NeurIPS - arXivDaily 期刊&会议

2407.20109 2024-11-01 cs.LG cs.AI

Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning

Liyuan Mao, Haoran Xu, Xianyuan Zhan, Weinan Zhang, Amy Zhang

Comments NeurIPS 2024, first two authors contribute equally

2407.16434 2024-11-01 cs.CL

Enhancing LLM's Cognition via Structurization

Kai Liu, Zhihang Fu, Chao Chen, Wei Zhang, Rongxin Jiang, Fan Zhou, Yaowu Chen, Yue Wu, Jieping Ye

Comments This paper has been accepted by NeurIPS 2024. Code is available at https://github.com/alibaba/struxgpt

2407.16430 2024-11-01 cs.CV

Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution

Kai Liu, Zhihang Fu, Sheng Jin, Chao Chen, Ze Chen, Rongxin Jiang, Fan Zhou, Yaowu Chen, Jieping Ye

Comments This paper has been accepted by NeurIPS 2024. Code is available at https://github.com/alibaba/imood

2407.08447 2024-11-01 cs.CV

WildGaussians: 3D Gaussian Splatting in the Wild

Jonas Kulhanek, Songyou Peng, Zuzana Kukelova, Marc Pollefeys, Torsten Sattler

Comments NeurIPS 2024; Project page: https://wild-gaussians.github.io/

2407.05516 2024-11-01 eess.AS cs.AI cs.SD eess.SP

Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation

Jin Woo Lee, Jaehyun Park, Min Jun Choi, Kyogu Lee

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

2407.03978 2024-11-01 cs.CL cs.AI

Benchmarking Complex Instruction-Following with Multiple Constraints Composition

Bosi Wen, Pei Ke, Xiaotao Gu, Lindong Wu, Hao Huang, Jinfeng Zhou, Wenchuang Li, Binxin Hu, Wendy Gao, Jiaxin Xu, Yiming Liu, Jie Tang, Hongning Wang, Minlie Huang

Comments NeurIPS 2024 Datasets and Benchmarks Track

2407.03550 2024-11-01 cs.CV

CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding

Emanuele Vivoli, Marco Bertini, Dimosthenis Karatzas

Comments Accepted at NeurIPS 2024 (D&B)

2407.02013 2024-11-01 cs.LG

DiGRAF: Diffeomorphic Graph-Adaptive Activation Function

Krishna Sri Ipsit Mantri, Xinzhi Wang, Carola-Bibiane Schönlieb, Bruno Ribeiro, Beatrice Bevilacqua, Moshe Eliasof

Comments NeurIPS 2024

2407.01079 2024-11-01 stat.ML cs.AI cs.LG

On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)

Jerry Yao-Chieh Hu, Weimin Wu, Zhao Song, Han Liu

Comments Accepted at NeurIPS 2024. v3 updated to camera-ready version with many typos fixed; v2 fixed typos, added Fig. 1 and added clarifications

2407.00626 2024-11-01 cs.LG cs.AI

Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models

Sangwoong Yoon, Himchan Hwang, Dohyun Kwon, Yung-Kyun Noh, Frank C. Park

Comments NeurIPS 2024 Oral Presentation. Code is released at https://github.com/swyoon/Diffusion-by-MaxEntIRL

2407.00114 2024-11-01 cs.LG cs.AI cs.CL

OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents

Zihao Wang, Shaofei Cai, Zhancun Mu, Haowei Lin, Ceyao Zhang, Xuejie Liu, Qing Li, Anji Liu, Xiaojian Ma, Yitao Liang

Comments accepted on NeurIPS 2024

2407.00002 2024-11-01 q-bio.BM cs.LG

Kermut: Composite kernel regression for protein variant effects

Peter Mørch Groth, Mads Herbert Kerrn, Lars Olsen, Jesper Salomon, Wouter Boomsma

Comments Accepted to NeurIPS 2024 as Spotlight

2406.20087 2024-11-01 cs.LG cs.AI cs.CL cs.CY cs.HC

ProgressGym: Alignment with a Millennium of Moral Progress

Tianyi Qiu, Yang Zhang, Xuchuan Huang, Jasmine Xinze Li, Jiaming Ji, Yaodong Yang

Comments NeurIPS 2024 Track on Datasets and Benchmarks (Spotlight)

2406.19861 2024-11-01 cs.LG math.OC stat.ML

Operator World Models for Reinforcement Learning

Pietro Novelli, Marco Pratticò, Massimiliano Pontil, Carlo Ciliberto

Journal ref The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024

2406.19073 2024-11-01 cs.CL

AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries

Irina Saparina, Mirella Lapata

Comments NeurIPS 2024 D&B Track Spotlight

2406.18043 2024-11-01 cs.AI cs.CV cs.LG cs.RO

GenRL: Multimodal-foundation world models for generalization in embodied agents

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Aaron Courville, Sai Rajeswar

Comments Presented at NeurIPS 2024

2406.15916 2024-11-01 cs.LG cs.CR stat.ML

Credit Attribution and Stable Compression

Roi Livni, Shay Moran, Kobbi Nissim, Chirag Pabbaraju

Comments 16 pages, 1 figure. NeurIPS 2024 camera-ready version

2406.15349 2024-11-01 cs.CV cs.AI cs.LG cs.RO

NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

Daniel Dauner, Marcel Hallgarten, Tianyu Li, Xinshuo Weng, Zhiyu Huang, Zetong Yang, Hongyang Li, Igor Gilitschenski, Boris Ivanovic, Marco Pavone, Andreas Geiger, Kashyap Chitta

Comments NeurIPS 2024 Datasets and Benchmarks

2406.14927 2024-11-01 cs.CV cs.RO

GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation

Junhao Cai, Yuji Yang, Weihao Yuan, Yisheng He, Zilong Dong, Liefeng Bo, Hui Cheng, Qifeng Chen

Comments 21 pages, 8 figures, NeurIPS 2024

2406.14219 2024-11-01 cs.AI

Proving Olympiad Algebraic Inequalities without Human Demonstrations

Chenrui Wei, Mengzhou Sun, Wei Wang

Comments 36 pages, 32 figures, 2 tables, published as a conference paper at NeurIPS 2024

2406.13762 2024-11-01 cs.LG cs.AI cs.CL cs.CV stat.ML

Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis

Rachel S. Y. Teo, Tan M. Nguyen

Comments 10 pages in the main text. Published at NeurIPS 2024. The code is available at https://github.com/rachtsy/KPCA_code

2406.12095 2024-11-01 cs.CV cs.AI cs.RO

DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features

Letian Wang, Seung Wook Kim, Jiawei Yang, Cunjun Yu, Boris Ivanovic, Steven L. Waslander, Yue Wang, Sanja Fidler, Marco Pavone, Peter Karkus

Comments Accepted by Advances in Neural Information Processing Systems (NeurIPS 2024)

2406.11906 2024-11-01 q-bio.QM cs.AI

NovoBench: Benchmarking Deep Learning-based De Novo Peptide Sequencing Methods in Proteomics

Jingbo Zhou, Shaorong Chen, Jun Xia, Sizhe Liu, Tianze Ling, Wenjie Du, Yue Liu, Jianwei Yin, Stan Z. Li

Comments NeurIPS 2024 D&B track

2406.11200 2024-11-01 cs.LG cs.CL

AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning

Shirley Wu, Shiyu Zhao, Qian Huang, Kexin Huang, Michihiro Yasunaga, Kaidi Cao, Vassilis N. Ioannidis, Karthik Subbian, Jure Leskovec, James Zou

Comments NeurIPS 2024 main conference

2406.10490 2024-11-01 stat.ML cs.LG

Active, anytime-valid risk controlling prediction sets

Ziyu Xu, Nikos Karampatziakis, Paul Mineiro

Comments 22 pages, 3 figures. Accepted to NeurIPS 2024

2406.09867 2024-11-01 cs.CV

Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox

Xingming Long, Jie Zhang, Shiguang Shan, Xilin Chen

Comments Accepted at NeurIPS 2024

2406.09714 2024-11-01 stat.ML cs.LG stat.ME

Large language model validity via enhanced conformal prediction methods

John J. Cherian, Isaac Gibbs, Emmanuel J. Candès

Comments 24 pages, 14 figures, NeurIPS

2406.09168 2024-11-01 eess.IV cs.CV cs.LG

SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution

Soufiane Belharbi, Mara KM Whitford, Phuong Hoang, Shakeeb Murtaza, Luke McCaffrey, Eric Granger

Comments 27 pages, 15 figures, NeurIPS 2024

2406.09136 2024-11-01 cs.CL cs.LG

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

Xuan Zhang, Chao Du, Tianyu Pang, Qian Liu, Wei Gao, Min Lin

Comments NeurIPS 2024

2406.08747 2024-11-01 cs.CL

StreamBench: Towards Benchmarking Continuous Improvement of Language Agents

Cheng-Kuang Wu, Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen, Hung-yi Lee

Comments NeurIPS 2024 Track on Datasets and Benchmarks