ICLR 2025 Conference Submissions

COBias and Debias: Minimizing Language Model Pairwise Accuracy Bias via Nonlinear Integer Programming
Ruixi Lin, Yang You
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
PerFIT: Personalized Federated Instruction Tuning via Neural Architecture Search
Pengyu Zhang, Yingbo Zhou, Ming Hu, Junxian Feng, Yao Liu, Xian Wei, Mingsong Chen
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
A transfer learning framework for weak to strong generalization
Seamus Somerstep, Felipe Maia Polo, Moulinath Banerjee, Yaacov Ritov, Mikhail Yurochkin, Yuekai Sun
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting
Haoyuan Li, Zhou Yanpeng, Tao Tang, Jifei Song, Yihan Zeng, Michael Kampffmeyer, Hang Xu, Xiaodan Liang
- Published: 22 Jan 2025, Last Modified: 08 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Language Representations Can be What Recommenders Need: Findings and Potentials
Leheng Sheng, An Zhang, Yi Zhang, Yuxin Chen, Xiang Wang, Tat-Seng Chua
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Oral
- Readers: Everyone
ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts
Xumeng Han, Longhui Wei, Zhiyang Dou, Zipeng Wang, Chenhui Qiang, XIN HE, Yingfei Sun, Zhenjun Han, Qi Tian
- 26 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Multi-Task Dense Predictions via Unleashing the Power of Diffusion
Yuqi Yang, Peng-Tao Jiang, Qibin Hou, Hao Zhang, Jinwei Chen, Bo Li
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
P-BERT: Hardware-Aware Optimization of BERT Using Evolutionary Techniques
Lim Sze Ying, Zhehui Wang, Rick Siow Mong Goh, Tao Luo
- 26 Sept 2024 (modified: 20 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Demystifying the Token Dynamics of Deep Selective State Space Models
Thieu Vo, Duy-Tung Pham, Xin T. Tong, Tan Minh Nguyen
- Published: 22 Jan 2025, Last Modified: 14 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Insufficient Task Description can Impair In-context Learning: A Study from Information Perspective
Meidai Xuanyuan, Tao Yang, Jingwen Fu, Yuwang Wang
- 26 Sept 2024 (modified: 18 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Model Collapse Analysis and Improvement for Rectified Flow Models
Huminhao Zhu, Fangyikang Wang, Tianyu Ding, Qing Qu, Zhihui Zhu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Contrastive Learning Via Equivariant Representation
Sifan Song, Jinfeng Wang, Qiaochu Zhao, Xiang Li, Dufan Wu, Angelos Stefanidis, Jionglong Su, S Kevin Zhou, Quanzheng Li
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ScalePerson: Towards Good Practices in Evaluating Physical Adversarial Attacks on Person Detection
Hui Wei, Yuanwei Liu, Xuemei Jia, Baraa Al-Hassani, Manhuen Zhang, Joey Tianyi Zhou, Zheng Wang
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Understanding Self-supervised Learning as an Approximation of Supervised Learning
Byeongchan Lee
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset
Yiqin Yang, Quanwei Wang, Chenghao Li, Hao Hu, Chengjie Wu, Yuhua Jiang, Dianyu Zhong, Ziyou Zhang, Qianchuan Zhao, Chongjie Zhang, Bo XU
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
GroupCoOp: Group-robust Fine-tuning via Group Prompt Learning
Nayeong Kim, Seong Joon Oh, Suha Kwak
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Off-policy Evaluation with Deeply-abstracted States
Meiling Hao, Pingfan Su, Liyuan Hu, Zoltán Szabó, Qingyuan Zhao, Chengchun Shi
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Abhay Sheshadri, Aidan Ewart, Phillip Huang Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, Stephen Casper
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Incremental Aggregated Asynchronous SGD for Arbitrarily Heterogeneous Data
Xiaolu Wang, Yuchang Sun, Hoi To Wai, Jun Zhang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Distinct and Shared Concept Discovery for Fine-grained Concept Inversion
Nam Hyeon-Woo, Jongheon Jeong, Subin Kim, Tae-Hyun Oh
- 26 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Rethinking the Roles of Time and Frequency Domains Before Tackling Time Series UDA
Fang-Yi Su, Ching Chieh Tsao, Jung-Hsien Chiang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
JudgeRail: Harnessing Open-Source LLMs for Fast Harmful Text Detection with Judicial Prompting and Logit Rectification
Zhongjie Ba, Hongye Fu, Yiqi Yang, Hui Chen, Qinglong Wang, Peng Cheng, Zhan Qin, Kui Ren
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Turning Challenges into Opportunities: How Distribution Shifts Enhance Identifiability in Causal Representation Learning
Yuhang Liu, Zhen Zhang, Dong Gong, Biwei Huang, Mingming Gong, Anton van den Hengel, Kun Zhang, Javen Qinfeng Shi
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Training-free Detection of AI-generated Images via High-frequency Influence
Sungik Choi, Sungwoo Park, Jaehoon Lee, SeungHyun Kim, Stanley Jungkyu Choi, Moontae Lee
- 26 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
From Commands to Prompts: LLM-based Semantic File System for AIOS
Zeru Shi, Kai Mei, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu, Mengnan Du, Dong Deng, Yongfeng Zhang
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone