ICLR 2025 Conference Submissions

Towards Out-of-Modal Generalization without Instance-level Modal Correspondence
Zhuo Huang, Gang Niu, Bo Han, Masashi Sugiyama, Tongliang Liu
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
A grid world agent with favorable inductive biases
Patrick Hammer, Peter Isaev, Andre N. Costa, Ali Beikmohammadi, Sindri Magnússon
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
IT$^3$: Idempotent Test-Time Training
Nikita Durasov, Assaf Shocher, Doruk Oner, Gal Chechik, Alexei A Efros, Pascal Fua
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Uncertainty Estimation for 3D Object Detection via Evidential Learning
Nikita Durasov, Rafid Mahmood, Jiwoong Choi, Marc T. Law, James Lucas, Pascal Fua, Jose M. Alvarez
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Hybrid Preference Optimization: Augmenting Direct Preference Optimization with Auxiliary Objectives
Anirudhan Badrinath, Prabhat Agarwal, Jiajing Xu
- 24 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
From Unimodal to Multimodal:Scaling up Projectors to Align Modalities
Mayug Maniparambil, Raiymbek Akshulakov, YASSER ABDELAZIZ DAHOU DJILALI, Sanath Narayan, Ankit Singh, Noel O'Connor
- 24 Sept 2024 (modified: 16 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Data Distillation for extrapolative protein design through exact preference optimization
Mostafa Karimi, Sharmi Banerjee, Tommi Jaakkola, Bella Dubrov, Shang Shang, Ron Benson
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
A Realistic Threat Model for Large Language Model Jailbreaks
Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein, Jonas Geiping
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Radial Basis Operator Networks
Jason Kurz, Sean Oughton, Shitao Liu
- 24 Sept 2024 (modified: 27 Feb 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model
Zhiwei Xu, Zhiyu Ni, Yixin Wang, Wei Hu
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Bradley Brown, Jordan Juravsky, Ryan Saul Ehrlich, Ronald Clark, Quoc V Le, Christopher Re, Azalia Mirhoseini
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Zero-shot Outlier Detection via Synthetically Pretrained Transformers: Model Selection Bygone!
Yuchen Shen, Haomin Wen, Leman Akoglu
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
Atoosa Chegini, Hamid Kazemi, Seyed Iman Mirzadeh, Dong Yin, Maxwell Horton, Moin Nabi, Mehrdad Farajtabar, Keivan Alizadeh
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Coordinate In and Value Out: Training Flow Transformers in Ambient Space
Yuyang Wang, Anurag Ranjan, Joshua M. Susskind, Miguel Ángel Bautista
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Do LLMs estimate uncertainty well in instruction-following?
Juyeon Heo, Miao Xiong, Christina Heinze-Deml, Jaya Narain
- Published: 22 Jan 2025, Last Modified: 28 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
TopoDiffusionNet: A Topology-aware Diffusion Model
Saumya Gupta, Dimitris Samaras, Chao Chen
- Published: 22 Jan 2025, Last Modified: 21 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Analyzing the Language of Visual Tokens
David Chan, Rodolfo Corona, Joonyong Park, Cheol Jun Cho, Yutong Bai, Trevor Darrell
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DistillHGNN: A Knowledge Distillation Approach for High-Speed Hypergraph Neural Networks
Saman Forouzandeh, Parham Moradi DW, Mahdi Jalili
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
The Geometry of Attention: Ricci Curvature and Transformers Training and Robustness
Amirhossein Farzam, Oded Schlesinger, Joshua M. Susskind, Juan Matias Di Martino, Guillermo Sapiro
- 24 Sept 2024 (modified: 24 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Learning Transformer-based World Models with Contrastive Predictive Coding
Maxime Burchi, Radu Timofte
- Published: 22 Jan 2025, Last Modified: 15 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Covariate-informed continuous-time gray-box modeling to identify responsiveness of post-surgical pain to opioid therapy
Ran Liu, Rodrigo Gutierrez, Rory Vu Mather, Edward A Bittner, Patrick L. Purdon
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Logical Consistency of Large Language Models in Fact-Checking
Bishwamittra Ghosh, Sarah Hasan, Naheed Anjum Arafat, Arijit Khan
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
GLIMO: Grounding Large Language Models With Imperfect World Models
Haolan Liu, Jishen Zhao
- 24 Sept 2024 (modified: 02 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
An Image is Worth $K$ Slots: Data-efficient Scaling of Self-supervised Visual Pre-training
Xin Wen, Bingchen Zhao, Yilun Chen, Jiangmiao Pang, XIAOJUAN QI
- 24 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
Defu Cao, Wen Ye, Yizhou Zhang, Yan Liu
- 24 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone