ICLR 2025 Conference Submissions

MSR-ViR: Modularized Self-reflected Video Reasoner for Video Question Answering
Zihan Song, Zi Qian, Xin Wang, Hong Chen, Yaofei Wu, Longtao Huang, Hui Xue', Wenwu Zhu
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
RDAS: A Low Latency and High Throughput Raw Data Engine for Machine Learning Systems
Weijian Li, Han Liu
- 28 Sept 2024 (modified: 16 Oct 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone
Adversarial Robustness of Count-Min Sketch
Krzysztof Onak, Dragos-Florian Ristache
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
The Latent Road to Atoms: Backmapping Coarse-grained Protein Structures with Latent Diffusion
Han Xu, Yuancheng SUN, Kai Chen, Kang Liu, Qiwei Ye
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Not Only Vision: Evolve Visual Speech Recognition via Peripheral Information
Zhaoxin Yuan, Shuang Yang, Shiguang Shan, Xilin Chen
- 28 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Plastic Learning with Deep Fourier Features
Alex Lewandowski, Dale Schuurmans, Marlos C. Machado
- Published: 22 Jan 2025, Last Modified: 08 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
MCCE: Missingness-aware Causal Concept Explainer
Jifan Gao, Guanhua Chen
- 28 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Tianlin Li, Weipeng Jiang, Yang Liu
- Published: 22 Jan 2025, Last Modified: 12 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Interpretable Reward Design in Robotics
Letian Chen, Matthew Gombolay
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
A diffusion model on toric varieties with application to protein loop modeling
Xin Cao, Evangelos Coutsias, Ernest Glukhov, Sergei Kotelnikov, Dmytro Kozakov, Thu Nguyen
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DebUnc: Improving Large Language Model Agent Communication Via Uncertainty Metrics
Luke Yoffe, Alfonso Amayuelas, William Yang Wang
- 28 Sept 2024 (modified: 17 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
EDGE OF STOCHASTIC STABILITY: REVISITING THE EDGE OF STABILITY FOR SGD
Arseniy Andreyev, Pierfrancesco Beneventano
- 28 Sept 2024 (modified: 03 Oct 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Time-to-Event Pretraining for 3D Medical Imaging
Zepeng Frazier Huo, Jason Alan Fries, Alejandro Lozano, Jeya Maria Jose Valanarasu, Ethan Steinberg, Louis Blankemeier, Akshay S Chaudhari, Curtis Langlotz, Nigam Shah
- Published: 22 Jan 2025, Last Modified: 19 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
From Static to Dynamic: Leveraging Implicit Behavioral Models to Facilitate Transition in Offline-to-Online Reinforcement Learning
Lipeng Zu, Xiaonan Zhang, Yukun Yuan, Shayok Chakraborty
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
Xiao Yu, Baolin Peng, Vineeth Vajipey, Hao Cheng, Michel Galley, Jianfeng Gao, Zhou Yu
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Learning Generalizable and Well-Shaped Reward Functions from Too Few Demonstrations
Ziyi Liu, Grace Zhang, Gaurav S. Sukhatme
- 28 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Detail Loss in Super-Resolution Models Based on the Laplacian Pyramid and Repeated Upscaling-Downscaling Structure
Sangjun Han, Youngmi Hur
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Using Reinforcement Learning to Investigate Neural Dynamics During Motor Learning
Derek Xiao, Ken-Fu Liang, Keyu Ji, Jonathan Kao
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models
Ziyao Shangguan, Chuhan Li, Yuxuan Ding, Yanan Zheng, Yilun Zhao, Tesca Fitzgerald, Arman Cohan
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers
Shijie Chen, Bernal Jimenez Gutierrez, Yu Su
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Edge Matters: A Predict-and-Search Framework for MILP based on Sinkhorn-Nomalized Edge Attention Networks and Adaptive Regret-Greedy Search
Yufan Deng, Tianle Pu, Li Zeng, Junfeng Kong, Changjun Fan
- 28 Sept 2024 (modified: 21 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
A Systemic Review of Static Memory Analysis
Enoch Solomon
- 28 Sept 2024 (modified: 17 Oct 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone
Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
Christopher Ackerman, Nina Panickssery
- Published: 22 Jan 2025, Last Modified: 14 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Towards Learning High-Precision Least Squares Algorithms with Sequence Models
Jerry Weihong Liu, Jessica Grogan, Owen M Dugan, Ashish Rao, Simran Arora, Atri Rudra, Christopher Re
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction
Baiting Luo, Ava Pettet, Aron Laszka, Abhishek Dubey, Ayan Mukhopadhyay
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone