News
ICLR 2026 Accepted Papers
This year marks the fourteenth annual International Conference on Learning Representations (ICLR). “ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.” This year’s conference took place from April 23rd to 27th at the Riocentro Convention and Event Center in Rio de Janeiro, Brazil. This year CAIDA had sixteen members with papers accepted for ICLR. A big congratulations to our members and their teams for their success! You can see the CAIDA papers below, and the remainder of ICLR’s selections here.
Main Conference Papers:
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
Jenny Zhang, Shengran Hu, Cong Lu, Robert Lange, Jeff Clune
DRBench: A Realistic Benchmark for Enterprise Deep Research
Amirhossein Abaskohi, Tianyi Chen, Miguel Muñoz-Mármol, Curtis Fox, Amrutha Varshini Ramesh, Etienne Marcotte, Xing Han Lù, Nicolas Chapados, Spandana Gella, Peter West, Giuseppe Carenini, Christopher Pal, Alexandre Drouin, Issam H. Laradji
Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection
Siyuan Chen, Minghao Guo, Caoliwen Wang, Anka He Chen, Yikun Zhang, Jingjing Chai, Yin Yang, Wojciech Matusik, Peter Yichen Chen
Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation
Mingyu Kim, Young-Heon Kim, Mi Jung Park
*Oral presentation
SPIKE-RL: Video-LLMs meet Bayesian Surprise
Sahithya Ravi, Aditya Chinchure, Raymond Ng, Leonid Sigal, Vered Shwartz
SysMoBench: Evaluating AI on Formally Specifying Complex Real-World Systems
Qian Cheng, Ruize Tang, Emilie Ma, Finn Hackett, Peiyang He, Yiming Su, Ivan Beschastnikh, Yu Huang, Xiaoxing Ma, Tianyin Xu
Thicker and Quicker: The Jumbo Token for Fast Plain Vision Transformers
Anthony Fuller, Yousef Yassin, Daniel Kyrollos, Evan Shelhamer, James Green
To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
Jiayun Luo, Wan-Cyuan Fan, Lyuyang Wang, Xiangteng He, Tanzila Rahman, Purang Abolmaesumi, Leonid Sigal
Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
Wenlong Deng, Yi Ren, Yushu Li, Boying Gong, Danica Sutherland, Xiaoxiao Li, Christos Thrampoulidis
Accepted papers in various ICLR workshops:
Bridging Generative and Predictive Paradigms via Hidden-Self-Distillation
Scott C. Lowe, Anthony Fuller, Sageev Oore, Evan Shelhamer, Graham W. Taylor
Multimodal Intelligence: Next Token Prediction & Beyond Workshop
Caravan: Asynchronous Test-Time Adaptation for Faster Inference
Jiayin Kralik, Ethan Zhao, Anrui Liu, Reto Achermann, Ivan Beschastnikh, Evan Shelhamer
Test-Time Updates Workshop (TTU)
Changing Modalities by Cross-Band Transfer, Addition, and Peeking
Tim G. Zhou, Anthony Fuller, Geoff Pleiss, Evan Shelhamer
Machine Learning for Remote Sensing Workshop (ML4RS)
Discrete Meanflow Training Curriculum
Chia-Hong HSU, Frank Wood
Deep Generative Model in Machine Learning: Theory, Principle and Efficacy Workshop (DeLTa)
Hidden-Layer Self-Distillation Yields Drift-Resilient Visual Representations
Scott C. Lowe, Anthony Fuller, Sageev Oore, Graham W. Taylor, Evan Shelhamer
Catch, Adapt, and Operate: Monitoring ML Models Under Drift Workshop (CAO)
Learning to Continually Learn via Meta-learning Agentic Memory Designs
Yiming Xiong, Shengran Hu, Jeff Clune
AI with Recursive Self-Improvement Workshop (RSI) & Memory for LLM-Based Agentic Systems Workshop
LookSharp: Attention Entropy Minimization for Test-Time Adaptation
Yash Mali, Evan Shelhamer
Catch, Adapt, and Operate: Monitoring ML Models Under Drift Workshop (CAO) &
Test-Time Updates Workshop (TTU)
ProtoTTA: Prototype-Guided Test-Time Adaptation
Mohammad Mahdi Abootorabi, Parvin Mousavi, Purang Abolmaesumi, Evan Shelhamer
Test-Time Updates Workshop (TTU)
Self-Soupervision: Cooking and Seasoning Model Soups without Labels for Adaptation
Anthony Fuller, James R Green, Evan Shelhamer
Test-Time Updates Workshop (TTU)
Value Drifts: Tracing Value Alignment During LLM Post-Training
Mehar Bhatia, Shravan Nayak, Gaurav Kamath, Marius Mosbach, Karolina Stanczak, Vered Shwartz, Siva Reddy
Catch, Adapt, and Operate: Monitoring ML Models Under Drift Workshop (CAO)
When is Model Souping Tasty? Similarity, Transitivity, and Robustness
Pierre Mackenzie, Simon Ghyselincks, Evan Shelhamer
Test-Time Updates Workshop (TTU)