Wenbo Li

Even state-of-the-art streaming VLMs miss crucial fast-paced events in real-world video, scoring below 51% on a new high-dynamic benchmark.

Robots can adapt to unseen tasks purely through simulated imagination, boosting real-world manipulation success from 20% to 77% without requiring new human demonstrations or external environment rollouts.

Robot policies can now test and refine manipulation plans entirely within a learned visual simulator across ten distinct embodiments, gaining up to 21.4 percentage points in task success without any target-domain fine-tuning.

This work introduces LIFD (Look, Imagine, Focus, and Do), a framework for persistent, 3D-aware scene memory that learns a scene-token representation from multi-view agreement and completes it from a single RGB view and recurrent memory.