Yi-Fan Hou

MLPs can achieve higher accuracy than their training quantum chemistry methods by learning to generalize across computational approaches, not just chemical spaces.

Multimodal models master chart semantics with near-perfect accuracy, yet fundamentally collapse when reasoning about 2.5D visual occlusions—dropping to 61% on layer ordering while generative editors fail under visibility constraints with mIoUs as low as 0.37%.

Visual summaries from KnowVis not only clarify complex concepts but also boost student retention and understanding, outperforming traditional video summarization techniques.

Adapting pretrained policies with just a modest multisensory dataset can enhance robot manipulation performance across diverse tasks without sacrificing prior knowledge.