Mingyu Liu

5

Papers

84

Total Citations

Papers (5)

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation

3D Object Detection with a Self-Supervised Lidar Scene Flow Backbone