Senqiao Yang

8

Papers

72

Total Citations

Papers (8)

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction

Unified Language-driven Zero-shot Domain Adaptation

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

VisionZip: Longer is Better but Not Necessary in Vision Language Models

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation

LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding

Mitigating Object Hallucinations via Sentence-Level Early Intervention

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition