Zhang, Yiming
39 publications
ICLR
2026
OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
NeurIPS
2025
InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion
NeurIPS
2025
Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
NeurIPSW
2022
Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance