Tong Wu

GPT-Policy is introduced, a general-agent framework for in-context robot learning that integrates a context compiler that preserves task-relevant visual transitions, a VLM that proposes robot-tool actions, and a constrained controller that verifies and executes each action and reports its outcome.

Injecting explicit Plücker-ray geometry and local feature sampling into foundation vision backbones drives egocentric 3D hand-object interaction error down to sub-3cm precision.

Chinese model guardrails target coordination rather than ideology—declining even to organize pro-government rallies—yet their sky-high refusal rates collapse under basic adversarial paraphrasing.

Hierarchical planning with vision-language models and decoupled arm-hand control unlocks dexterous grasping in cluttered, tiered workspaces where traditional methods falter.