Che Liu

SR-OPSD redefines the optimization landscape by stabilizing the distillation process, leading to superior performance in complex reasoning tasks.

Task-conditioned foveated perception can drastically enhance the robustness and efficiency of robotic foundation models by aligning policy learning with relevant visual evidence.

Generators can dramatically improve their performance on long-tailed visual requests by leveraging a teach-then-search co-training approach, overcoming a critical knowledge boundary.

UniBrain achieves remarkable performance in brain MRI analysis, even when faced with significant data incompleteness, revolutionizing how we approach medical imaging challenges.