ICLR 2025 Conference Submissions

Towards Off-Road Autonomous Driving via Planner Guided Policy Optimization
Vedant Mundheda, Zhouchonghao Wu, Jeff Schneider
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Recurrent Action Transformer with Memory
Egor Cherepanov, Aleksei Staroverov, Dmitry Yudin, Alexey Kovalev, Aleksandr Panov
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
Simran Kaur, Simon Park, Anirudh Goyal, Sanjeev Arora
- Published: 22 Jan 2025, Last Modified: 14 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
On the Limitation and Redundancy of Transformers: A Rank Perspective
Zeping Min, Zhong Li
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
PEDVLM: PEDESTRIAN VISION LANGUAGE MODEL FOR INTENTIONS PREDICTION
Farzeen Munir, Shoaib Azam, Tsvetomila Mihaylova, Ville Kyrki, Tomasz Piotr Kucner
- 27 Sept 2024 (modified: 29 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Improving Inverse Folding for Peptide Design with Diversity-Regularized Direct Preference Optimization
Ryan Park, Darren J. Hsu, Chen Tessler, Maria Korshunova, C. Brian Roland, Olivia Viessmann, Bruno Trentini
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Multimodal Structure Preservation Learning
Chang Liu, Jieshi Chen, Lee H Harrison, Artur Dubrawski
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Building Generalist Robot Policy from Pre-trained Visual Representations
Yunshi Wen, Zhengye Yang, Richard Radke, Anak Agung Julius
- 27 Sept 2024 (modified: 26 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
On Learning Representations for Tabular Dataset Distillation
Inwon Kang, Parikshit Ram, Yi Zhou, Horst Samulowitz, Oshani Seneviratne
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS
Malyaban Bal, Abhronil Sengupta
- Published: 22 Jan 2025, Last Modified: 16 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Speeding Up Image Classifiers with Little Companions
Yang Liu, Kowshik Thopalli, Jayaraman J. Thiagarajan
- 27 Sept 2024 (modified: 01 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
A Kernel Perspective on Training-Free Few-Shot Adaptation of Large Vision-Language Models
Yassir Bendou, Amine Ouasfi, Vincent Gripon, Adnane Boukhayma
- 27 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Better autoregressive regression with LLMs via regression-aware fine-tuning
Michal Lukasik, Zhao Meng, Harikrishna Narasimhan, Yin-Wen Chang, Aditya Krishna Menon, Felix Yu, Sanjiv Kumar
- Published: 22 Jan 2025, Last Modified: 15 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Aligning Multimodal Models for Clinical Reasoning using Rule-based Rewards
Shenghuan Sun, Alexander Marcel Schubert, Gregory M. Goldgof, Zhiqing Sun, Wei Day, Thomas Hartvigsen, Atul J. Butte, Ahmed Alaa
- 27 Sept 2024 (modified: 23 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
100 instances is all you need: predicting LLM success by testing on a few instances
Lorenzo Pacchiardi, Lucy G Cheke, Jose Hernandez-Orallo
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
Spencer Frei, Gal Vardi
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
ReferPix2Pix: Guiding Multi-Modal LLMs for Image Editing with Referential Pixel Grounding
Xiaoqian Shen, Mohamed Elhoseiny
- 27 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Bayesian Learning of Adaptive Koopman Operator with Application to Robust Motion Planning for Autonomous Trucks
Mahmoud Selim, Sriharsha Bhat, Karl Henrik Johansson
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs
Oskar van der Wal, Pietro Lesci, Max Müller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem Zuidema, Stella Biderman
- Published: 22 Jan 2025, Last Modified: 17 May 2025
- ICLR 2025 Poster
- Readers: Everyone
FoundationForensics: Traceback Backdoor Attacks for Vision Foundation Models
Hongbin Liu, Zedian Shao, Yuqi Jia, Jinghuai Zhang, Minghong Fang, Cheng Hong, Neil Zhenqiang Gong
- 27 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra
Roman Worschech, Bernd Rosenow
- Published: 22 Jan 2025, Last Modified: 16 May 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?
HyoJung Han, Akiko Eriguchi, Haoran Xu, Hieu Hoang, Marine Carpuat, Huda Khayrallah
- Published: 22 Jan 2025, Last Modified: 19 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Model Collapse in the Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling
Youngseok Yoon, Dainong Hu, Iain Weissburg, Yao Qin, Haewon Jeong
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SSPictR: Spatial Semantic Pointer Picture Representation
Anna Penzkofer, Karim Habashy, Abhishek Tyagi, Yuhao Zhu, Chris Eliasmith, Andreas Bulling
- 27 Sept 2024 (modified: 03 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Revisiting the Superficial Alignment Hypothesis
Mohit Raghavendra, Vaskar Nath, Sean M. Hendryx
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone