Hai-Quan Wang

RepoAtlas is a training-free module that maintains evolving multimodal repository views through a select--project--refresh loop over a repository code graph, which combines evidence from the issue with the agent's current exploration state to select a task-relevant region under a fixed budget, projects the selected structure into complementary visual and textual representations, and refreshes the view when changes in the exploration state render it outdated.

Iapetus achieves a remarkable 91.6% task completion rate while slashing mean latency and battery draw by over 50% in satellite-based ViT inference.

Native computer use can be achieved at scale, enabling agents to outperform leading systems while significantly enhancing security against adversarial attacks.

Forget hand-crafted benchmarks: CUA-Gym's auto-generated training data lets computer-use agents crush existing open-source models on real-world tasks.

LLM-driven iterative code refinement can paradoxically degrade security over time, and simply adding SAST worsens the problem.