Fei-Fei Li

Visual tracks can double the success rates of robot tasks by providing a powerful interface between control and visual prediction.

Misleading historical data can corrupt over 30% of tool-calling decisions, but a new method can restore accuracy by effectively transferring reliable policies from teacher to student models.

Unifying motion and camera controls in a single visual representation leads to unprecedented improvements in video generation fidelity and robustness.

Jointly optimizing knowledge construction and querying leads to a 6.3-point boost in answer correctness, revolutionizing how agents interact with their knowledge bases.

Revealing robot motion in video models can transform how we predict and control robotic actions, achieving high fidelity with minimal training data.

Scaling visuomotor context to 8K timesteps enables robots to master complex tasks and adapt in real-time, outperforming previous models by a staggering margin.

Transforming video generation from a pixel sampling problem to a structured orchestration of the physical world, WNM enables unprecedented control and efficiency in content creation.

Tactile-reactive policies can boost robotic manipulation success rates by over 30% through innovative data collection and a new Mixture-of-Transformers architecture.

Robots can now learn to reproduce oil paintings with impressive accuracy through self-play and model-based planning, even without human demonstrations or high-fidelity simulators.