ICLR - arXivDaily 期刊&会议

2310.00390 2024-03-19 cs.CV

InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists

Yulu Gan, Sungwoo Park, Alexander Schubert, Anthony Philippakis, Ahmed M. Alaa

Comments ICLR 2024; Code is available at https://github.com/AlaaLab/InstructCV

2309.11499 2024-03-19 cs.CV cs.CL cs.LG

DreamLLM: Synergistic Multimodal Comprehension and Creation

Runpei Dong, Chunrui Han, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, Li Yi

Comments ICLR 2024 (Spotlight)

2307.12950 2024-03-19 cs.CL cs.AI

RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment

Kevin Yang, Dan Klein, Asli Celikyilmaz, Nanyun Peng, Yuandong Tian

Comments ICLR 2024

2306.09884 2024-03-19 cs.LG cs.AI

Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX

Clément Bonnet, Daniel Luo, Donal Byrne, Shikha Surana, Sasha Abramowitz, Paul Duckworth, Vincent Coyette, Laurence I. Midgley, Elshadai Tegegn, Tristan Kalloniatis, Omayma Mahjoub, Matthew Macfarlane, Andries P. Smit, Nathan Grinsztajn, Raphael Boige, Cemlyn N. Waters, Mohamed A. Mimouni, Ulrich A. Mbou Sob, Ruan de Kock, Siddarth Singh, Daniel Furelos-Blanco, Victor Le, Arnu Pretorius, Alexandre Laterre

Comments 9 pages + 21 pages of appendices and references. Published at ICLR 2024

2302.05825 2024-03-19 cs.LG math.FA stat.ML

Koopman-based generalization bound: New aspect for full-rank weights

Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki

Journal ref ICLR 2024

2302.02060 2024-03-19 cs.CL cs.LG

Representation Deficiency in Masked Language Modeling

Yu Meng, Jitin Krishnan, Sinong Wang, Qifan Wang, Yuning Mao, Han Fang, Marjan Ghazvininejad, Jiawei Han, Luke Zettlemoyer

Comments ICLR 2024

2205.12532 2024-03-19 cs.LG cs.LO

Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning

Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman

Comments Published as a conference paper at ICLR 2024

2403.09953 2024-03-18 cs.LG

Online GNN Evaluation Under Test-time Graph Distribution Shifts

Xin Zheng, Dongjin Song, Qingsong Wen, Bo Du, Shirui Pan

Comments Accepted by ICLR-2024

2403.09889 2024-03-18 cs.LG

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Yihang Chen, Fanghui Liu, Yiping Lu, Grigorios G. Chrysos, Volkan Cevher

Comments ICLR 2024 (Spotlight)

2403.09766 2024-03-18 cs.CV

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models

Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr

Comments Accepted to ICLR 2024

2403.08017 2024-03-18 cs.CV cs.AI

Red Teaming Models for Hyperspectral Image Analysis Using Explainable AI

Vladimir Zaigrajew, Hubert Baniecki, Lukasz Tulczyjew, Agata M. Wijata, Jakub Nalepa, Nicolas Longépé, Przemyslaw Biecek

Comments 14 pages, 9 figures, ICLR 2024 Machine Learning for Remote Sensing (ML4RS) Workshop

2402.15656 2024-03-18 cs.LG cs.AI cs.NA math.NA

Learning Semilinear Neural Operators : A Unified Recursive Framework For Prediction And Data Assimilation

Ashutosh Singh, Ricardo Augusto Borsoi, Deniz Erdogmus, Tales Imbiriba

Comments ICLR 2024

2402.02340 2024-03-18 cs.CV cs.LG

Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning

Li Ren, Chen Chen, Liqiang Wang, Kien Hua

Comments Published in ICLR 2024

2312.08515 2024-03-18 cs.LG math.AT

Simplicial Representation Learning with Neural $k$-Forms

Kelly Maggs, Celia Hacker, Bastian Rieck

Comments Accepted at ICLR 2024 (https://openreview.net/forum?id=Djw0XhjHZb)

2312.05742 2024-03-18 cs.LG cs.AI

The Generalization Gap in Offline Reinforcement Learning

Ishita Mediratta, Qingfei You, Minqi Jiang, Roberta Raileanu

Comments Published as a conference paper at ICLR 2024; First two authors contributed equally

2312.02436 2024-03-18 cs.CL cs.AI

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following

Renze Lou, Kai Zhang, Jian Xie, Yuxuan Sun, Janice Ahn, Hanzi Xu, Yu Su, Wenpeng Yin

Comments ICLR 2024. Data, model, and code are available at: https://renzelou.github.io/Muffin/

2311.07604 2024-03-18 cs.LG cs.AI cs.CV cs.CY

Finetuning Text-to-Image Diffusion Models for Fairness

Xudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, Mohan Kankanhalli

Comments ICLR 2024 oral presentation

2311.07593 2024-03-18 cs.CL cs.CV cs.LG

Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

Reza Esfandiarpoor, Stephen H. Bach

Comments ICLR 2024

2311.00500 2024-03-18 cs.LG cs.AI cs.CV

Intriguing Properties of Data Attribution on Diffusion Models

Xiaosen Zheng, Tianyu Pang, Chao Du, Jing Jiang, Min Lin

Comments ICLR 2024

2310.19791 2024-03-18 cs.CL cs.AI cs.LG cs.PL

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

Gabriel Grand, Lionel Wong, Maddy Bowers, Theo X. Olausson, Muxin Liu, Joshua B. Tenenbaum, Jacob Andreas

Comments ICLR 2024 camera-ready

2310.13011 2024-03-18 cs.CL cs.LG

Compositional preference models for aligning LMs

Dongyoung Go, Tomasz Korbak, Germán Kruszewski, Jos Rozen, Marc Dymetman

Comments ICLR 2024

2310.09562 2024-03-18 cs.CV cs.AI cs.LG

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?

Prasanna Mayilvahanan, Thaddäus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel

Comments ICLR 2024 camera-ready version

2310.08579 2024-03-18 cs.CV

HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion

Xian Liu, Jian Ren, Aliaksandr Siarohin, Ivan Skorokhodov, Yanyu Li, Dahua Lin, Xihui Liu, Ziwei Liu, Sergey Tulyakov

Comments Accepted by ICLR 2024, camera-ready version. Project Page: https://snap-research.github.io/HyperHuman/

2310.08391 2024-03-18 stat.ML cs.LG

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?

Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Peter L. Bartlett

Comments ICLR 2024 Camera Ready

2310.07297 2024-03-18 cs.LG

Score Regularized Policy Optimization through Diffusion Behavior

Huayu Chen, Cheng Lu, Zhengyi Wang, Hang Su, Jun Zhu

Comments ICLR 2024

2310.06020 2024-03-18 cs.CV cs.AI cs.GR cs.LG cs.RO

DyST: Towards Dynamic Neural Scene Representations on Real-World Videos

Maximilian Seitzer, Sjoerd van Steenkiste, Thomas Kipf, Klaus Greff, Mehdi S. M. Sajjadi

Comments ICLR 2024 spotlight. Project website: https://dyst-paper.github.io/

2310.05725 2024-03-18 stat.ML cs.LG

Post-hoc Bias Scoring Is Optimal For Fair Classification

Wenlong Chen, Yegor Klochkov, Yang Liu

Comments Published at The Twelfth International Conference on Learning Representations (ICLR 2024)

2310.02970 2024-03-18 cs.LG math.GR

Fast, Expressive SE$(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space

Erik J Bekkers, Sharvaree Vadgama, Rob D Hesselink, Putri A van der Linden, David W Romero

Comments Our code is publicly available at https://github.com/ebekkers/ponita . Published at ICLR 2024

2310.02227 2024-03-18 cs.LG cs.AI

SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training

Kazem Meidani, Parshin Shojaee, Chandan K. Reddy, Amir Barati Farimani

Comments ICLR 2024 Spotlight Paper

2310.02025 2024-03-18 cs.LG

DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training

Aochuan Chen, Yimeng Zhang, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu

Comments Accepted to ICLR'24. Codes are available at https://github.com/OPTML-Group/DeepZero