ICLR - arXivDaily 期刊&会议

2402.10433 2024-03-13 q-bio.BM cs.LG q-bio.QM

Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations

Jiarui Lu, Zuobai Zhang, Bozitao Zhong, Chence Shi, Jian Tang

Comments Published at the GEM workshop, ICLR 2024

2401.11725 2024-03-13 cs.CL

Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models

Yile Wang, Sijie Cheng, Zixin Sun, Peng Li, Yang Liu

Comments ICLR AGI Workshop 2024

2401.11237 2024-03-13 cs.LG

Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View

Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach

Comments ICLR 2024, Project code: https://github.com/RajGhugare19/stitching-is-combinatorial-generalisation

2401.04578 2024-03-13 cs.CV

Effective pruning of web-scale datasets based on complexity of concept clusters

Amro Abbas, Evgenia Rusak, Kushal Tirumala, Wieland Brendel, Kamalika Chaudhuri, Ari S. Morcos

Comments Accepted at ICLR 2024, code available at https://github.com/amro-kamal/effective_pruning

2310.06117 2024-03-13 cs.LG cs.AI cs.CL

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H. Chi, Quoc V Le, Denny Zhou

Comments ICLR 2024

2310.03646 2024-03-13 cs.LG cs.CL

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

Tom Sherborne, Naomi Saphra, Pradeep Dasigi, Hao Peng

Comments Camera Ready for ICLR 2024 (Accepted as Spotlight). 21 pages, 14 tables, 2 figures

2310.02832 2024-03-13 cs.LG cs.CL

Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness

Fran Jelenić, Josip Jukić, Martin Tutek, Mate Puljiz, Jan Šnajder

Comments International Conference on Learning Representations: ICLR 2024

2309.16319 2024-03-13 cs.CL cs.AI

Augmenting Transformers with Recursively Composed Multi-grained Representations

Xiang Hu, Qingyang Zhu, Kewei Tu, Wei Wu

Comments ICLR 2024 poster

2309.10691 2024-03-13 cs.CL cs.AI cs.LG

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback

Xingyao Wang, Zihan Wang, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, Heng Ji

Comments ICLR 2024. Code is available on our project website: https://xingyaoww.github.io/mint-bench

2308.10547 2024-03-13 math.OC cs.LG cs.SY eess.SY

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

Jun Chen, Haishan Ye, Mengmeng Wang, Tianxin Huang, Guang Dai, Ivor W. Tsang, Yong Liu

Journal ref International Conference on Learning Representations, 2024

2306.03117 2024-03-13 q-bio.QM cs.LG q-bio.BM

Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling

Jiarui Lu, Bozitao Zhong, Zuobai Zhang, Jian Tang

Comments Published as a conference paper at ICLR 2024, see https://openreview.net/forum?id=C4BikKsgmK

2305.14585 2024-03-13 cs.LG

Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models

Andrew Engel, Zhichao Wang, Natalie S. Frank, Ioana Dumitriu, Sutanay Choudhury, Anand Sarwate, Tony Chiang

Comments 9 pages, 2 figures, 3 tables Updated 3/11/2024 various additions/clarifications after ICLR review. Accepted as a Spotlight paper at ICLR 2024

2305.14550 2024-03-13 cs.LG cs.AI

When should we prefer Decision Transformers for Offline Reinforcement Learning?

Prajjwal Bhargava, Rohan Chitnis, Alborz Geramifard, Shagun Sodhani, Amy Zhang

Comments International Conference on Learning Representations (ICLR) 2024

2403.06971 2024-03-12 cs.LG cs.IT math.IT

A representation-learning game for classes of prediction tasks

Neria Uzan, Nir Weinberger

Comments ICLR 2024

2403.06826 2024-03-12 cs.LG cs.AI stat.ML

In-context Exploration-Exploitation for Reinforcement Learning

Zhenwen Dai, Federico Tomasi, Sina Ghiassian

Comments Published at ICLR 2024

2403.06425 2024-03-12 cs.LG cs.AI

A Differential Geometric View and Explainability of GNN on Evolving Graphs

Yazheng Liu, Xi Zhang, Sihong Xie

Comments Accepted into ICLR 2023

2403.06392 2024-03-12 cs.LG

Towards Robust Out-of-Distribution Generalization Bounds via Sharpness

Yingtian Zou, Kenji Kawaguchi, Yingnan Liu, Jiashuo Liu, Mong-Li Lee, Wynne Hsu

Comments 40 pages, 9 figures, ICLR 2024 Spotlight Presentation

2401.13171 2024-03-12 cs.LG cs.AI cs.CE

Compositional Generative Inverse Design

Tailin Wu, Takashi Maruyama, Long Wei, Tao Zhang, Yilun Du, Gianluca Iaccarino, Jure Leskovec

Comments ICLR 2024 spotlight. 30 pages, 17 figures

2401.08819 2024-03-12 cs.LG cs.AI

Learning from Sparse Offline Datasets via Conservative Density Estimation

Zhepeng Cen, Zuxin Liu, Zitong Wang, Yihang Yao, Henry Lam, Ding Zhao

Comments ICLR 2024

2311.15100 2024-03-12 cs.CV cs.AI cs.LG

Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation

Luca Eyring, Dominik Klein, Théo Uscidda, Giovanni Palla, Niki Kilbertus, Zeynep Akata, Fabian Theis

Comments ICLR 2024

2311.00262 2024-03-12 cs.CL cs.AI

Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents

Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua

Comments Accepted by ICLR 2024

2310.16047 2024-03-12 cs.CV cs.LG eess.IV

From Posterior Sampling to Meaningful Diversity in Image Restoration

Noa Cohen, Hila Manor, Yuval Bahat, Tomer Michaeli

Comments Accepted for ICLR 2024. Code and examples are available at https://noa-cohen.github.io/MeaningfulDiversityInIR

2310.05136 2024-03-12 cs.AI cs.CV

InstructDET: Diversifying Referring Object Detection with Generalized Instructions

Ronghao Dang, Jiangyan Feng, Haodong Zhang, Chongjian Ge, Lin Song, Lijun Gong, Chengju Liu, Qijun Chen, Feng Zhu, Rui Zhao, Yibing Song

Comments 29 pages (include Appendix) Published in ICLR

2310.01706 2024-03-12 cs.LG

On Representation Complexity of Model-based and Model-free Reinforcement Learning

Hanlin Zhu, Baihe Huang, Stuart Russell

Comments 23 pages, 9 figures, to be published in ICLR 2024

2309.17002 2024-03-12 cs.LG cs.AI cs.CV

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

Hao Chen, Jindong Wang, Ankit Shah, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj

Comments ICLR 2024 Spotlight

2309.14859 2024-03-12 cs.CV cs.AI cs.GR cs.LG

Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation

Shih-Ying Yeh, Yu-Guan Hsieh, Zhidong Gao, Bernard B W Yang, Giyeong Oh, Yanmin Gong

Comments In International Conference on Learning Representations 12 (ICLR 2024) [79 pages, 54 figures, 7 tables]

2309.14675 2024-03-12 cs.LG cs.DC

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler

Zilinghan Li, Pranshu Chaturvedi, Shilan He, Han Chen, Gagandeep Singh, Volodymyr Kindratenko, E. A. Huerta, Kibaek Kim, Ravi Madduri

Comments Accepted as poster at The Twelfth International Conference on Learning Representations (ICLR 2024)

2309.12819 2024-03-12 stat.ME cs.LG

Doubly Robust Proximal Causal Learning for Continuous Treatments

Yong Wu, Yanwei Fu, Shouyan Wang, Xinwei Sun

Comments Published as a conference paper at ICLR 2024

2309.03883 2024-03-12 cs.CL cs.AI cs.LG

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, Pengcheng He

Comments ICLR 2024 main conference paper. The source code is available at https://github.com/voidism/DoLa

2306.02879 2024-03-12 cs.LG

Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization

Yibing Liu, Chris Xing Tian, Haoliang Li, Lei Ma, Shiqi Wang

Comments ICLR 2024 Spotlight