Yiming Wang

6 papers Shanghai Jiao Tong University

• ConViS-Bench: Estimating Video Similarity Through Semantic Concepts
• Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting
• Learning from Disjoint Views: A Contrastive Prototype Matching Network for Fully Incomplete Multi-View Clustering
• PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts
• Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
• Training-free Online Video Step Grounding