Jiming Chen

TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection

MIMIC: Mask-Injected Manipulation Video Generation with Interaction Control

DiffPBR: Point-Based Rendering via Spatial-Aware Residual Diffusion

VELR: Efficient Video Reward Feedback via Ensemble Latent Reward Models

Learning Multi-granularity Visual-textual Alignment for Zero-shot Anomaly Detection

RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching

FairDD: Fair Dataset Distillation

FairDD: Fair Dataset Distillation via Adversarial Matching

VTDexManip: A Dataset and Benchmark for Visual-tactile Pretraining and Dexterous Manipulation with Reinforcement Learning