Jia-Qi Yin

VISTA-Policy achieves superior manipulation accuracy by transforming visual feedback into actionable tactile insights, outperforming both vision-only and tactile-only baselines.

QuISE effectively neutralizes typographic attacks on VLMs without any model-specific adjustments, achieving impressive accuracy recovery rates.

Differentiable optimization can supercharge classical ILP solvers, slashing runtime by 10x on combinatorial scheduling problems.