Mingyu Liu

NoTVLA: Narrowing of Dense Action Trajectories for Generalizable Robot Manipulation

Learning Primitive Embodied World Models: Towards Scalable Robotic Learning

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

ACTIVE-o3 : Empowering MLLMs with Active Perception via Pure Reinforcement Learning

Bridge Thinking and Acting: Unleashing Physical Potential of VLM with Generalizable Action Expert

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks

PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training

MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences

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

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