ICLR 2025 Conference Submissions

Unveiling Concept Attribution in Diffusion Models
Nguyen Hung-Quang, Hoang Phan, Khoa D Doan
- 28 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition
Aliyah R. Hsu, Georgia Zhou, Yeshwanth Cherapanamjeri, Yaxuan Huang, Anobel Odisho, Peter R. Carroll, Bin Yu
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Towards an Understanding of Graph Sequence Models
Ali Behrouz, Ali Parviz, Mahdi Karami, Clayton Sanford, Bryan Perozzi, Vahab Mirrokni
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
LLF-Bench: A Benchmark for Interactive Learning from Language Feedback
Ching-An Cheng, Andrey Kolobov, Dipendra Misra, Allen Nie, Adith Swaminathan
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
How to Evaluate Reward Models for RLHF
Evan Frick, Tianle Li, Connor Chen, Wei-Lin Chiang, Anastasios Nikolas Angelopoulos, Jiantao Jiao, Banghua Zhu, Joseph E. Gonzalez, Ion Stoica
- Published: 22 Jan 2025, Last Modified: 07 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
On the Surprising Efficacy of Online Self-Improvement for Embodied Multimodal Foundation Models
Seyed Kamyar Seyed Ghasemipour, Ayzaan Wahid, Jonathan Tompson, Pannag R Sanketi, Igor Mordatch
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
An Efficient Framework for Crediting Data Contributors of Diffusion Models
MingYu Lu, Chris Lin, Chanwoo Kim, Su-In Lee
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Weakly-supervised & Uncertainty-aware 3D Gaze Estimation with Geometry-guided Constraints
Chenyi Kuang, Jeffrey O. Kephart, Qiang Ji
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Decentralized Finite-Sum Optimization over Time-Varying Networks
Dmitry Metelev, Savelii Chezhegov, Alexander Rogozin, Aleksandr Beznosikov, Alexander Sholokhov, Alexander Gasnikov, Dmitry Kovalev
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Decentralized Optimization with Coupled Constraints
Demyan Yarmoshik, Alexander Rogozin, Nikita Kiselev, Daniil Dorin, Alexander Gasnikov, Dmitry Kovalev
- Published: 22 Jan 2025, Last Modified: 30 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
DenseAttention: No-Compromise Exact All $N \times N$ Interactions Algorithm with $O(N)$ Space and Time Complexity
Andrew Argatkiny
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Why Not Transform Chat Large Language Models to Non-English?
Xiang Geng, Ming Zhu, Jiahuan Li, Zhejian Lai, Wei Zou, Shuaijie She, Jiaxin GUO, Xiaofeng Zhao, Yinglu Li, Yuang Li, Chang Su, Yanqing Zhao, Xinglin Lyu, Min Zhang, Jiajun Chen, Hao Yang, Shujian Huang
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data
Tahir Javed, Kaushal Santosh Bhogale, Mitesh M Khapra
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
FreDF: Learning to Forecast in the Frequency Domain
Hao Wang, Lichen Pan, Yuan Shen, Zhichao Chen, Degui Yang, Yifei Yang, Sen Zhang, Xinggao Liu, Haoxuan Li, Dacheng Tao
- Published: 22 Jan 2025, Last Modified: 02 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Large Language Models are Demonstration Pre-Selectors for Themselves
Jiarui Jin, Yuwei Wu, Xiaoting He, Haoxuan Li, Weinan Zhang, Yiming Yang, Yong Yu, Jun Wang, Mengyue Yang
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
PromptWizard: Task-Aware Prompt Optimization Framework
Eshaan Agarwal, Joykirat Singh, Vivek Dani, Raghav Magazine, Tanuja Ganu, Akshay Nambi
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
From Scaling Law to Sub-Scaling Law: Understanding the Diminishing Returns of Larger Models
Zhengyu Chen, Siqi Wang, Teng Xiao, Yudong Wang, Shiqi Chen, Xunliang Cai, Junxian He, Jingang Wang
- 28 Sept 2024 (modified: 18 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Jintao Zhang, Jia wei, Pengle Zhang, Jun Zhu, Jianfei Chen
- Published: 22 Jan 2025, Last Modified: 30 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Foundation Models for Boolean Logic
Chris Cameron, Xing Jin, Taylor Lundy, Jason Hartford, Kevin Leyton-Brown
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Active Causal Learning for Conditional Average Treatment Effect Estimation
Pu Yang, Haoxuan Li, Xinqin Feng, Haotian Wang, Xu Chen, Jun Wang, Mengyue Yang
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
Xiabin Zhou, Wenbin Wang, Minyan Zeng, Jiaxian Guo, Xuebo Liu, Li Shen, Min Zhang, Liang Ding
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation
Farima Fatahi Bayat, Lechen Zhang, Sheza Munir, Lu Wang
- 28 Sept 2024 (modified: 16 Feb 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Efficient Adaptive Filtering for Deformable Image registration
Renjiu Hu, Xiang Chen, Jiacheng Wang, Gaolei Li, Noel C Codella, Hang Zhang
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning
Joykirat Singh, Akshay Nambi, Vibhav Vineet
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone