Xiang Yu

A novel framework flags 68 traffic signs for immediate replacement, revealing significant gaps in nighttime retroreflectivity that traditional methods overlook.

RootMem transforms how personalized LLMs access critical logical memories, outperforming traditional methods by integrating structured decision logic into memory retrieval.

Time-inconsistent control problems can be tackled effectively with a novel two-stage reinforcement learning algorithm that learns equilibrium policies, bridging theory and practical applications in finance.

DCPM reveals that separating memory processes can boost LLM agents' ability to infer user intentions and beliefs across sessions, leading to a dramatic increase in personalization accuracy.

Q-learning can now tackle mean-field control problems with common noise, even when the ideal data is unobservable, opening the door to more realistic and complex multi-agent control scenarios.

Tackling mean-field control with common noise requires a novel integrated q-function (Iq-function) approach to identify optimal policies as fixed points.

Injecting knowledge graphs into LLMs boosts medical question generation by 8%, suggesting a simple way to patch up LLM knowledge gaps.

Forget end-to-end molecular design; this retrieval-augmented model lets you steer analog generation with prompts and external references, mimicking medicinal chemists' intuition.