Wenming Yang

OmniCVR: A Benchmark for Omni-Composed Video Retrieval with Vision, Audio, and Text

RAR: Reversing Visual Attention Re-Sinking for Unlocking Potential in Multimodal Large Language Models

Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy

ICDiffAD: Implicit Conditioning Diffusion Model for Time Series Anomaly Detection

TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs

Flowing with Precision: Rectified Flow Image Editing with Trajectory and Frequency Guidance

GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning

ConsisSR: Delving Deep into Consistency in Diffusion-based Image Super-Resolution

BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network