ICLR 2025 Conference Submissions

DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows
Mashrur M. Morshed
- 24 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Sensitivity-Adaptive Augmentation for Robust Segmentation
Laura Yu Zheng, Wenjie Wei, Tony Wu, Jacob Clements, Shreelekha Revankar, Andre Harrison, Yu Shen, Ming Lin
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Rapid Response: Mitigating LLM Jailbreaks With A Few Examples
Alwin Peng, Julian Michael, Henry Sleight, Ethan Perez, Mrinank Sharma
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
HiBO: Hierarchical Bayesian Optimization via Adaptive Search Space Partitioning
Wenxuan Li, Taiyi Wang, Eiko Yoneki
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness
Khyathi Chandu, Linjie Li, Anas Awadalla, Ximing Lu, Jae Sung Park, Jack Hessel, Lijuan Wang, Yejin Choi
- Published: 22 Jan 2025, Last Modified: 08 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
Felipe Maia Polo, Seamus Somerstep, Leshem Choshen, Yuekai Sun, Mikhail Yurochkin
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Learning with Exact Invariances in Polynomial Time
Ashkan Soleymani, Behrooz Tahmasebi, Stefanie Jegelka, Patrick Jaillet
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Few-shot Text Adversarial Attack for Black-box Multi-task Learning
Wenqiang Wang, Hao Lin, Yan XIAO, jiehongli, Xiaochun Cao
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Generative Verifiers: Reward Modeling as Next-Token Prediction
Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, Rishabh Agarwal
- Published: 22 Jan 2025, Last Modified: 20 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
Yiming Liu, Kezhao Liu, Yao Xiao, ZiYi Dong, Xiaogang Xu, Pengxu Wei, Liang Lin
- Published: 22 Jan 2025, Last Modified: 02 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts
Youngseog Chung, Dhruv Malik, Jeff Schneider, Yuanzhi Li, Aarti Singh
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
What Matters for Model Merging at Scale?
Prateek Yadav, Tu Vu, Jonathan Lai, Alexandra Chronopoulou, Manaal Faruqui, Mohit Bansal, Tsendsuren Munkhdalai
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training
Haocheng Xi, Han Cai, Ligeng Zhu, Yao Lu, Kurt Keutzer, Jianfei Chen, Song Han
- Published: 22 Jan 2025, Last Modified: 05 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Higher-Order Graphon Neural Networks: Approximation and Cut Distance
Daniel Herbst, Stefanie Jegelka
- Published: 22 Jan 2025, Last Modified: 18 May 2025
- ICLR 2025 Spotlight
- Readers: Everyone
MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark
Elliot L Epstein, Kaisheng Yao, Jing Li, Xinyi Bai, Hamid Palangi
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Understanding Reasoning in Chain-of-Thought from the Hopfieldian View
Lijie Hu, Liang Liu, Shu Yang, Xin CHEN, Zhen Tan, Muhammad Asif Ali, Mengdi Li, Di Wang
- 24 Sept 2024 (modified: 24 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards General-Purpose Model-Free Reinforcement Learning
Scott Fujimoto, Pierluca D'Oro, Amy Zhang, Yuandong Tian, Michael Rabbat
- Published: 22 Jan 2025, Last Modified: 18 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Deviation Ratings: A general, clone invariant rating method
Luke Marris, Siqi Liu, Ian Gemp, Georgios Piliouras, Marc Lanctot
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On Explaining Equivariant Graph Networks via Improved Relevance Propagation
Hongyi Ling, Haiyang Yu, Zhimeng Jiang, Na Zou, Shuiwang Ji
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Error-quantified Conformal Inference for Time Series
Junxi Wu, Dongjian Hu, Yajie Bao, Shu-Tao Xia, Changliang Zou
- Published: 22 Jan 2025, Last Modified: 01 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Retrieval Or Holistic Understanding? Dolce: Differentiate Our Long Context Evaluation Tasks
Zi Yang
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systems
Deepak Akkil, Ruhana Azam, Tamer Abuelsaad, Prasenjit Dey, Aditya Vempaty, Ashish Jagmohan, Ravi Kokku
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Compressed Decentralized Learning with Error-Feedback under Data Heterogeneity
Xin Yao, Shiqiang Wang, Jake Perazzone, Kevin S Chan, Mingyue Ji
- 24 Sept 2024 (modified: 04 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Multi-Field Adaptive Retrieval
Millicent Li, Tongfei Chen, Benjamin Van Durme, Patrick Xia
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Bayesian Neighborhood Adaptation for Graph Neural Networks
Paribesh Regmi, Rui Li, Kishan K C
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone