ICLR 2025 Conference Submissions

An Auditing Test to Detect Behavioral Shift in Language Models
Leo Richter, Xuanli He, Pasquale Minervini, Matt Kusner
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Enhancing Hallucination Detection with Noise Injection
Litian Liu, Reza Pourreza, Sunny Panchal, Apratim Bhattacharyya, Yao Qin, Roland Memisevic
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Blind Unlearning: Unlearning Without a Forget Set
Aviraj Newatia, Michael Cooper, Rahul Krishnan
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Generative modeling of density regression through tree flows
Zhuoqun Wang, Naoki Awaya, Li Ma
- 27 Sept 2024 (modified: 03 Oct 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
All You Need Is A Reference: Cross-modality Referring Segmentation for Abdominal MRI
Sumin Kim, Jun Ma, BO WANG
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Visual Prompting with Iterative Refinement for Design Critique Generation
Peitong Duan, Chin-Yi Cheng, Bjorn Hartmann, Yang Li
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Task Vectors are Cross-Modal
Grace Luo, Trevor Darrell, Amir Bar
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Gradients protection in federated learning for Biometric authentication
YALDA KASRAVI MAVI, Abdelhakim Senhaji Hafid
- 27 Sept 2024 (modified: 20 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Actions Speak Louder Than States: Going Beyond Bayesian Inference in In-Context Reinforcement Learning
Bilgehan Sel, Annie Xie, Jonathan Lee, Ming Jin
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SWGA: A Distributed Hyperparameter Search Method for Time Series Prediction Models
Weijian Li, Haozheng Luo, Chenwei Xu, Han Liu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Customized Procedure Planning in Instructional Videos
Ali Zare, Constantine Tsibouris, Xudong Lin, Li Zhang, Ming-Hsuan Yang, Shih-Fu Chang
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks
Mathis Pink, Vy A. Vo, Qinyuan Wu, Jianing Mu, Javier S. Turek, Uri Hasson, Kenneth A. Norman, Sebastian Michelmann, Alexander Huth, Mariya Toneva
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Radar: Fast Long-Context Decoding for Any Transformer
Yongchang Hao, Mengyao Zhai, Hossein Hajimirsadeghi, Sepidehsadat Hosseini, Frederick Tung
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Bypassing Skip-Gram Negative Sampling: Dimension Regularization as a More Efficient Alternative for Graph Embeddings
David Mingfei Liu, Arjun Seshadri, Tina Eliassi-Rad, Johan Ugander
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Transformers meet Neural Algorithmic Reasoners
Wilfried Bounsi, Borja Ibarz, Andrew Joseph Dudzik, Jessica B Hamrick, Larisa Markeeva, Alex Vitvitskyi, Razvan Pascanu, Petar Veličković
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
NETS: A Non-Equilibrium Transport Sampler
Michael Samuel Albergo, Eric Vanden-Eijnden
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance - A Case Study in Finance
Menachem Brief, Oded Ovadia, Gil Shenderovitz, Noga BenYoash, Rachel Lemberg, Eitam Sheetrit
- 27 Sept 2024 (modified: 03 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Can Knowledge Editing Really Correct Hallucinations?
Baixiang Huang, Canyu Chen, Xiongxiao Xu, Ali Payani, Kai Shu
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
Angelika Romanou, Negar Foroutan, Anna Sotnikova, Sree Harsha Nelaturu, Shivalika Singh, Rishabh Maheshwary, Micol Altomare, Zeming Chen, Mohamed A. Haggag, Snegha A, Alfonso Amayuelas, Azril Hafizi Amirudin, Danylo Boiko, Michael Chang, Jenny Chim, Gal Cohen, Aditya Kumar Dalmia, Abraham Diress, Sharad Duwal, Daniil Dzenhaliou et al. (37 additional authors not shown)
- Published: 22 Jan 2025, Last Modified: 11 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems
Patrick Emami, Zhaonan Li, Saumya Sinha, Truc Nguyen
- Published: 22 Jan 2025, Last Modified: 07 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks
Yinglun Xu, Zhiwei Wang, Gagandeep Singh
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Generative Classifiers Avoid Shortcut Solutions
Alexander Cong Li, Ananya Kumar, Deepak Pathak
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Compute-Constrained Data Selection
Junjie Yin, Alexander M Rush
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
softmax is not enough (for sharp out-of-distribution)
Petar Veličković, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Beyond the Boundaries of Proximal Policy Optimization
Charlie B. Tan, Edan Toledo, Benjamin Ellis, Jakob Nicolaus Foerster, Ferenc Huszár
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone