Lei He

SALI-FP is introduced, an evidence-gated multimodal pipeline that converts a plan into reviewable semantic maps, objects, vectors, and relation records while constraining local revisions by image evidence.

A judge's benchmark accuracy can significantly overstate its true evaluative competence, revealing critical insights for optimizing skill evaluation in AI systems.

Achieving 86% accuracy in automated symbol generation could revolutionize PCB design by drastically reducing manual errors and time investment.

Synthesizing novel views from extrapolated poses no longer requires dense supervision, thanks to a geometry-conditioned diffusion model that explicitly learns to handle out-of-trajectory artifacts.

Autonomous vehicles can now better avoid collisions by focusing on the riskiest actors in traffic, rather than treating all agents equally.