2026 arXiv Don’t Mask the Environment: Observation Supervision Changes How Agents Explore Under RL Juzheng Zhang, Disha Makhija, Manoj Ghuhan Arivazhagan, Vinayshekhar Bannihatti Kumar, and 1 more author arXiv preprint arXiv:2609.20715, 2026 PAPER Thread Blog Post Learning from Mixed Rollouts: Logit Fusion as a Bridge Between Imitation and Exploration Juzheng Zhang, Abhimanyu Hans, John Kirchenbauer, Micah Goldblum, and 2 more authors Notion Blog Post, 2026 Blog Code Thread 2025 COLM LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation Juzheng Zhang, Jiacheng You, Ashwinee Panda, and Tom Goldstein Conference on Language Modeling, 2025 PAPER Code Model Thread ICML HIGHT: Hierarchical Graph Tokenization for Molecule-Language Alignment Yongqiang Chen, Quanming Yao, Juzheng Zhang, James Cheng, and 1 more author International Conference on Machine Learning, 2025 PAPER Website Dataset 2024 KDD Heuristic Learning with Graph Neural Networks: A Unified Framework for Link Prediction Juzheng Zhang, Lanning Wei, Zhen Xu, and Quanming Yao In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024 PAPER Code arXiv UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation Juzheng Zhang, Yatao Bian, Yongqiang Chen, and Quanming Yao arXiv preprint arXiv:2408.00863, 2024 PAPER Website NeurIPS Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction Haotong Du, Quanming Yao, Juzheng Zhang, Yang Liu, and 1 more author Advances in Neural Information Processing Systems, 2024 PAPER Code