Yang Deng

By isolating translational optical flow and leveraging an uncertainty mask, this method nearly doubles the flight speed of autonomous UAVs in complex environments.

The fragmented field of world modeling can now be unified under a "levels x laws" taxonomy, revealing critical gaps in autonomous model revision and decision-centric evaluation.

LLMs have consistent, situation-dependent personality "neurons" that can be steered without training, enabling more adaptable and human-like interactions.

LLM agents can achieve superior performance and generalization in complex tasks while slashing token usage by learning from compact, step-level summaries of subtask progress.