NeurIPS - arXivDaily 期刊&会议

2402.09236 2024-12-10 cs.LG cs.AI math.ST stat.ML stat.TH

Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models

Goutham Rajendran, Simon Buchholz, Bryon Aragam, Bernhard Schölkopf, Pradeep Ravikumar

Comments To appear in NeurIPS 2024 under the modified title 'From Causal to Concept-Based Representation Learning'

2312.01658 2024-12-10 cs.LG cs.DC math.OC

AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix

Yun Yue, Zhiling Ye, Jiadi Jiang, Yongchao Liu, Ke Zhang

Comments 21 pages. Accepted as a conference paper at NeurIPS '23

2306.07951 2024-12-10 cs.CL

Questioning the Survey Responses of Large Language Models

Ricardo Dominguez-Olmedo, Moritz Hardt, Celestine Mendler-Dünner

Comments NeurIPS 2024

2412.06063 2024-12-10 cs.LG cs.DS stat.ML

On Socially Fair Low-Rank Approximation and Column Subset Selection

Zhao Song, Ali Vakilian, David P. Woodruff, Samson Zhou

Comments NeurIPS 2024

2412.06060 2024-12-10 cs.CL cs.AI

Steering Large Language Models to Evaluate and Amplify Creativity

Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck, Shao-yen Tseng, Vasudev Lal

Comments (Spotlight) NeurIPS 2024 Workshop on Creativity & Generative AI. Authors 1 and 2 contributed equally

2412.05926 2024-12-10 cs.CV

BiDM: Pushing the Limit of Quantization for Diffusion Models

Xingyu Zheng, Xianglong Liu, Yichen Bian, Xudong Ma, Yulun Zhang, Jiakai Wang, Jinyang Guo, Haotong Qin

Comments NeurIPS 2024

2412.05823 2024-12-10 cs.LG cs.AI

DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices

Yongzhe Jia, Xuyun Zhang, Hongsheng Hu, Kim-Kwang Raymond Choo, Lianyong Qi, Xiaolong Xu, Amin Beheshti, Wanchun Dou

Comments Oral accepted by NeurIPS 2024

2412.05807 2024-12-10 cs.DS

Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters

David P. Woodruff, Samson Zhou

Comments NeurIPS 2024

2412.05768 2024-12-10 cs.CL cs.AI

Uncovering Uncertainty in Transformer Inference

Greyson Brothers, Willa Mannering, Amber Tien, John Winder

Comments Accepted poster at the 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Workshop on Foundation Model Interventions

2412.05766 2024-12-10 cs.LG cs.AI

Policy-shaped prediction: avoiding distractions in model-based reinforcement learning

Miles Hutson, Isaac Kauvar, Nick Haber

Comments Accepted at NeurIPS 2024

2412.05592 2024-12-10 cs.AI

From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation

Kristoffer Wickstrøm, Marina Marie-Claire Höhne, Anna Hedström

Comments Published in ECCV 2024 Workshop on Explainable Computer Vision: Where are We and Where are We Going? Shorter non-archival version also appeared in the NeurIPS 2024 Interpretable AI workshop. Code is available at \url{https://github.com/Wickstrom/quantitative-xai-manipulation}

2412.05571 2024-12-10 cs.CL

A polar coordinate system represents syntax in large language models

Pablo Diego-Simón, Stéphane D'Ascoli, Emmanuel Chemla, Yair Lakretz, Jean-Rémi King

Journal ref NeurIPS 2024

2412.05570 2024-12-10 cs.CV

Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis

Diwen Wan, Yuxiang Wang, Ruijie Lu, Gang Zeng

Comments Accepted by NeurIPS 2024

2412.05460 2024-12-10 cs.CV

CigTime: Corrective Instruction Generation Through Inverse Motion Editing

Qihang Fang, Chengcheng Tang, Bugra Tekin, Yanchao Yang

Comments 20 pages, 8 figures, NeurIPS 2024

2412.05388 2024-12-10 cs.CL cs.AI cs.LG

CALICO: Conversational Agent Localization via Synthetic Data Generation

Andy Rosenbaum, Pegah Kharazmi, Ershad Banijamali, Lu Zeng, Christopher DiPersio, Pan Wei, Gokmen Oz, Clement Chung, Karolina Owczarzak, Fabian Triefenbach, Wael Hamza

Comments Accepted to The 37th International Conference on Neural Information Processing Systems (NeurIPS 2023) December 10-16, 2023 - SyntheticData4ML Workshop, New Orleans, United States https://neurips.cc/virtual/2023/workshop/66540

2410.23855 2024-12-10 cs.LG cs.AI cs.SI

RAGraph: A General Retrieval-Augmented Graph Learning Framework

Xinke Jiang, Rihong Qiu, Yongxin Xu, Wentao Zhang, Yichen Zhu, Ruizhe Zhang, Yuchen Fang, Xu Chu, Junfeng Zhao, Yasha Wang

Comments NeurIPS 2024

2410.10931 2024-12-10 cs.DB cs.LG

Combining Observational Data and Language for Species Range Estimation

Max Hamilton, Christian Lange, Elijah Cole, Alexander Shepard, Samuel Heinrich, Oisin Mac Aodha, Grant Van Horn, Subhransu Maji

Comments NeurIPS 2024

2410.01091 2024-12-10 cs.LG cs.AI

Efficient and Private Marginal Reconstruction with Local Non-Negativity

Brett Mullins, Miguel Fuentes, Yingtai Xiao, Daniel Kifer, Cameron Musco, Daniel Sheldon

Comments To appear at NeurIPS 2024

2409.17481 2024-12-10 cs.AI cs.CL cs.LG

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

Gongfan Fang, Hongxu Yin, Saurav Muralidharan, Greg Heinrich, Jeff Pool, Jan Kautz, Pavlo Molchanov, Xinchao Wang

Comments NeurIPS 2024 Spotlight

2406.10215 2024-12-10 cs.CL cs.LG

DevBench: A multimodal developmental benchmark for language learning

Alvin Wei Ming Tan, Sunny Yu, Bria Long, Wanjing Anya Ma, Tonya Murray, Rebecca D. Silverman, Jason D. Yeatman, Michael C. Frank

Comments Accepted at NeurIPS 2024 (Oral)

2406.08850 2024-12-10 cs.CV

COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing

Jiangshan Wang, Yue Ma, Jiayi Guo, Yicheng Xiao, Gao Huang, Xiu Li

Comments NeurIPS 2024

2406.06567 2024-12-10 cs.LG cs.AI cs.CL

DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion

Yilong Chen, Linhao Zhang, Junyuan Shang, Zhenyu Zhang, Tingwen Liu, Shuohuan Wang, Yu Sun

Comments Accepted at NeurIPS 2024 10 pages, 9 figures, 3 tables

2405.15731 2024-12-10 cs.LG cs.AI cs.SY eess.SY

Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks

Jerome Sieber, Carmen Amo Alonso, Alexandre Didier, Melanie N. Zeilinger, Antonio Orvieto

Comments NeurIPS 2024

2405.14473 2024-12-10 cs.LG cs.AI q-bio.NC

Poisson Variational Autoencoder

Hadi Vafaii, Dekel Galor, Jacob L. Yates

Comments Published as a NeurIPS 2024 Spotlight paper (https://openreview.net/forum?id=ektPEcqGLb)

2404.16698 2024-12-10 cs.CL

Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents

Giorgio Piatti, Zhijing Jin, Max Kleiman-Weiner, Bernhard Schölkopf, Mrinmaya Sachan, Rada Mihalcea

Comments NeurIPS 2024

2312.17248 2024-12-10 cs.LG cs.AI cs.CC cs.DS stat.ML

Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity

Guhao Feng, Han Zhong

Comments NeurIPS 2024; this updated version includes additional theoretical findings and experimental results

2312.14556 2024-12-10 cs.CV

CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities

Rohith Peddi, Shivvrat Arya, Bharath Challa, Likhitha Pallapothula, Akshay Vyas, Bhavya Gouripeddi, Jikai Wang, Qifan Zhang, Vasundhara Komaragiri, Eric Ragan, Nicholas Ruozzi, Yu Xiang, Vibhav Gogate

Comments Accepted to the 2024 Neural Information Processing Systems Datasets and Benchmarks Track, Project Page: https://rohithpeddi.github.io/#/captaincook

2312.13289 2024-12-10 cond-mat.mtrl-sci cs.LG

Compositional Representation of Polymorphic Crystalline Materials

Namkyeong Lee, Heewoong Noh, Gyoung S. Na, Jimeng Sun, Tianfan Fu, Marinka Zitnik, Chanyoung Park

Comments NeurIPS 2023 AI4Science Workshop

2312.10523 2024-12-10 cs.CL cs.AI cs.LG

Paloma: A Benchmark for Evaluating Language Model Fit

Ian Magnusson, Akshita Bhagia, Valentin Hofmann, Luca Soldaini, Ananya Harsh Jha, Oyvind Tafjord, Dustin Schwenk, Evan Pete Walsh, Yanai Elazar, Kyle Lo, Dirk Groeneveld, Iz Beltagy, Hannaneh Hajishirzi, Noah A. Smith, Kyle Richardson, Jesse Dodge

Comments Conference: NeurIPS 2024, Project Page: https://paloma.allen.ai/

2311.09058 2024-12-10 cs.LG

Improving Deep Learning Optimization through Constrained Parameter Regularization

Jörg K. H. Franke, Michael Hefenbrock, Gregor Koehler, Frank Hutter

Comments In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024), 35 pages