ICLR 2025 Conference Submissions

One Step Diffusion via Shortcut Models
Kevin Frans, Danijar Hafner, Sergey Levine, Pieter Abbeel
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola, Markos Georgopoulos, Artsiom Sanakoyeu, Yuming Du, Edgar Schönfeld, Ali Thabet, Jonas K Kohler
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Oral
- Readers: Everyone
Scale-Free Graph-Language Models
Jianglin Lu, Yixuan Liu, Yitian Zhang, Yun Fu
- Published: 22 Jan 2025, Last Modified: 21 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, junxian guo, Shang Yang, Haotian Tang, Yao Fu, Song Han
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Private Stochastic Convex Optimization with Tysbakov Noise Condition and Large Lipschitz Constant
Difei Xu, Meng Ding, Zihang Xiang, Jinhui Xu, Di Wang
- 25 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Feature Matching Intervention: Leveraging Observational Data for Causal Representation Learning
Haoze Li, Jun Xie
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Density Ratio Estimation-based Bayesian Optimization with Semi-Supervised Learning
Jungtaek Kim
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models
Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Knockout: A simple way to handle missing inputs
Minh Nguyen, Batuhan K. Karaman, Heejong Kim, Alan Q. Wang, Fengbei Liu, Mert R. Sabuncu
- 25 Sept 2024 (modified: 08 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen
- 25 Sept 2024 (modified: 14 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Robustness Inspired Graph Backdoor Defense
Zhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu, Enyan Dai, Suhang Wang
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Oral
- Readers: Everyone
Counterfactual Explanations for 3D Point-Cloud Classifiers
Yann Bouquet, Zhuoqian Yang, Mathieu Salzmann
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Risk Aware Negative Sampling in Link Prediction
Thomas Markovich, Zahra Fazel, Muberra Ozmen, Florence Regol
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies
Shalini Sarode, Muhammad Saif Ullah Khan, Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
Qi CHEN, Jierui Zhu, Florian Shkurti
- Published: 22 Jan 2025, Last Modified: 30 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
OGBench: Benchmarking Offline Goal-Conditioned RL
Seohong Park, Kevin Frans, Benjamin Eysenbach, Sergey Levine
- Published: 22 Jan 2025, Last Modified: 13 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Representational Knowledge Distillation Across Wearable Biosignals
Salar Abbaspourazad, Anshuman Mishra, Joseph Futoma, Andrew Miller, Ian Shapiro
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes
Juan Sebastian Rojas, Chi-Guhn Lee
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Optimal Causal Representations and the Causal Information Bottleneck
Francisco N. F. Q. Simoes, Mehdi Dastani, Thijs van Ommen
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation
Eliot Xing, Vernon Luk, Jean Oh
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Scale-Invariant Continuous Implicit Neural Representations For Object Counting
Siyuan Xu, Yucheng Wang, Xihaier Luo, Byung-Jun Yoon, Xiaoning Qian
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
From Attention to Prediction Maps: Per-Class Gradient-Free Transformer Explanations
Ronen Schaffer, Tomer Michaeli, Meir Yossef Levi
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Multiscale Training of Convolutional Neural Networks
Niloufar Zakariaei, Shadab Ahamed, Eldad Haber, Moshe Eliasof
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback
GUOJUN XIONG, Ujwal Dinesha, Debajoy Mukherjee, Jian Li, Srinivas Shakkottai
- Published: 22 Jan 2025, Last Modified: 22 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Weak-to-Strong Jailbreaking on Large Language Models
Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li, Yu-Xiang Wang, William Yang Wang
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone