NeurIPS - arXivDaily 期刊&会议

2410.19479 2024-10-28 cs.CV cs.AI

Peter Parker or Spiderman? Disambiguating Multiple Class Labels

Nuthan Mummani, Simran Ketha, Venkatakrishnan Ramaswamy

Comments Accepted to Neural Information Processing Systems (NeurIPS 2024). ATTRIB Workshop

2410.19294 2024-10-28 cs.CV

Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting

Xingyu Zhu, Beier Zhu, Yi Tan, Shuo Wang, Yanbin Hao, Hanwang Zhang

Comments NeurIPS 2024 Spotlight

2410.19163 2024-10-28 cs.GT cs.DS

Fairness and Efficiency in Online Class Matching

MohammadTaghi Hajiaghayi, Shayan Chashm Jahan, Mohammad Sharifi, Suho Shin, Max Springer

Comments Accepted to NeurIPS 2024

2410.19123 2024-10-28 cs.CL cs.LG

Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

Ruisi Cai, Yeonju Ro, Geon-Woo Kim, Peihao Wang, Babak Ehteshami Bejnordi, Aditya Akella, Zhangyang Wang

Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

2410.19081 2024-10-28 cs.LG stat.ML

FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models

Jiachang Liu, Rui Zhang, Cynthia Rudin

Comments Accepted into NeurIPS 2024

2410.19055 2024-10-28 cs.LG

Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms

Felix Petersen, Christian Borgelt, Tobias Sutter, Hilde Kuehne, Oliver Deussen, Stefano Ermon

Comments Published at NeurIPS 2024

2410.18986 2024-10-28 cs.CV cs.LG

VehicleSDF: A 3D generative model for constrained engineering design via surrogate modeling

Hayata Morita, Kohei Shintani, Chenyang Yuan, Frank Permenter

Comments 9 pages, 14 figures, NeurIPS 2024 workshop

2410.17020 2024-10-28 cs.LG cs.CV

LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization

Liang Chen, Yong Zhang, Yibing Song, Zhiqiang Shen, Lingqiao Liu

Comments Accepted by NeurIPS 2024

2410.16973 2024-10-28 cs.CL cs.AI cs.LG

Learning Mathematical Rules with Large Language Models

Antoine Gorceix, Bastien Le Chenadec, Ahmad Rammal, Nelson Vadori, Manuela Veloso

Comments NeurIPS'24 MATH-AI, the 4th Workshop on Mathematical Reasoning and AI

2410.08021 2024-10-28 cs.CV

OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling

Linhui Xiao, Xiaoshan Yang, Fang Peng, Yaowei Wang, Changsheng Xu

Comments Accepted by NeurIPS 2024. The project page: https://github.com/linhuixiao/OneRef

2410.05465 2024-10-28 cs.AI cs.LG

On the Expressive Power of Tree-Structured Probabilistic Circuits

Lang Yin, Han Zhao

Comments This paper was accepted to NeurIPS 2024. This version uses a more accurate terminology for a complexity class, and adds a preliminary paragraph on relevant complexity classes

2409.19659 2024-10-28 cs.CV

Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery

Haonan Lin, Wenbin An, Jiahao Wang, Yan Chen, Feng Tian, Mengmeng Wang, Guang Dai, Qianying Wang, Jingdong Wang

Comments Accepted by NeurIPS 2024 (Oral)

2406.06040 2024-10-28 cs.CV

Vript: A Video Is Worth Thousands of Words

Dongjie Yang, Suyuan Huang, Chengqiang Lu, Xiaodong Han, Haoxin Zhang, Yan Gao, Yao Hu, Hai Zhao

Comments Accepted by NeurIPS Dataset & Benchmark track

2406.03537 2024-10-28 cs.LG cs.AI stat.ML

A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models

Hamidreza Kamkari, Brendan Leigh Ross, Rasa Hosseinzadeh, Jesse C. Cresswell, Gabriel Loaiza-Ganem

Comments NeurIPS 2024 (spotlight)

2405.15324 2024-10-28 cs.RO cs.AI cs.CV

Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving

Jianbiao Mei, Yukai Ma, Xuemeng Yang, Licheng Wen, Xinyu Cai, Xin Li, Daocheng Fu, Bo Zhang, Pinlong Cai, Min Dou, Botian Shi, Liang He, Yong Liu, Yu Qiao

Comments NeurIPS 2024

2405.15018 2024-10-28 cs.LG cs.AI cs.CV

What Variables Affect Out-of-Distribution Generalization in Pretrained Models?

Md Yousuf Harun, Kyungbok Lee, Jhair Gallardo, Giri Krishnan, Christopher Kanan

Comments Accepted to NeurIPS 2024

2405.14285 2024-10-28 stat.ML cs.LG math.OC

Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise

Sebastian Allmeier, Nicolas Gast

Comments 24 pages. Accepted at NeurIPS 2024

2405.13557 2024-10-28 cs.LG cs.AI cs.CV

MotionCraft: Physics-based Zero-Shot Video Generation

Luca Savant Aira, Antonio Montanaro, Emanuele Aiello, Diego Valsesia, Enrico Magli

Journal ref NeurIPS 2024

2405.06525 2024-10-28 cs.CV

SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation

Xiaowen Ma, Zhenliang Ni, Xinghao Chen

Comments NeurIPS 2024

2402.16302 2024-10-28 cs.LG cs.AI cs.CE

Graph Diffusion Policy Optimization

Yijing Liu, Chao Du, Tianyu Pang, Chongxuan Li, Min Lin, Wei Chen

Comments NeurIPS 2024

2402.01469 2024-10-28 cs.CL

AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback

Jian Guan, Wei Wu, Zujie Wen, Peng Xu, Hongning Wang, Minlie Huang

Comments NeurIPS 2024

2410.18926 2024-10-25 cs.LG

LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search

Elias Jääsaari, Ville Hyvönen, Teemu Roos

Comments Accepted to NeurIPS 2024

2410.18917 2024-10-25 cs.LG cs.NA math.NA

Using Parametric PINNs for Predicting Internal and External Turbulent Flows

Shinjan Ghosh, Amit Chakraborty, Georgia Olympia Brikis, Biswadip Dey

Comments To be presented at the Data-driven and Differentiable Simulations, Surrogates, and Solvers (D3S3) Workshop at NeurIPS'2024

2410.11722 2024-10-25 cs.CV cs.AI cs.HC

RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation

Anton Antonov, Andrey Moskalenko, Denis Shepelev, Alexander Krapukhin, Konstantin Soshin, Anton Konushin, Vlad Shakhuro

Comments Accepted by NeurIPS 2024

2410.18785 2024-10-25 cs.AI

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

Qi Li, Xiang Liu, Zhenheng Tang, Peijie Dong, Zeyu Li, Xinglin Pan, Xiaowen Chu

Comments NeurIPS 2024 https://github.com/lqinfdim/EditingEvaluation

2410.18712 2024-10-25 cs.LG

Retrieval-Augmented Diffusion Models for Time Series Forecasting

Jingwei Liu, Ling Yang, Hongyan Li, Shenda Hong

Comments NeurIPS 2024

2410.18391 2024-10-25 cs.LG cs.CR math.OC

Faster Algorithms for User-Level Private Stochastic Convex Optimization

Andrew Lowy, Daogao Liu, Hilal Asi

Comments NeurIPS 2024

2410.18351 2024-10-25 cs.CL cs.LG

AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability

Sudhanshu Agrawal, Wonseok Jeon, Mingu Lee

Comments Workshop on Efficient Natural Language and Signal Processing at NeurIPS 2024

2410.18153 2024-10-25 math.NA cond-mat.dis-nn cs.AI cs.NA hep-th stat.ML

Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees

Taiki Miyagawa, Takeru Yokota

Comments Accepted at NeurIPS 2024. Both authors contributed equally. Some contents are omitted due to arXiv's storage limit. Please refer to the full paper at OpenReview (NeurIPS 2024) or https://github.com/TaikiMiyagawa/FunctionalPINN

2410.15859 2024-10-25 cs.LG cs.AI

Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs

Xin Ma, Yang Liu, Jingjing Liu, Xiaoxu Ma

Comments Accepted by NeurIPS 2024; 13 pages and 30 pages appendix;