Yizeng Han

7

Papers

190

Total Citations

Papers (7)

GSVA: Generalized Segmentation via Multimodal Large Language Models

Dynamic Diffusion Transformer

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection

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

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs

Mask Grounding for Referring Image Segmentation

SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning