Zhenyang Li

6

Papers

8

Total Citations

Papers (6)

Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization

Toward Material-Agnostic System Identification from Videos

Enhanced Velocity Field Modeling for Gaussian Video Reconstruction

Tracking by Natural Language Specification

Actor and Action Video Segmentation From a Sentence

Alignment-guided Temporal Attention for Video Action Recognition