Publication MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction Jung Min Lee, Dohyeok Lee, Seokhun Ju, Taehyun Cho, Jin Woo Koo, Li Zhao, Sangwoo Hong, Jungwoo Lee ICML 2026 | May 2026
Publication DEPART: DEcomposing PARiTy across Multilingual LLMs Manan Uppadhyay, Prashant Kodali, Pranjal A. Chitale, Reshma Ramaprasad, Himanshu Beniwal, Sunayana Sitaram May 2026 arXiv | May 2026 Project
Publication Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models Hayden S. Helm, Xiaodong Liu, Weiwei Yang May 2026 arXiv | May 2026
Publication Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Zeyi Huang, Xuehai He, Liliang Ren, Yiping Wang, Baolin Peng, Hao Cheng, Shuohang Wang, Pengcheng He, Jianfeng Gao, Yong Jae Lee, Yelong Shen May 2026 arXiv | May 2026
Publication IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference Xintong Yang, Hao Gu, Bin Xu, Lujun Li, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Sirui Han, Yike Guo May 2026 arXiv | May 2026
Publication Explaining Too Much? Understanding How Large Language Model Reasoning Traces Influence Performance and Metacognition Daniela Fernandes, Daniel Buschek, Lev Tankelevitch, Thomas Kosch, Robin Welsch May 2026 arXiv | May 2026
Publication AI-Assisted Systematization for Evaluating GenAI Systems Dhruv Agarwal, Emily Sheng, Chad Atalla, Jean Garcia-Gathright, Hussein Mozannar, Hannah Washington, Alexandra Chouldechova, Solon Barocas, Hanna Wallach May 2026 arXiv | May 2026
Publication Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents Donghyun Kim, Reuben Tan, Donghyun Kim ICML 2026 | May 2026
Publication Can Social Networks Substitute for Reputation Systems? Evidence from a Large Scale Field Experiment David Holtz, Alex Dow, Sinan Aral AAAI Conference on Web and Social Media | May 2026
Publication Proact-VL: A Proactive VideoLLM for Real-Time AI Companions Weicai Yan, Yuhong Dai, Qimu Ran, Haodong Li, Wang Lin, Haodong Liao, Xing Xie, Tao Jin, Jianxun Lian ICML 2026 | May 2026