ICLR 2025 Conference Submissions

Interpolate: How Resetting Active Neurons can also improve Generalizability in Online Learning
Pranshu Malviya, Darshan Patil, Maryam Hashemzadeh, Quentin Fournier, Sarath Chandar
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback
Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
LVM-NET: Efficient Long-Form Video Reasoning using neural sampling
Saket Gurukar, Asim Kadav
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MolMiner: Transformer architecture for fragment-based autoregressive generation of molecular stories
Raul Ortega Ochoa, Tejs Vegge, Jes Frellsen
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Context-Aware Online Recommendation with Bayesian Incentive Compatibility
Yuantong Li, Guang Cheng, Xiaowu Dai
- 27 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Better Instruction-Following Through Minimum Bayes Risk
Ian Wu, Patrick Fernandes, Amanda Bertsch, Seungone Kim, Sina Khoshfetrat Pakazad, Graham Neubig
- Published: 22 Jan 2025, Last Modified: 25 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Rényi Regularised Reinforcement Learning
Edward James Young, Yashar Ahmadian
- 27 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
FLAIR: FEDERATED LEARNING WITH AUGMENTED AND IMPROVED FEATURE REPRESENTATIONS
Sujit Chowdhury, Aritra Bhaduri, Raju Halder
- 27 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Subtle Errors Matter: Preference Learning via Error-injected Self-editing
Kaishuai Xu, Tiezheng YU, Wenjun Hou, Yi Cheng, Chak Tou Leong, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MMD-NSL: Mixed Multinomial Distribution-based Neuro-Symbolic Learning
Pengwei Xing, Songtao Lu, Han Yu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Language Model Merging in Iterative Preference Learning
Chenmien Tan, Simon Yu, Shay B Cohen
- 27 Sept 2024 (modified: 23 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Evaluating the Unseen: A Novel Framework for Assessing Unsupervised Concept Bottleneck Models
Songning Lai, Hongru Xiao, Jiechao Gao, Weitao Xiong, Xin Xu, Wenshuo Chen, Bowen Tian, Andrew Liu, Lijie Hu, Yutao Yue
- 27 Sept 2024 (modified: 22 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
IntGrad MT: Enhancing LLMs' Machine Translation Capabilities with Sentence Interpolation Guided Gradual MT
Seungwoo Choi, Gahyun Yoo, Jay-Yoon Lee
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing
Yang Li
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
A Provably Robust Algorithm for Differentially Private Clustered Federated Learning
Saber Malekmohammadi, Afaf Taik, Golnoosh Farnadi
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
Michael Crawshaw, Mingrui Liu
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
Michael Matthews, Michael Beukman, Chris Lu, Jakob Nicolaus Foerster
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
IS TRANSFORMER A STOCHASTIC PARROT? A CASE STUDY IN SIMPLE ARITHMETIC TASK
WANG PEIXU, Chen Yu, Yu Ming
- 27 Sept 2024 (modified: 23 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Promptus: Representing Real-World Video as Stable Diffusion Prompts for Video Streaming
Jiangkai Wu, Liming Liu, Yunpeng Tan, Junlin Hao, Xinggong ZHANG
- 27 Sept 2024 (modified: 23 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Scaling Transformers for Low-Bitrate High-Quality Speech Coding
Julian D Parker, Anton Smirnov, Jordi Pons, CJ Carr, Zack Zukowski, Zach Evans, Xubo Liu
- Published: 22 Jan 2025, Last Modified: 14 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Riemannian Optimization for Hyperbolic Prototypical Networks
Samuele Fonio, Roberto Esposito, Marco Aldinucci
- 27 Sept 2024 (modified: 19 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PREDICTING 3D STRUCTURE BY LATENT POSTERIOR SAMPLING
Azmi A. Haider, Dan Rosenbaum
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Insight Over Sight? Exploring the Vision-Knowledge Conflicts in Multimodal LLMs
Xiaoyuan Liu, Wenxuan Wang, Youliang Yuan, Jen-tse Huang, Qiuzhi Liu, Pinjia He, Zhaopeng Tu
- 27 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
On Understanding of the Dynamics of Model Capacity in Continual Learning
Supriyo Chakraborty, Krishnan Raghavan
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk, Pavel Kolev, Georg Martius
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone