Language Models the Language of Biology |
link |
Daniel Levine, Syed A Rizvi,..., David van Dijk |
| 16 |
2024-02-29 |
Smooth Tchebycheff Scalarization for Multi-Objective Optimization |
link |
Xi Lin, Xiaoyuan Zhang,..., Qingfu Zhang |
| 16 |
2024-06-11 |
Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for
Sampling |
link |
Denis Blessing, Xiaogang Jia,..., Gerhard Neumann |
| 16 |
2024-02-13 |
eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale,
High-quality Instruction Data |
link |
Bo Peng, Xinyi Ling,..., Xia Ning |
| 16 |
2024-02-12 |
Active Preference Learning for Large Language Models |
link |
William Muldrew, Peter Hayes,..., David Barber |
| 16 |
2024-03-20 |
Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes |
link |
Yifan Chen, Mark Goldstein,..., Eric Vanden-Eijnden |
| 16 |
2024-03-04 |
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary
Time Series as Exogenous Variables |
link |
Jiecheng Lu, Xu Han,..., Shihao Yang |
| 16 |
2024-05-06 |
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning
in Large Language Models |
link |
George-Octavian Bărbulescu, Peter Triantafillou |
| 16 |
2023-07-21 |
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width
Guarantees and Benefits of Complex Eigenvalues |
link |
Antonio Orvieto, Soham De,..., Samuel L Smith |
| 16 |
2024-02-06 |
MusicRL: Aligning Music Generation to Human Preferences |
link |
Geoffrey Cideron, Sertan Girgin,..., Andrea Agostinelli |
| 16 |
2024-02-12 |
Benchmarking and Building Long-Context Retrieval Models with LoCo and
M2-BERT |
link |
Jon Saad-Falcon, Daniel Y Fu,..., Christopher Re |
| 16 |
2024-02-05 |
Graph-enhanced Large Language Models in Asynchronous Plan Reasoning |
link |
Fangru Lin, Emanuele La Malfa,..., Janet B. Pierrehumbert |
| 16 |
2023-12-20 |
Learning and Forgetting Unsafe Examples in Large Language Models |
link |
Jiachen Zhao, Zhun Deng,..., Mengye Ren |
| 16 |
2024-09-09 |
TERD: A Unified Framework for Safeguarding Diffusion Models Against
Backdoors |
link |
Yichuan Mo, Hui Huang,..., Yisen Wang |
| 16 |
2024-02-05 |
Position: What Can Large Language Models Tell Us about
Time Series Analysis |
link |
Ming Jin, YiFan Zhang,..., Qingsong Wen |
| 16 |
2023-11-15 |
ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy |
link |
Kirill Vishniakov, Zhiqiang Shen, Zhuang Liu |
| 16 |
2023-05-27 |
Matrix Information Theory for Self-Supervised Learning |
link |
Yifan Zhang, Zhiquan Tan,..., Yang Yuan |
| 15 |
2024-03-07 |
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks |
link |
Linyuan Gong, Sida Wang,..., Alvin Cheung |
| 15 |
2023-11-23 |
Scalable AI Safety via Doubly-Efficient Debate |
link |
Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras |
| 15 |
2024-08-18 |
Parameterized Physics-informed Neural Networks for Parameterized PDEs |
link |
Woojin Cho, Minju Jo,..., Noseong Park |
| 15 |
2023-12-26 |
Generalization in Kernel Regression Under Realistic Assumptions |
link |
Daniel Barzilai, Ohad Shamir |
| 15 |
2024-02-27 |
RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences |
link |
Jie Cheng, Gang Xiong,..., Fei-Yue Wang |
| 15 |
2024-06-01 |
Slow and Steady Wins the Race: Maintaining Plasticity with
Hare and Tortoise Networks |
link |
Hojoon Lee, Hyeonseo Cho,..., Clare Lyle |
| 15 |
2023-07-14 |
Graph Positional and Structural Encoder |
link |
Semih Cantürk, Renming Liu,..., Ladislav Rampášek |
| 15 |
2024-06-14 |
Towards Scalable and Versatile Weight Space Learning |
link |
Konstantin Schürholt, Michael W. Mahoney, Damian Borth |
| 15 |
2024-06-02 |
Full-Atom Peptide Design based on Multi-modal Flow Matching |
link |
Jiahan Li, Chaoran Cheng,..., Jianzhu Ma |
| 15 |
None |
UniAudio: Towards Universal Audio Generation with Large Language Models |
link |
Dongchao Yang, Jinchuan Tian,..., Helen M. Meng |
| 15 |
2023-09-08 |
Graph Neural Networks Use Graphs When They Shouldn't |
link |
Maya Bechler-Speicher, Ido Amos,..., Amir Globerson |
| 15 |
2024-06-03 |
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer |
link |
Ding Jia, Jianyuan Guo,..., Xinghao Chen |
| 15 |
2024-05-20 |
Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using
Spatio-Temporal Slices |
link |
Nathaniel Cohen, Vladimir Kulikov,..., Tomer Michaeli |
| 14 |
2024-07-11 |
Position: Measure Dataset Diversity, Don't Just Claim It |
link |
Dora Zhao, Jerone Andrews,..., Alice Xiang |
| 14 |
2024-02-04 |
Revisiting the Power of Prompt for Visual Tuning |
link |
Yuzhu Wang, Lechao Cheng,..., Meng Wang |
| 14 |
2024-04-17 |
Decomposing and Editing Predictions by Modeling Model Computation |
link |
Harshay Shah, Andrew Ilyas, Aleksander Madry |
| 14 |
2024-05-18 |
On the Trajectory Regularity of ODE-based Diffusion Sampling |
link |
Defang Chen, Zhenyu Zhou,..., Siwei Lyu |
| 14 |
2024-04-11 |
Lyapunov-stable Neural Control for State and Output Feedback: A
Novel Formulation |
link |
Lujie Yang, Hongkai Dai,..., Huan Zhang |
| 14 |
2023-11-16 |
Structured Chemistry Reasoning with Large Language Models |
link |
Siru Ouyang, Zhuosheng Zhang,..., Lianhui Qin |
| 14 |
2024-02-27 |
Automated Statistical Model Discovery with Language Models |
link |
Michael Y. Li, Emily Fox, Noah Goodman |
| 14 |
2024-03-12 |
BAGEL: Bootstrapping Agents by Guiding Exploration with Language |
link |
Shikhar Murty, Christopher D Manning,..., Kenton Lee |
| 14 |
2024-02-02 |
MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning
in Smaller Language Models |
link |
Justin Chen, Swarnadeep Saha,..., Mohit Bansal |
| 14 |
2024-02-23 |
How Do Nonlinear Transformers Learn and Generalize in In-Context
Learning? |
link |
Hongkang Li, Meng Wang,..., Pin-Yu Chen |
| 14 |
2024-02-04 |
Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models |
link |
Fangzhao Zhang, Mert Pilanci |
| 14 |
2023-06-05 |
Seizing Serendipity: Exploiting the Value of Past Success in
Off-Policy Actor-Critic |
link |
Tianying Ji, Yu Luo,..., Huazhe Xu |
| 14 |
2024-02-02 |
Simulation of Graph Algorithms with Looped Transformers |
link |
Artur Back de Luca, Kimon Fountoulakis |
| 14 |
None |
Diffusion Models Encode the Intrinsic Dimension of Data Manifolds |
link |
Jan Pawel Stanczuk, Georgios Batzolis,..., Carola-Bibiane Schönlieb |
| 14 |
2024-03-30 |
Privacy Backdoors: Stealing Data with Corrupted Pretrained Models |
link |
Shanglun Feng, Florian Tramèr |
| 14 |
2024-02-23 |
Human vs. Generative AI in Content Creation Competition: Symbiosis
or Conflict? |
link |
Fan Yao, Chuanhao Li,..., Haifeng Xu |
| 14 |
2023-12-20 |
In-Context Reinforcement Learning for Variable Action Spaces |
link |
Viacheslav Sinii, Alexander Nikulin,..., Sergey Kolesnikov |
| 14 |
2023-12-18 |
The Good, The Bad, and Why: Unveiling Emotions in
Generative AI |
link |
CHENG LI, Jindong Wang,..., Xing Xie |
| 14 |
2024-02-02 |
BAT: Learning to Reason about Spatial Sounds with Large
Language Models |
link |
Zhisheng Zheng, Puyuan Peng,..., David Harwath |
| 14 |
2023-10-11 |
LLark: A Multimodal Instruction-Following Language Model for Music |
link |
Joshua P Gardner, Simon Durand,..., Rachel M Bittner |
| 14 |
2024-02-10 |
Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF |
link |
Han Shen, Zhuoran Yang, Tianyi Chen |
| 14 |
2023-12-08 |
Membership Inference Attacks on Diffusion Models via Quantile Regression |
link |
Shuai Tang, Steven Wu,..., Aaron Roth |
| 14 |
2024-02-28 |
Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for
Large Language Models |
link |
Mingjia Huo, Sai Ashish Somayajula,..., Pengtao Xie |
| 14 |
2023-11-15 |
Converting Transformers to Polynomial Form for Secure Inference Over
Homomorphic Encryption |
link |
Itamar Zimerman, Moran Baruch,..., Lior Wolf |
| 14 |
2023-12-06 |
Interpretability Illusions in the Generalization of Simplified Models |
link |
Dan Friedman, Andrew Kyle Lampinen,..., Asma Ghandeharioun |
| 13 |
2024-02-11 |
How do Large Language Models Navigate Conflicts between Honesty
and Helpfulness? |
link |
Ryan Liu, Theodore Sumers,..., Thomas L. Griffiths |
| 13 |
2024-02-19 |
LoRA Training in the NTK Regime has No Spurious
Local Minima |
link |
Uijeong Jang, Jason D. Lee, Ernest K. Ryu |
| 13 |
2023-10-03 |
High-Probability Convergence for Composite and Distributed Stochastic Minimization and
Variational Inequalities with Heavy-Tailed Noise |
link |
Eduard Gorbunov, Abdurakhmon Sadiev,..., Peter Richtárik |
| 13 |
2024-02-05 |
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation
Problem |
link |
Maciej Wolczyk, Bartłomiej Cupiał,..., Piotr Miłoś |
| 13 |
2024-02-26 |
CARTE: Pretraining and Transfer for Tabular Learning |
link |
Myung Jun Kim, Leo Grinsztajn, Gael Varoquaux |
| 13 |
2023-06-02 |
Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning |
link |
Xiangzhe Kong, Wenbing Huang, Yang Liu |
| 13 |
2024-01-29 |
ReGAL: Refactoring Programs to Discover Generalizable Abstractions |
link |
Elias Stengel-Eskin, Archiki Prasad, Mohit Bansal |
| 13 |
2024-02-05 |
On Least Square Estimation in Softmax Gating Mixture of
Experts |
link |
Huy Nguyen, Nhat Ho, Alessandro Rinaldo |
| 13 |
2024-02-05 |
Light and Optimal Schrödinger Bridge Matching |
link |
Nikita Gushchin, Sergei Kholkin,..., Alexander Korotin |
| 13 |
2024-06-10 |
A Statistical Theory of Regularization-Based Continual Learning |
link |
Xuyang Zhao, Huiyuan Wang,..., Wei Lin |
| 13 |
2024-04-14 |
Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies |
link |
Brian R. Bartoldson, James Diffenderfer,..., Bhavya Kailkhura |
| 13 |
2024-05-02 |
On Mechanistic Knowledge Localization in Text-to-Image Generative Models |
link |
Samyadeep Basu, Keivan Rezaei,..., Soheil Feizi |
| 13 |
2024-06-02 |
Is In-Context Learning in Large Language Models Bayesian? A
Martingale Perspective |
link |
Fabian Falck, Ziyu Wang, Christopher C. Holmes |
| 13 |
2024-04-16 |
Fewer Truncations Improve Language Modeling |
link |
Hantian Ding, Zijian Wang,..., Stefano Soatto |
| 13 |
2024-03-13 |
A Sparsity Principle for Partially Observable Causal Representation Learning |
link |
Danru Xu, Dingling Yao,..., Sara Magliacane |
| 13 |
2024-02-15 |
Representation Surgery: Theory and Practice of Affine Steering |
link |
Shashwat Singh, Shauli Ravfogel,..., Ponnurangam Kumaraguru |
| 13 |
2024-05-14 |
Reinformer: Max-Return Sequence Modeling for Offline RL |
link |
Zifeng Zhuang, Dengyun Peng,..., Donglin Wang |
| 13 |
2024-01-31 |
Do Language Models Exhibit the Same Cognitive Biases in
Problem Solving as Human Learners? |
link |
Andreas Opedal, Alessandro Stolfo,..., Mrinmaya Sachan |
| 13 |
2023-06-07 |
Catapults in SGD: spikes in the training loss and
their impact on generalization through feature learning |
link |
Libin Zhu, Chaoyue Liu,..., Mikhail Belkin |
| 13 |
2024-05-28 |
MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance |
link |
Yake Wei, Di Hu |
| 13 |
2024-05-30 |
Proteus: Exploring Protein Structure Generation for Enhanced Designability and
Efficiency |
link |
Chentong Wang, Yannan Qu,..., Longxing Cao |
| 13 |
2023-11-24 |
StableSSM: Alleviating the Curse of Memory in State-space Models
through Stable Reparameterization |
link |
Shida Wang, Qianxiao Li |
| 13 |
2024-02-20 |
Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series
Dependencies and Intra-Series Variations Modeling |
link |
Guoqi Yu, Jing Zou,..., Shujun Wang |
| 13 |
2023-09-29 |
Information Flow in Self-Supervised Learning |
link |
Zhiquan Tan, Jingqin Yang,..., Yifan Zhang |
| 13 |
2024-02-11 |
Self-Correcting Self-Consuming Loops for Generative Model Training |
link |
Nate Gillman, Michael Freeman,..., Chen Sun |
| 13 |
2023-12-16 |
Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge |
link |
Conghan Yue, Zhengwei Peng,..., Dongyu Zhang |
| 12 |
2024-06-06 |
Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation |
link |
Can Yaras, Peng Wang,..., Qing Qu |
| 12 |
2024-03-26 |
How Private are DP-SGD Implementations? |
link |
Lynn Chua, Badih Ghazi,..., Chiyuan Zhang |
| 12 |
2023-06-15 |
ViP: A Differentially Private Foundation Model for Computer Vision |
link |
Yaodong Yu, Maziar Sanjabi,..., Chuan Guo |
| 12 |
2024-02-16 |
Stochastic Localization via Iterative Posterior Sampling |
link |
Louis Grenioux, Maxence Noble,..., Alain Oliviero Durmus |
| 12 |
2023-06-06 |
Designing Decision Support Systems using Counterfactual Prediction Sets |
link |
Eleni Straitouri, Manuel Gomez Rodriguez |
| 12 |
2024-06-20 |
Understanding Finetuning for Factual Knowledge Extraction |
link |
Gaurav Rohit Ghosal, Tatsunori Hashimoto, Aditi Raghunathan |
| 12 |
2024-02-22 |
Clifford-Steerable Convolutional Neural Networks |
link |
Maksim Zhdanov, David Ruhe,..., Patrick Forré |
| 12 |
2024-04-02 |
What Can Transformer Learn with Varying Depth? Case Studies
on Sequence Learning Tasks |
link |
Xingwu Chen, Difan Zou |
| 12 |
2024-02-05 |
Can We Remove the Square-Root in Adaptive Gradient Methods?
A Second-Order Perspective |
link |
Wu Lin, Felix Dangel,..., Alireza Makhzani |
| 12 |
2024-01-08 |
Sampling in Unit Time with Kernel Fisher-Rao Flow |
link |
Aimee Maurais, Youssef Marzouk |
| 12 |
2024-02-15 |
Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification |
link |
Yiming Meng, Ruikun Zhou,..., Jun Liu |
| 12 |
2024-05-08 |
VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems
in Visual Context |
link |
yunxin li, Baotian Hu,..., Min Zhang |
| 12 |
2024-05-12 |
Learning Reward for Robot Skills Using Large Language Models
via Self-Alignment |
link |
Yuwei Zeng, Yao Mu, Lin Shao |
| 12 |
2024-06-11 |
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets
Cannot |
link |
Zixuan Wang, Stanley Wei,..., Jason D. Lee |
| 12 |
2023-07-03 |
Trainable Transformer in Transformer |
link |
Abhishek Panigrahi, Sadhika Malladi,..., Sanjeev Arora |
| 12 |
2024-06-03 |
Do Large Language Models Perform the Way People Expect?
Measuring the Human Generalization Function |
link |
Keyon Vafa, Ashesh Rambachan, Sendhil Mullainathan |
| 12 |
2024-06-28 |
Multimodal Prototyping for cancer survival prediction |
link |
Andrew H. Song, Richard J. Chen,..., Faisal Mahmood |
| 12 |
2024-07-03 |
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents |
link |
Yilun Xu, Gabriele Corso,..., Karsten Kreis |
| 12 |
2024-02-06 |
Improved Generalization of Weight Space Networks via Augmentations |
link |
Aviv Shamsian, Aviv Navon,..., Haggai Maron |
| 12 |
2022-12-21 |
Not Just Pretty Pictures: Toward Interventional Data Augmentation Using
Text-to-Image Generators |
link |
Jianhao Yuan, Francesco Pinto,..., Philip Torr |
| 12 |
2023-11-02 |
Gaussian Processes on Cellular Complexes |
link |
Mathieu Alain, So Takao,..., Marc Peter Deisenroth |
| 12 |
2023-10-18 |
A connection between Tempering and Entropic Mirror Descent |
link |
Nicolas Chopin, Francesca Crucinio, Anna Korba |
| 12 |
2023-12-15 |
Fast Decision Boundary based Out-of-Distribution Detector |
link |
Litian Liu, Yao Qin |
| 12 |
2024-06-05 |
Graph Neural Network Explanations are Fragile |
link |
Jiate Li, Meng Pang,..., Binghui Wang |
| 12 |
2024-03-05 |
PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching |
link |
Haitao Lin, Odin Zhang,..., Stan Z. Li |
| 12 |
2024-05-08 |
The Entropy Enigma: Success and Failure of Entropy Minimization |
link |
Ori Press, Ravid Shwartz-Ziv,..., Matthias Bethge |
| 12 |
2024-06-02 |
FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning |
link |
Yuwei Fu, Haichao Zhang,..., Benoit Boulet |
| 12 |
2024-05-30 |
SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for
Embodied Manipulation |
link |
Junjie Zhang, Chenjia Bai,..., Xuelong Li |
| 12 |
2024-02-15 |
Accelerating Parallel Sampling of Diffusion Models |
link |
Zhiwei Tang, Jiasheng Tang,..., Tsung-Hui Chang |
| 12 |
2024-06-10 |
Diving into Underwater: Segment Anything Model Guided Underwater Salient
Instance Segmentation and A Large-scale Dataset |
link |
Shijie Lian, Ziyi Zhang,..., Runmin Cong |
| 12 |
2024-05-28 |
SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity,
ECG and Respiratory Signals |
link |
Rahul Thapa, Bryan He,..., James Zou |
| 12 |
2024-02-11 |
More Benefits of Being Distributional: Second-Order Bounds for Reinforcement
Learning |
link |
Kaiwen Wang, Owen Oertell,..., Wen Sun |
| 12 |
2024-02-06 |
DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic
Systems |
link |
Yair Schiff, Zhong Yi Wan,..., Leonardo Zepeda-Núñez |
| 12 |
2023-09-29 |
Latent Space Symmetry Discovery |
link |
Jianke Yang, Nima Dehmamy,..., Rose Yu |
| 12 |
2024-05-27 |
Q-value Regularized Transformer for Offline Reinforcement Learning |
link |
Shengchao Hu, Ziqing Fan,..., Dacheng Tao |
| 12 |
2024-04-06 |
Multicalibration for Confidence Scoring in LLMs |
link |
Gianluca Detommaso, Martin Bertran Lopez,..., Aaron Roth |
| 11 |
2024-02-22 |
ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization |
link |
Tianying Ji, Yongyuan Liang,..., Huazhe Xu |
| 11 |
2024-02-08 |
Offline Actor-Critic Reinforcement Learning Scales to Large Models |
link |
Jost Tobias Springenberg, Abbas Abdolmaleki,..., Martin Riedmiller |
| 11 |
2024-05-20 |
LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph
Clustering |
link |
Li Sun, Zhenhao Huang,..., Philip S. Yu |
| 11 |
2023-10-19 |
Improved Operator Learning by Orthogonal Attention |
link |
Zipeng Xiao, Zhongkai Hao,..., Hang Su |
| 11 |
2024-03-19 |
End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations |
link |
Lirui Luo, Guoxi Zhang,..., Qing Li |
| 11 |
2024-05-29 |
Locally Estimated Global Perturbations are Better than Local Perturbations
for Federated Sharpness-aware Minimization |
link |
Ziqing Fan, Shengchao Hu,..., Yanfeng Wang |
| 11 |
2024-05-28 |
FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic
Prediction |
link |
Zhonghang Li, Lianghao Xia,..., Chao Huang |
| 11 |
2024-02-16 |
RLVF: Learning from Verbal Feedback without Overgeneralization |
link |
Moritz Pascal Stephan, Alexander Khazatsky,..., Chelsea Finn |
| 11 |
2022-12-08 |
A New Linear Scaling Rule for Private Adaptive Hyperparameter
Optimization |
link |
Ashwinee Panda, Xinyu Tang,..., Prateek Mittal |
| 11 |
2024-01-05 |
AST-T5: Structure-Aware Pretraining for Code Generation and Understanding |
link |
Linyuan Gong, Mostafa Elhoushi, Alvin Cheung |
| 11 |
2024-02-14 |
Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning
Methods? |
link |
Mira Juergens, Nis Meinert,..., Willem Waegeman |
| 11 |
2024-01-17 |
Understanding Heterophily for Graph Neural Networks |
link |
Junfu Wang, Yuanfang Guo,..., Yunhong Wang |
| 11 |
2024-04-24 |
Unifying Bayesian Flow Networks and Diffusion Models through Stochastic
Differential Equations |
link |
Kaiwen Xue, Yuhao Zhou,..., Chongxuan Li |
| 11 |
2024-02-02 |
InferCept: Efficient Intercept Support for Augmented Large Language Model
Inference |
link |
Reyna Abhyankar, Zijian He,..., Yiying Zhang |
| 11 |
2024-03-03 |
Critical windows: non-asymptotic theory for feature emergence in diffusion
models |
link |
Marvin Li, Sitan Chen |
| 11 |
2023-05-26 |
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural
Networks |
link |
Atli Kosson, Bettina Messmer, Martin Jaggi |
| 11 |
2024-02-23 |
Explorations of Self-Repair in Language Models |
link |
Cody Rushing, Neel Nanda |
| 11 |
2024-02-13 |
Homomorphism Counts for Graph Neural Networks: All About That
Basis |
link |
Emily Jin, Michael M. Bronstein,..., Matthias Lanzinger |
| 11 |
2024-06-10 |
Compute Better Spent: Replacing Dense Layers with Structured Matrices |
link |
Shikai Qiu, Andres Potapczynski,..., Andrew Gordon Wilson |
| 11 |
2024-02-01 |
Towards Efficient Exact Optimization of Language Model Alignment |
link |
Haozhe Ji, Cheng Lu,..., Minlie Huang |
| 11 |
2024-02-16 |
Language Models as Science Tutors |
link |
Alexis Chevalier, Jiayi Geng,..., Danqi Chen |
| 11 |
2024-04-11 |
Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models |
link |
Tanmay Gautam, Youngsuk Park,..., Wooseok Ha |
| 11 |
2023-10-14 |
DPZero: Private Fine-Tuning of Language Models without Backpropagation |
link |
Liang Zhang, Bingcong Li,..., Niao He |
| 11 |
2024-03-04 |
Reward Model Learning vs. Direct Policy Optimization: A Comparative
Analysis of Learning from Human Preferences |
link |
Andi Nika, Debmalya Mandal,..., Adish Singla |
| 11 |
2024-02-08 |
Time Series Diffusion in the Frequency Domain |
link |
Jonathan Crabbé, Nicolas Huynh,..., Mihaela van der Schaar |
| 11 |
2024-02-05 |
Understanding Reasoning Ability of Language Models From the Perspective
of Reasoning Paths Aggregation |
link |
Xinyi Wang, Alfonso Amayuelas,..., William Yang Wang |
| 11 |
2024-05-11 |
Non-confusing Generation of Customized Concepts in Diffusion Models |
link |
Wang Lin, Jingyuan Chen,..., Hanwang Zhang |
| 11 |
2024-01-24 |
ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal
Models |
link |
Rohan Wadhawan, Hritik Bansal,..., Nanyun Peng |
| 11 |
2024-02-01 |
Transforming and Combining Rewards for Aligning Large Language Models |
link |
Zihao Wang, Chirag Nagpal,..., Victor Veitch |
| 11 |
2024-01-26 |
Residual Quantization with Implicit Neural Codebooks |
link |
Iris A.M. Huijben, Matthijs Douze,..., Jakob Verbeek |
| 11 |
2024-02-02 |
Understanding Adam Optimizer via Online Learning of Updates: Adam
is FTRL in Disguise |
link |
Kwangjun Ahn, Zhiyu Zhang,..., Yan Dai |
| 11 |
2024-02-22 |
Prompting a Pretrained Transformer Can Be a Universal Approximator |
link |
Aleksandar Petrov, Philip Torr, Adel Bibi |
| 11 |
2024-01-04 |
Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU
Features Model |
link |
Hien Dang, Tho Tran Huu,..., Nhat Ho |
| 11 |
2023-03-15 |
Borda Regret Minimization for Generalized Linear Dueling Bandits |
link |
Yue Wu, Tao Jin,..., Quanquan Gu |
| 11 |
2023-05-30 |
Plug-in Performative Optimization |
link |
Licong Lin, Tijana Zrnic |
| 11 |
2024-03-27 |
Understanding the Learning Dynamics of Alignment with Human Feedback |
link |
Shawn Im, Yixuan Li |
| 11 |
2023-11-28 |
Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models |
link |
Zhihe Lu, Jiawang Bai,..., Xinchao Wang |
| 11 |
2024-02-06 |
Neural Networks Learn Statistics of Increasing Complexity |
link |
Nora Belrose, Quintin Pope,..., Xiaoli Fern |
| 10 |
2024-03-05 |
Active Statistical Inference |
link |
Tijana Zrnic, Emmanuel Candes |
| 10 |
2023-10-18 |
Image Clustering with External Guidance |
link |
Yunfan Li, Peng Hu,..., Xi Peng |
| 10 |
2023-07-13 |
Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks |
link |
Liam Collins, Hamed Hassani,..., Sanjay Shakkottai |
| 10 |
2024-06-11 |
Flextron: Many-in-One Flexible Large Language Model |
link |
Ruisi Cai, Saurav Muralidharan,..., Pavlo Molchanov |
| 10 |
None |
Relaxing the Accurate Imputation Assumption in Doubly Robust Learning
for Debiased Collaborative Filtering |
link |
Haoxuan Li, Chunyuan Zheng,..., Xiao-Hua Zhou |
| 10 |
2024-03-28 |
Regression with Multi-Expert Deferral |
link |
Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 10 |
2024-06-11 |
Failures Are Fated, But Can Be Faded: Characterizing and
Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models |
link |
Som Sagar, Aditya Taparia, Ransalu Senanayake |
| 10 |
2024-02-27 |
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings |
link |
Kevin Frans, Seohong Park,..., Sergey Levine |
| 10 |
2023-11-01 |
Robust and Conjugate Gaussian Process Regression |
link |
Matias Altamirano, Francois-Xavier Briol, Jeremias Knoblauch |
| 10 |
2024-02-07 |
CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks |
link |
Yulong Huang, Xiaopeng LIN,..., Bojun Cheng |
| 10 |
2023-07-11 |
Memorization Through the Lens of Curvature of Loss Function
Around Samples |
link |
Isha Garg, Deepak Ravikumar, Kaushik Roy |
| 10 |
2024-03-01 |
EfficientZero V2: Mastering Discrete and Continuous Control with Limited
Data |
link |
Shengjie Wang, Shaohuai Liu,..., Yang Gao |
| 10 |
None |
Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV
Tracking |
link |
Yongxin Li, Mengyuan Liu,..., Shuiwang Li |
| 10 |
2024-02-12 |
Weisfeiler-Leman at the margin: When more expressivity matters |
link |
Billy Joe Franks, Christopher Morris,..., Floris Geerts |
| 10 |
2024-06-05 |
SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN |
link |
kang you, Zekai Xu,..., Zhezhi He |
| 10 |
None |
Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution
Approximation |
link |
Boheng Li, Yishuo Cai,..., Tianwei Zhang |
| 10 |
2023-11-20 |
HexGen: Generative Inference of Large Language Model over Heterogeneous
Environment |
link |
YOUHE JIANG, Ran Yan,..., Binhang Yuan |
| 10 |
2023-12-05 |
UPOCR: Towards Unified Pixel-Level OCR Interface |
link |
Dezhi Peng, Zhenhua Yang,..., Lianwen Jin |
| 10 |
2024-05-15 |
ReconBoost: Boosting Can Achieve Modality Reconcilement |
link |
Cong Hua, Qianqian Xu,..., Qingming Huang |
| 10 |
2024-05-20 |
Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning |
link |
Kai Gan, Tong Wei |
| 10 |
2024-01-05 |
Graph2Tac: Online Representation Learning of Formal Math Concepts |
link |
Lasse Blaauwbroek, Mirek Olšák,..., Vasily Pestun |
| 10 |
None |
Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification |
link |
Jintong Gao, He Zhao,..., Hongyuan Zha |
| 10 |
2023-10-22 |
A General Theory for Softmax Gating Multinomial Logistic Mixture
of Experts |
link |
Huy Nguyen, Pedram Akbarian,..., Nhat Ho |
| 10 |
2024-06-04 |
What Improves the Generalization of Graph Transformers? A Theoretical
Dive into the Self-attention and Positional Encoding |
link |
Hongkang Li, Meng Wang,..., Pin-Yu Chen |
| 10 |
2024-05-02 |
Uncertainty for Active Learning on Graphs |
link |
Dominik Fuchsgruber, Tom Wollschläger,..., Stephan Günnemann |
| 10 |
2024-02-22 |
Comparing Graph Transformers via Positional Encodings |
link |
Mitchell Black, Zhengchao Wan,..., Yusu Wang |
| 10 |
2024-02-28 |
Out-of-Domain Generalization in Dynamical Systems Reconstruction |
link |
Niclas Alexander Göring, Florian Hess,..., Daniel Durstewitz |
| 10 |
2024-02-15 |
Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient
Data Utilization |
link |
Yihan Du, Anna Winnicki,..., R. Srikant |
| 10 |
2024-01-25 |
Is Temperature Sample Efficient for Softmax Gaussian Mixture of
Experts? |
link |
Huy Nguyen, Pedram Akbarian, Nhat Ho |
| 10 |
2023-01-27 |
Single-Trajectory Distributionally Robust Reinforcement Learning |
link |
Zhipeng Liang, Xiaoteng Ma,..., Zhengyuan Zhou |
| 10 |
None |
Equivariant Diffusion for Crystal Structure Prediction |
link |
Peijia Lin, Pin Chen,..., Yutong Lu |
| 10 |
2023-04-16 |
An Empirical Study of Realized GNN Expressiveness |
link |
Yanbo Wang, Muhan Zhang |
| 10 |
2024-04-12 |
On the Independence Assumption in Neurosymbolic Learning |
link |
Emile van Krieken, Pasquale Minervini,..., Antonio Vergari |
| 10 |
2023-10-13 |
Split-and-Denoise: Protect large language model inference with local differential
privacy |
link |
Peihua Mai, Ran Yan,..., Yan Pang |
| 10 |
2024-02-23 |
Fair Resource Allocation in Multi-Task Learning |
link |
Hao Ban, Kaiyi Ji |
| 10 |
2024-02-07 |
Multi-Sender Persuasion: A Computational Perspective |
link |
Safwan Hossain, Tonghan Wang,..., Haifeng Xu |
| 10 |
2024-01-21 |
Linear Alignment: A Closed-form Solution for Aligning Human Preferences
without Tuning and Feedback |
link |
Songyang Gao, Qiming Ge,..., Dahua Lin |
| 10 |
2024-06-02 |
Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution
Detection |
link |
Chentao Cao, Zhun Zhong,..., Bo Han |