ICLR 2025 Conference Submissions

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
Hai Huang, Randall Balestriero
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Learning Efficient Positional Encodings with Graph Neural Networks
Charilaos Kanatsoulis, Evelyn Choi, Stefanie Jegelka, Jure Leskovec, Alejandro Ribeiro
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Enhancing Cooperative Problem-Solving in Sparse-Reward Systems via Co-evolutionary Curriculum Learning
Kangsheng Wang, Shuyan Liu, Canran Xiao
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Inductive Linguistic Reasoning with Large Language Models
Raghav Ramji, Keshav Ramji
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Deployment Efficient Reward-Free Exploration with Linear Function Approximation
Zihan Zhang, Lin Yang, Yuxin Chen, Jason D. Lee, Simon Shaolei Du, Ruosong Wang
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
How Transformers Solve Propositional Logic Problems: A Mechanistic Analysis
Guan Zhe Hong, Nishanth Dikkala, Enming Luo, Cyrus Rashtchian, Xin Wang, Rina Panigrahy
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
Heyang Zhao, Chenlu Ye, Quanquan Gu, Tong Zhang
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Understanding Gradient Descent through the Training Jacobian
Nora Belrose, Adam Scherlis
- 28 Sept 2024 (modified: 21 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Conditional density estimation for video prediction with score-based models
Pierre-Étienne H Fiquet
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Systematic Review of Large Language Models: Applications, Limitations, Practical Usages and Future Directions
Enoch Solomon, Abraham Woubie Zewoudie
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On the Cost-Effectiveness of Partially-Annotating Methods for Multi-Label Learning
Ming-Kun Xie, Ji-Long Niu, Jia-Hao Xiao, Gang Niu, Masashi Sugiyama, Sheng-Jun Huang
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SAFE: Spiking Neural Network-based Audio Fidelity Evaluation
Aaditya Arunkumar Khant, Raveen Wijewickrama, Murtuza Jadliwala
- 28 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
All-in-One: Prompt-Driven Mixture of Hallucination-Aware Experts for Universal Anomaly Detection Across Multi-Modal Multi-Organ Medical Images
Chunlei Li, Yilei Shi, Jingliang Hu, Xiao Xiang Zhu, Lichao Mou
- 28 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data
Haoyan Yang, Ting Hua, Shangqian Gao, Binfeng Xu, Zheng Tang, Jie Xu, Hongxia Jin, Vijay Srinivasan
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards a Knowledge guided Multimodal Foundation Model for Spatio-Temporal Remote Sensing Applications
Praveen Ravirathinam, Ankush Khandelwal, Rahul Ghosh, Vipin Kumar
- 28 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection
Chunlei Li, Yilei Shi, Jingliang Hu, Xiao Xiang Zhu, Lichao Mou
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Local-Global Shortest Path Algorithms on Random Graphs, Enhanced with GNNs
My Le, Luana Ruiz, Souvik Dhara
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Scalable Influence and Fact Tracing for Large Language Model Pretraining
Tyler A. Chang, Dheeraj Rajagopal, Tolga Bolukbasi, Lucas Dixon, Ian Tenney
- Published: 22 Jan 2025, Last Modified: 21 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption
Joonsung Jeon, Woo Jae Kim, Suhyeon Ha, Sooel Son, Sung-eui Yoon
- Published: 22 Jan 2025, Last Modified: 13 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Temporal-Aware Test-Time Training via Self-Distillation for One-Shot Image-to-Video Segmentation
Zixuan Zheng, Yilei Shi, Jingliang Hu, Xiao Xiang Zhu, Lichao Mou
- 28 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement
Kotaro Yoshida, Yuji Naraki, Takafumi Horie, Ryosuke Yamaki, Ryotaro Shimizu, Yuki Saito, Julian McAuley, Hiroki Naganuma
- Published: 22 Jan 2025, Last Modified: 21 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Generating CAD Code with Vision-Language Models for 3D Designs
Kamel Alrashedy, Pradyumna Tambwekar, Zulfiqar Haider Zaidi, Megan Langwasser, Wei Xu, Matthew Gombolay
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
A Formal Framework for Understanding Length Generalization in Transformers
Xinting Huang, Andy Yang, Satwik Bhattamishra, Yash Sarrof, Andreas Krebs, Hattie Zhou, Preetum Nakkiran, Michael Hahn
- Published: 22 Jan 2025, Last Modified: 30 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Instruction Following is not all you need: Rethinking LLM Generation's Evaluation
Yijie Hao, Haofei Yu, Jiaxuan You
- 28 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Testing the Limits of Jailbreaking with the Purple Problem
Taeyoun Kim, Suhas Kotha, Aditi Raghunathan
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone