YongJie Ye

Vision as LoRA

arXiv 2025

SAIL-VL2 Technical Report

arXiv 2025

Elysium: Exploring Object-level Perception in Videos via MLLM

arXiv 2024

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering

arXiv 2024

TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy

arXiv 2024

Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM

arXiv 2024

Can Huang

Han Wang

Yanjie Wang

Jinghui Lu

Jingqun Tang

Yuxiang Nie

Haiyang Yu

Hao Feng

Hao liu

Qi Liu