Publications and preprints
Selected papers, sorted by recency. * denotes equal contribution. Full list on Google Scholar.
MMPact: Autonomous Multimodal Context Compaction for LLM Agents
Feng Luo, Yang Zhang, Yujian Liu, Shiyu Chang, Mayank Darbari, Liangjie Hong, Liang Wu
Under review
Autonomous context compaction for multimodal LLM agents.
Game2Player: Scaling Gameplay Experience for Visual Agents through Environment–Player Co-DevelopmentXirui Jiang*, Yuxi Chen*, Rui Yang*,
Feng Luo*, Pengcheng Wang, Bingxuan Li, Zihao Zhao, Yushan Li, Han Wang, Manling Li, et al.
PreprintCode / Project PageScaling visual-agent gameplay through environment–player co-development. Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language ModelsFeng Luo, Yu-Neng Chuang, Guanchu Wang, Zicheng Xu, Xiaotian Han, Tianyi Zhang, Vladimir Braverman
Conference on Language Modeling (COLM), 2026PaperUnderstanding length inflation in on-policy distillation and stabilizing training with StableOPD. AutoL2S: Auto Long-Short Reasoning for Efficient Large Language ModelsFeng Luo*, Yu-Neng Chuang*, Guanchu Wang, Hoang Anh Duy Le, Shaochen Zhong, Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, Xia Hu
Findings of the Association for Computational Linguistics (ACL), 2026Paper / CodeLearning when to use long or short reasoning to improve the efficiency of large language models. MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference LearningJingyan Shen, Jiarui Yao, Rui Yang, Yifan Sun,
Feng Luo, Rui Pan, Tong Zhang, Han Zhao
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025 · Outstanding Paper AwardPaper / CodeMixture-based preference modeling with context-aware routing for personalized alignment. Rethinking Diverse Human Preference Learning through Principal Component AnalysisFeng Luo*, Rui Yang*, Hao Sun, Chunyuan Deng, Jiarui Yao, Jingyan Shen, Huan Zhang, Hanjie Chen
Findings of the Association for Computational Linguistics (ACL), 2025Paper / CodeDecomposed reward models uncover interpretable preference dimensions from binary comparisons. Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference AdjustmentRui Yang*, Xiaoman Pan*,
Feng Luo*, Shuang Qiu*, Han Zhong, Dong Yu, Jianshu Chen
International Conference on Machine Learning (ICML), 2024Paper / CodeMulti-objective foundation-model alignment with dynamically adjustable preferences. 