ICLR 2025 Conference Submissions

Task-agnostic Pre-training and Task-guided Fine-tuning for Versatile Diffusion Planner
Chenyou Fan, Chenjia Bai, Zhao Shan, Haoran He, Yang Zhang, Zhen Wang
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
Bingrui Li, Wei Huang, Andi Han, Zhanpeng Zhou, Taiji Suzuki, Jun Zhu, Jianfei Chen
- Published: 22 Jan 2025, Last Modified: 01 May 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Lens: Rethinking Multilingual Enhancement for Large Language Models
Weixiang Zhao, Yulin Hu, Jiahe Guo, Xingyu Sui, Tongtong Wu, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, Ting Liu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
Yonatan Slutzky, Yotam Alexander, Noam Razin, Nadav Cohen
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Attention as a Hypernetwork
Simon Schug, Seijin Kobayashi, Yassir Akram, Joao Sacramento, Razvan Pascanu
- Published: 22 Jan 2025, Last Modified: 17 Feb 2025
- ICLR 2025 Oral
- Readers: Everyone
IN the known, OUT of the ordinary: Probing OOD detection methods with Synthetic datasets.
Amruth Sagar, Ravi Kiran Sarvadevabhatla
- 27 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PFGuard: A Generative Framework with Privacy and Fairness Safeguards
Soyeon Kim, Yuji Roh, Geon Heo, Steven Euijong Whang
- Published: 22 Jan 2025, Last Modified: 20 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Rethinking Uncertainty Estimation in Natural Language Generation
Lukas Aichberger, Kajetan Schweighofer, Sepp Hochreiter
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Evaluating Robustness of Reward Models for Mathematical Reasoning
Sunghwan Kim, Dongjin Kang, Taeyoon Kwon, Hyungjoo Chae, Jungsoo Won, Dongha Lee, Jinyoung Yeo
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
LLM-Informed Semi-Supervised Learning for Text Classification
Tiberiu Sosea, Cornelia Caragea
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ProteinWeaver: A Divide-and-Assembly Approach for Protein Backbone Design
Yiming Ma, Fei YE, Yi Zhou, Zaixiang Zheng, Dongyu Xue, Quanquan Gu
- 27 Sept 2024 (modified: 23 Nov 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Jiale Cheng, Xiao Liu, Cunxiang Wang, Xiaotao Gu, Yida Lu, Dan Zhang, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking
Zhuang Li, YUNCHENG HUA, Thuy-Trang Vu, Haolan Zhan, Lizhen Qu, Gholamreza Haffari
- 27 Sept 2024 (modified: 13 Mar 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment
Yifei Xing, Xiangyuan Lan, Ruiping Wang, Dongmei Jiang, Wenjun Huang, Zheng Qingfang, Yaowei Wang
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Mitigating Spurious Bias with Last-Layer Selective Activation Retraining
Guangtao Zheng, Wenqian Ye, Aidong Zhang
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Emergent Orientation Maps —— Mechanisms, Coding Efficiency and Robustness
Haixin Zhong, Haoyu Wang, Wei P Dai, Yuchao Huang, Mingyi Huang, Rubin Wang, Anna Wang Roe, yuguo yu
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Spotlight
- Readers: Everyone
OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning
Pengxiang Li, Lu Yin, Xiaowei Gao, Shiwei Liu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
packetLSTM: Dynamic LSTM Framework for Streaming Data with Varying Feature Space
Rohit Agarwal, Karaka Prasanth Naidu, Alexander Horsch, Krishna Agarwal, Dilip Prasad
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
From Link Prediction to Forecasting: Information Loss in Batch-based Temporal Graph Learning
Moritz Lampert, Christopher Blöcker, Ingo Scholtes
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Active Fine-Tuning of Generalist Policies
Marco Bagatella, Jonas Hübotter, Georg Martius, Andreas Krause
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
Tanqiu Jiang, Changjiang Li, Fenglong Ma, Ting Wang
- Published: 22 Jan 2025, Last Modified: 18 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks
Maximilian Muschalik, Fabian Fumagalli, Paolo Frazzetto, Janine Strotherm, Luca Hermes, Alessandro Sperduti, Eyke Hüllermeier, Barbara Hammer
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Privacy as a Free Lunch: Crafting Initial Distilled Datasets through the Kaleidoscope
Shuo Shi, Peng Sun, Xinyi Shang, Tianyu Du, Xuhong Zhang, Jianwei Yin, Tao Lin
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
GARLIC: LLM-Guided Dynamic Progress Control with Hierarchical Weighted Graph for Long Document QA
Xinyu Wang, Yanzheng Xiang, Lin Gui, Yulan He
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models with Leaky Visual Conversations
Gokul Karthik Kumar, Iheb Chaabane, Kebin Wu
- 27 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone