ICLR 2025 Conference Submissions

Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models
Hyunjin Seo, Taewon Kim, June Yong Yang, Eunho Yang
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Dense Video Object Captioning from Disjoint Supervision
Xingyi Zhou, Anurag Arnab, Chen Sun, Cordelia Schmid
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Faster Cascades via Speculative Decoding
Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Seungyeon Kim, Neha Gupta, Aditya Krishna Menon, Sanjiv Kumar
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference
Amirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi
- Published: 22 Jan 2025, Last Modified: 09 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Adaptive Pruning of Pretrained Transformer via Differential Inclusions
Yizhuo Ding, Ke Fan, Yikai Wang, Xinwei Sun, Yanwei Fu
- Published: 22 Jan 2025, Last Modified: 30 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
CASE-Bench: Context-Aware Safety Evaluation Benchmark for Large Language Models
Guangzhi Sun, Xiao Zhan, Phil Woodland, Jose M. Such
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Pseudo- vs. True-Randomness: Rethinking Distortion-Free Watermarks of Language Models under Watermark Key Collisions
Yihan Wu, Ruibo Chen, Zhengmian Hu, Yanshuo Chen, Junfeng Guo, Hongyang Zhang, Heng Huang
- 25 Sept 2024 (modified: 22 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Kernel Banzhaf: A Fast and Robust Estimator for Banzhaf Values
Yurong Liu, R. Teal Witter, Flip Korn, Tarfah Alrashed, Dimitris Paparas, Juliana Freire
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Markovian Compression: Looking to the Past Helps Accelerate the Future
Andrey Veprikov, Vladimir Solodkin, Mikhail Rudakov, Aleksandr Beznosikov
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Convergence of Distributed Adaptive Optimization with Local Updates
Ziheng Cheng, Margalit Glasgow
- Published: 22 Jan 2025, Last Modified: 12 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
LightSAM: Parameter-Agnostic Sharpness-Aware Minimization
Yifei Cheng, Li Shen, Hao Sun, Nan Yin, Xiaochun Cao, Enhong Chen
- 25 Sept 2024 (modified: 06 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods
Lise Le Boudec, Emmanuel de Bezenac, Louis Serrano, Ramon Daniel Regueiro-Espino, Yuan Yin, Patrick Gallinari
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
USDC: A Dataset of $\underline{U}$ser $\underline{S}$tance and $\underline{D}$ogmatism in Long $\underline{C}$onversations
mounika marreddy, SUBBA REDDY OOTA, Venkata Charan Chinni, Manish Gupta, Lucie Flek
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
Yuchen Liang, Peizhong Ju, Yingbin Liang, Ness Shroff
- Published: 22 Jan 2025, Last Modified: 24 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Towards Interpreting Visual Information Processing in Vision-Language Models
Clement Neo, Luke Ong, Philip Torr, Mor Geva, David Krueger, Fazl Barez
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Mitigating Compositional Issues in Text-to-Image Generative Models via Enhanced Text Embeddings
Arman Zarei, Keivan Rezaei, Samyadeep Basu, Mehrdad Saberi, Mazda Moayeri, Priyatham Kattakinda, Soheil Feizi
- 25 Sept 2024 (modified: 10 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Optimization on Manifolds with Riemannian Jacobian Regularization
Tuan Truong, Hoang-Phi Nguyen, Tung Pham, Mehrtash Harandi, Minh-Tuan Tran, Dinh Phung, Trung Le
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning
Théo Vincent, Fabian Wahren, Jan Peters, Boris Belousov, Carlo D'Eramo
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Exponential-Wrapped Mechanisms for Differential Privacy on Hadamard Manifolds
Yangdi Jiang, Xiaotian Chang, Lei Ding, Linglong Kong, Bei Jiang
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Replacing Implicit Regression with Classification in Policy Gradient Reinforcement Learning
Josiah P. Hanna, Brahma S Pavse, Abhinav Narayan Harish
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Enabling Weak LLMs to Judge Response Reliability via Meta Ranking
Zijun Liu, Boqun Kou, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Enhancing Decision-Making of Large Language Models via Actor-Critic
Heng Dong, Kefei Duan, Chongjie Zhang
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
TGTOD: A Global Temporal Graph Transformer for Outlier Detection at Scale
Kay Liu, Jiahao Ding, MohamadAli Torkamani, Philip S. Yu
- 25 Sept 2024 (modified: 28 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Adversarial Attacks on Data Attribution
Xinhe Wang, Pingbang Hu, Junwei Deng, Jiaqi W. Ma
- Published: 22 Jan 2025, Last Modified: 12 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models
Alireza Ganjdanesh, Reza Shirkavand, Shangqian Gao, Heng Huang
- Published: 22 Jan 2025, Last Modified: 25 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone