NeurIPS - arXivDaily 期刊&会议

2409.13708 2024-10-30 cs.CL cs.AI cs.CY

Towards Safe Multilingual Frontier AI

Artūrs Kanepajs, Vladimir Ivanov, Richard Moulange

Comments 23 pages; 1 figure and 10 supplementary figures; Accepted (spotlight presentation) at NeurIPS 2024 SoLaR workshop

2408.16862 2024-10-30 stat.ML cs.LG

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics

Yenho Chen, Noga Mudrik, Kyle A. Johnsen, Sankaraleengam Alagapan, Adam S. Charles, Christopher J. Rozell

Comments Accepted to NeurIPS 2024

2407.06121 2024-10-30 cs.LG

Periodic agent-state based Q-learning for POMDPs

Amit Sinha, Matthieu Geist, Aditya Mahajan

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

2407.02880 2024-10-30 cs.LG cs.AI cs.CV

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

Frederic Z. Zhang, Paul Albert, Cristian Rodriguez-Opazo, Anton van den Hengel, Ehsan Abbasnejad

Comments Accepted to NeurIPS'24

2407.02518 2024-10-30 cs.SE cs.AI cs.CL cs.CR cs.MA cs.PL

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness

Hung Le, Yingbo Zhou, Caiming Xiong, Silvio Savarese, Doyen Sahoo

Comments Accepted to The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

2406.17758 2024-10-30 cs.CV

MotionBooth: Motion-Aware Customized Text-to-Video Generation

Jianzong Wu, Xiangtai Li, Yanhong Zeng, Jiangning Zhang, Qianyu Zhou, Yining Li, Yunhai Tong, Kai Chen

Comments (NeurIPS 2024 Spotlight) Project page at https://jianzongwu.github.io/projects/motionbooth

2406.12137 2024-10-30 cs.AI

IDs for AI Systems

Alan Chan, Noam Kolt, Peter Wills, Usman Anwar, Christian Schroeder de Witt, Nitarshan Rajkumar, Lewis Hammond, David Krueger, Lennart Heim, Markus Anderljung

Comments Under review; accepted to RegML workshop at NeurIPS 2024

2406.10023 2024-10-30 cs.LG cs.CL stat.ML

Deep Bayesian Active Learning for Preference Modeling in Large Language Models

Luckeciano C. Melo, Panagiotis Tigas, Alessandro Abate, Yarin Gal

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

2406.09329 2024-10-30 cs.LG cs.AI

Is Value Learning Really the Main Bottleneck in Offline RL?

Seohong Park, Kevin Frans, Sergey Levine, Aviral Kumar

Comments NeurIPS 2024

2406.06523 2024-10-30 cs.CV

NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing

Ting-Hsuan Chen, Jiewen Chan, Hau-Shiang Shiu, Shih-Han Yen, Chang-Han Yeh, Yu-Lun Liu

Comments NeurIPS 2024. Project page: https://koi953215.github.io/NaRCan_page/ Code: https://github.com/koi953215/NaRCan

2406.03949 2024-10-30 cs.CL

UltraMedical: Building Specialized Generalists in Biomedicine

Kaiyan Zhang, Sihang Zeng, Ermo Hua, Ning Ding, Zhang-Ren Chen, Zhiyuan Ma, Haoxin Li, Ganqu Cui, Biqing Qi, Xuekai Zhu, Xingtai Lv, Hu Jinfang, Zhiyuan Liu, Bowen Zhou

Comments Camera ready version for NeurIPS 2024 D&B Track

2406.01946 2024-10-30 cs.CR cs.CL

Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature

Tong Zhou, Xuandong Zhao, Xiaolin Xu, Shaolei Ren

Comments NeurIPS 2024 camera-ready

2406.00943 2024-10-30 cs.LG cs.AI

State Space Models on Temporal Graphs: A First-Principles Study

Jintang Li, Ruofan Wu, Xinzhou Jin, Boqun Ma, Liang Chen, Zibin Zheng

Comments Accepted by NeurIPS 2024

2406.00048 2024-10-30 cs.CL cond-mat.dis-nn cs.LG

Towards a theory of how the structure of language is acquired by deep neural networks

Francesco Cagnetta, Matthieu Wyart

Comments NeurIPS 2024

2405.19487 2024-10-30 cs.CL

A Full-duplex Speech Dialogue Scheme Based On Large Language Models

Peng Wang, Songshuo Lu, Yaohua Tang, Sijie Yan, Wei Xia, Yuanjun Xiong

Comments Accepted to NeurIPS 2024

2405.16075 2024-10-30 cs.LG cs.AI

Continuous Temporal Domain Generalization

Zekun Cai, Guangji Bai, Renhe Jiang, Xuan Song, Liang Zhao

Comments Accepted by NeurIPS 2024

2405.15769 2024-10-30 cs.CV

FastDrag: Manipulate Anything in One Step

Xuanjia Zhao, Jian Guan, Congyi Fan, Dongli Xu, Youtian Lin, Haiwei Pan, Pengming Feng

Comments NeurIPS 2024 Accept, Project Page: https://fastdrag-site.github.io/

2405.15179 2024-10-30 cs.CL

VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks

Yang Li, Shaobo Han, Shihao Ji

Comments NeurIPS 2024

2405.14822 2024-10-30 cs.CV cs.AI cs.LG stat.ML

PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher

Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon

Comments NeurIPS 2024

2405.14569 2024-10-30 cs.CR cs.AI

PrivCirNet: Efficient Private Inference via Block Circulant Transformation

Tianshi Xu, Lemeng Wu, Runsheng Wang, Meng Li

Comments NeurIPS'2024

2405.14312 2024-10-30 cs.CV cs.CL cs.MM

Improving Gloss-free Sign Language Translation by Reducing Representation Density

Jinhui Ye, Xing Wang, Wenxiang Jiao, Junwei Liang, Hui Xiong

Comments Accepted at NeurIPS'24; Representation Density Problem and Performance Drop in Gloss-free SLT

2405.13943 2024-10-30 cs.CV

DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

Yu Chen, Gim Hee Lee

Comments Accepted to NeurIPS 2024

2405.12203 2024-10-30 cs.IT cs.LG math.IT

Accelerating Relative Entropy Coding with Space Partitioning

Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato

Comments NeurIPS 2024 camera-ready version. 31 pages, 12 figures, 5 algorithms

2404.08660 2024-10-30 cs.IR cs.LG

How Does Message Passing Improve Collaborative Filtering?

Mingxuan Ju, William Shiao, Zhichun Guo, Yanfang Ye, Yozen Liu, Neil Shah, Tong Zhao

Comments Accepted to NeurIPS'24. Code available at: https://github.com/snap-research/Test-time-Aggregation-for-CF

2404.04375 2024-10-30 cs.LG cs.SY eess.SY

ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks

Yuezhu Xu, S. Sivaranjani

Comments Accepted at NeurIPS 2024; 28 pages, 7 figures

2404.04125 2024-10-30 cs.CV cs.CL cs.LG

No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance

Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip H. S. Torr, Adel Bibi, Samuel Albanie, Matthias Bethge

Comments Short version accepted at DPFM, ICLR'24; Full paper at NeurIPS'24

2404.01595 2024-10-30 cs.LG stat.ME stat.ML

Propensity Score Alignment of Unpaired Multimodal Data

Johnny Xi, Jana Osea, Zuheng Xu, Jason Hartford

Comments NeurIPS 2024

2403.15371 2024-10-30 cs.LG cs.AI cs.CL

Can large language models explore in-context?

Akshay Krishnamurthy, Keegan Harris, Dylan J. Foster, Cyril Zhang, Aleksandrs Slivkins

Comments Accepted to NeurIPS 2024. This version: added references to related and concurrent work

2403.07350 2024-10-30 cs.CL cs.AI cs.CV

VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark

Han Huang, Haitian Zhong, Tao Yu, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan

Comments NeurIPS 2024, Datasets and Benchmarks Track

2403.02528 2024-10-30 cs.CL cs.AI

DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation

Xueqing Wu, Rui Zheng, Jingzhen Sha, Te-Lin Wu, Hanyu Zhou, Mohan Tang, Kai-Wei Chang, Nanyun Peng, Haoran Huang

Comments NeurIPS 2024 Dataset and Benchmark Track