2026 05 Icml Accepted

Five papers accepted by ICML 2026. Congratulations to everyone!

• “Hiper: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents”, J. Peng, Y. Liu, R. Zhou, C. Fleming, Z. Wang, A. Garcia, M. Hong. See here
• “A Minimalist Optimizer Design for LLM Pretraining”, A. Glentis, J. Li, A. Han, M. Hong. See here
• “StitchCUDA: An Automated Multi-Agent End-to-End GPU Programming Framework with Rubric-based Agentic Reinforcement Learning”, S. Li, Z. Zhang, W. Chen, Y. Luo, M. Hong, C. Ding. See here
• “Leak@k: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding”, H. Reisizadeh, J. Ruan, Y. Chen, S. Pal, S. Liu, M. Hong. See here
• “GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding”, B. Lei, N. Xu, A. Payani, M. Hong, C. Liao, Y. Cao, C. Ding. See here