Zeyu Zhang

HiVid: LLM-Guided Video Saliency For Content-Aware VOD And Live Streaming

Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding

VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery

MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Motion Generalist: Multimodal Motion Generation

AnyDepth: Depth Estimation Made Easy

UniVid: The Open-Source Unified Video Model

SafeMo: Trustworthy Motion Generation

BlockVid: Block Diffusion for High-Fidelity and Coherent Minute-Long Video Generation

Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning

BagelScore: Visual-Language Evaluation Made Easy

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning

Efficient Learning with Sine-Activated Low-Rank Matrices

FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation