ICLR

ControlAR: Controllable Image Generation with Autoregressive Models

Zongming Li, Tianheng Cheng, Shoufa Chen, Peize Sun, Haocheng Shen, Longjin Ran, Xiaoxin Chen, Wenyu Liu, Xinggang Wang

Comments To appear in ICLR 2025

Provably Accurate Shapley Value Estimation via Leverage Score Sampling

Christopher Musco, R. Teal Witter

Comments Accepted to ICLR 2025

Personality Alignment of Large Language Models

Minjun Zhu, Yixuan Weng, Linyi Yang, Yue Zhang

Comments Acecpt in ICLR 2025

Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach

Zechen Bai, Tianjun Xiao, Tong He, Pichao Wang, Zheng Zhang, Thomas Brox, Mike Zheng Shou

Comments Accepted by ICLR 2025

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

Yuang Peng, Yuxin Cui, Haomiao Tang, Zekun Qi, Runpei Dong, Jing Bai, Chunrui Han, Zheng Ge, Xiangyu Zhang, Shu-Tao Xia

Comments ICLR 2025, Project page: https://dreambenchplus.github.io/

SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation

Koichi Saito, Dongjun Kim, Takashi Shibuya, Chieh-Hsin Lai, Zhi Zhong, Yuhta Takida, Yuki Mitsufuji

Comments Audio samples: https://anonymus-soundctm.github.io/soundctm_iclr/. Codes: https://github.com/sony/soundctm. Checkpoints: https://huggingface.co/Sony/soundctm

Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering

Yibo Zhang, Lihong Wang, Changqing Zou, Tieru Wu, Rui Ma

Comments ICLR 2025

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

Yongxin Guo, Zhenglin Cheng, Xiaoying Tang, Zhaopeng Tu, Tao Lin

Comments ICLR 2025

How Much is Unseen Depends Chiefly on Information About the Seen

Seongmin Lee, Marcel Böhme

Comments 13 pages, 11 pages of appendix, ICLR'25

SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography

Xuanyu Zhang, Jiarui Meng, Zhipei Xu, Shuzhou Yang, Yanmin Wu, Ronggang Wang, Jian Zhang

Comments Accepted by ICLR 2025

LapLoss: Laplacian Pyramid-based Multiscale loss for Image Translation

Krish Didwania, Ishaan Gakhar, Prakhar Arya, Sanskriti Labroo

Comments Accepted at the DeLTa Workshop, ICLR 2025

Holistically Evaluating the Environmental Impact of Creating Language Models

Jacob Morrison, Clara Na, Jared Fernandez, Tim Dettmers, Emma Strubell, Jesse Dodge

Comments ICLR 2025 (spotlight)

LEWIS (LayEr WIse Sparsity) -- A Training Free Guided Model Merging Approach

Hetarth Chopra, Vidhi Rambhia, Vikram Adve

Comments Accepted at ICLR 2025 Workshop: SLLM (Sparsity in Large Language Models)

Strong Preferences Affect the Robustness of Preference Models and Value Alignment

Ziwei Xu, Mohan Kankanhalli

Comments 21 Pages. Accepted by ICLR 2025

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions

Sarah Wiegreffe, Oyvind Tafjord, Yonatan Belinkov, Hannaneh Hajishirzi, Ashish Sabharwal

Comments ICLR 2025 (spotlight). Substantially updated from previous preprint to contain experiments on 4-way multiple-choice with various answer choice symbols, 3 open model families, and extensive activation patching results, including on individual attention heads

Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

Yeongmin Kim, Kwanghyeon Lee, Minsang Park, Byeonghu Na, Il-Chul Moon

Comments ICLR 2025 Spotlight

Quantum-PEFT: Ultra parameter-efficient fine-tuning

Toshiaki Koike-Akino, Francesco Tonin, Yongtao Wu, Frank Zhengqing Wu, Leyla Naz Candogan, Volkan Cevher

Comments ICLR 2025

Uncertainty-Aware Decoding with Minimum Bayes Risk

Nico Daheim, Clara Meister, Thomas Möllenhoff, Iryna Gurevych

Comments ICLR 2025 (Poster)

Robust Conformal Prediction with a Single Binary Certificate

Soroush H. Zargarbashi, Aleksandar Bojchevski

Comments Published as a conference paper at ICLR 2025

Fair Clustering in the Sliding Window Model

Vincent Cohen-Addad, Shaofeng H. -C. Jiang, Qiaoyuan Yang, Yubo Zhang, Samson Zhou

Comments ICLR 2025

RocketEval: Efficient Automated LLM Evaluation via Grading Checklist

Tianjun Wei, Wei Wen, Ruizhi Qiao, Xing Sun, Jianghong Ma

Comments Accepted by ICLR 2025: https://openreview.net/forum?id=zJjzNj6QUe

On a Connection Between Imitation Learning and RLHF

Teng Xiao, Yige Yuan, Mingxiao Li, Zhengyu Chen, Vasant G Honavar

Comments ICLR 2025

ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

Hannes Stark, Bowen Jing, Tomas Geffner, Jason Yim, Tommi Jaakkola, Arash Vahdat, Karsten Kreis

Comments Published as a conference paper and Oral (top 1.8%) at ICLR 2025

Energy-Weighted Flow Matching for Offline Reinforcement Learning

Shiyuan Zhang, Weitong Zhang, Quanquan Gu

Comments 28 pages, 11 figures, accepted by ICLR 2025

Are Large Language Models Good In-context Learners for Financial Sentiment Analysis?

Xinyu Wei, Luojia Liu

Comments Accepted by ICLR 2025 Workshop on Advances in Financial AI

Distilling Dataset into Neural Field

Donghyeok Shin, HeeSun Bae, Gyuwon Sim, Wanmo Kang, Il-Chul Moon

Comments The Thirteenth International Conference on Learning Representations (ICLR 2025)

Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators

Hritik Bansal, Pratyush Maini

Comments Published as a blogpost at ICLR 2025. Originally posted at https://pratyushmaini.github.io/blog/2024/risks-private-evals/

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains

Wonje Choi, Jinwoo Park, Sanghyun Ahn, Daehee Lee, Honguk Woo

Comments Accepted at ICLR 2025. Project site with code: https://pjw971022.github.io/nesyc/

CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression

Yu-Ting Zhan, Cheng-Yuan Ho, Hebi Yang, Yi-Hsin Chen, Jui Chiu Chiang, Yu-Lun Liu, Wen-Hsiao Peng

Comments Accepted for Publication in International Conference on Learning Representations (ICLR)

Journal ref ICLR 2025

Shh, don't say that! Domain Certification in LLMs

Cornelius Emde, Alasdair Paren, Preetham Arvind, Maxime Kayser, Tom Rainforth, Thomas Lukasiewicz, Bernard Ghanem, Philip H. S. Torr, Adel Bibi

Comments 10 pages, includes appendix Published in International Conference on Learning Representations (ICLR) 2025

Journal ref International Conference on Learning Representations (ICLR) 2025