Bo Li

Today's visual generation models are often evaluated on the wrong things, leading to inflated performance claims that mask critical failures in spatial reasoning, temporal consistency, and causal understanding.

LLMs can orchestrate existing static analysis tools to achieve state-of-the-art Android malware detection at a fraction of the cost, without any domain-specific fine-tuning.

Forget dialogue summaries – FileGram builds user profiles directly from atomic file-system actions, unlocking a richer, more privacy-preserving approach to agent personalization.