ICLR 2025 Conference Submissions

From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
Kaiyue Wen, Huaqing Zhang, Hongzhou Lin, Jingzhao Zhang
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
Xiaoshuai Song, Muxi Diao, Guanting Dong, Zhengyang Wang, Yujia Fu, Runqi Qiao, Zhexu Wang, Dayuan Fu, Huangxuan Wu, Bin Liang, Weihao Zeng, Yejie Wang, Zhuoma GongQue, Jianing Yu, Qiuna Tan, Weiran Xu
- Published: 22 Jan 2025, Last Modified: 19 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Experimental Design for Nonstationary Optimization
Darshan Patil, Pranshu Malviya, Maryam Hashemzadeh, Sarath Chandar
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Optimal Adapter Placement for Efficient Transfer Learning
Aleksandra Nowak, Otniel-Bogdan Mercea, Anurag Arnab, Jonas Pfeiffer, Yann Dauphin, Utku Evci
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Certified Robustness to Clean-label Poisoning Using Diffusion Denoising
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
- 27 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
FLAG: Clustered Federated Learning Combining Data and Gradient Information in Heterogeneous Settings
Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Context is Key: A Benchmark for Forecasting with Essential Textual Information
Andrew Robert Williams, Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Jithendaraa Subramanian, Roland Riachi, James Requeima, Alexandre Lacoste, Irina Rish, Nicolas Chapados, Alexandre Drouin
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Teach Multimodal LLMs to Comprehend Electrocardiographic Images
Ruoqi Liu, yuelin bai, Xiang Yue, Ping Zhang
- 27 Sept 2024 (modified: 28 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Characterizing trainability, expressivity, and generalization of neural architecture with metrics from neural tangent kernel
Xinyu Chen, Jinlong Li, Faiza Amin, Huanhuan Chen, Qiuju Chen
- 27 Sept 2024 (modified: 16 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
The Case for Gradual Structured Pruning in Image-based Deep Reinforcement Learning
Raphael Trumpp, Mirco Theile, Marco Caccamo
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
A deep inverse-mapping model for a flapping robotic wing
Hadar Sharvit, Raz Karl, Tsevi Beatus
- Published: 22 Jan 2025, Last Modified: 13 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective
Xiangru Zhu, Penglei Sun, Yaoxian Song, Yanghua Xiao, Zhixu Li, Chengyu Wang, Jun Huang, Bei Yang, Xiaoxiao Xu
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
DAG-Jailbreak: Enhancing Black-box Jailbreak Attacks and Defenses through DAG Dependency Analysis
Lin Lu, Hai Yan, Zenghui Yuan, Jiawen Shi, Wenqi Wei, Pin-Yu Chen, Pan Zhou
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
CONTINUAL FINITE-SUM MINIMIZATION UNDER THE POLYAK-ŁOJASIEWICZ CONDITION
Ioannis Mavrothalassitis, Stratis Skoulakis, Elias Abad Rocamora, Andrej Janchevski, Volkan Cevher
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Vocabulary-Defined Semantics: Latent Space Clustering for Improving In-Context Learning
Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Reevaluating Theoretical Analysis Methods for Optimization in Deep Learning
Hoang Tran, Qinzi Zhang, Ashok Cutkosky
- 27 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
GraphRouter: A Graph-based Router for LLM Selections
Tao Feng, Yanzhen Shen, Jiaxuan You
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
Jihye Choi, Jayaram Raghuram, Yixuan Li, Somesh Jha
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Offline RL in Regular Decision Processes: Sample Efficiency via Language Metrics
Ahana Deb, Roberto Cipollone, Anders Jonsson, Alessandro Ronca, Mohammad Sadegh Talebi
- Published: 22 Jan 2025, Last Modified: 17 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in Surface Electromyographic Signal Analysis
Weiyu Guo, Ziyue Qiao, Ying Sun, Hui Xiong
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Think while You Generate: Discrete Diffusion with Planned Denoising
Sulin Liu, Juno Nam, Andrew Campbell, Hannes Stark, Yilun Xu, Tommi Jaakkola, Rafael Gomez-Bombarelli
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning
Alec F Diallo, Vaishak Belle, Paul Patras
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Constrained Skill Discovery: Quadruped Locomotion with Unsupervised Reinforcement Learning
Vassil Atanassov, Wanming Yu, Alexander Luis Mitchell, Mark Nicholas Finean, Ioannis Havoutis
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Thought-Retriever: Don’t Just Retrieve Raw Data, Retrieve Thoughts
Tao Feng, Pengrui Han, Guanyu Lin, Ge Liu, Jiaxuan You
- 27 Sept 2024 (modified: 02 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Improve Code Generation with Feedback
Zhi Xu, Yun Fu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone