Dahai Yu

EnergyMamba proposes an uncertainty-aware, graph-enhanced selective state space model to significantly improve both the accuracy and reliability of energy consumption prediction by explicitly modeling spatial dependencies.

EnergyMamba proposes an uncertainty-aware, graph-enhanced selective state space model to significantly improve both the accuracy and reliability of energy consumption prediction by explicitly modeling spatial dependencies.

E4GEN introduces an explainable diffusion framework that significantly improves time-series generation by specifically focusing on and controlling the fidelity of extreme events.

E4GEN introduces an explainable diffusion framework that significantly improves time-series generation by specifically focusing on and controlling the fidelity of extreme events.

This paper introduces Test-Time Harness Evolution (TTHE), a method for optimizing LLM agent harnesses during evaluation using execution traces, without requiring gold labels or training.