Peiyan Li

Current action-conditioned world models are limited by their reliance on visual patterns, failing to generalize physical dynamics across different robot embodiments.

Memory-augmented manipulation models can now achieve state-of-the-art performance while remaining data-efficient and generalizable across diverse tasks and environments.

A simple logistic regression can match the performance of advanced models in evaluating emotion descriptions, raising questions about the validity of current multimodal benchmarks.

Achieving a 57.6% success rate on RoboCasa365, Xiaomi-Robotics-1 sets a new standard for vision-language-action models in real-world robotic manipulation.

FlowWAM achieves a remarkable 92.94% success rate in manipulation tasks by harnessing optical flow as a video-native action representation.

E-TTS achieves up to a 33.14% performance boost in robotic manipulation by leveraging historical context and iterative refinement, redefining how we approach test-time scaling.

Structured supervision can boost VLA model performance by over 50% in complex robotic tasks, transforming how we approach fine-tuning in manipulation.

Achieve real-time robotic action with 79-91% success while generating high-fidelity 4D reconstructions, all within a single unified world model.