Zhirui Chen

monte carlo tree search (2) contrastive learning (1) offline reinforcement learning (1) model robustness (1) multimodal learning (1) point cloud (1) feature disentanglement (1) relational reasoning (1) backdoor attack (1) adversarial attack (1) pairwise comparison (1) vision-language model (1) supervised fine-tuning (1) out-of-domain generalization (1) exponential convergence (1) directed acyclic graph (1) rejection sampling (1) instance-dependent bound (1) long-context understanding (1) reasoning path (1)