Hanrong Ye

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing

arXiv 2026

Scaling RL to Long Videos

arXiv 2025

I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

arXiv 2025

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

arXiv 2025

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

arXiv 2025

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

arXiv 2025

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs

arXiv 2024

TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts

ICCV 2023 1

Hongxu Yin

Jan Kautz

Pavlo Molchanov

Song Han

Sifei Liu

Wei Huang

Yukang Chen

Baifeng Shi

Dan Xu

Ligeng Zhu