Haolong Jia

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training and rollout.

This paper proposes DPIFrame, a dual parallelizable framework for accelerating Click-through rate (CTR) model inference on GPU, achieving state-of-the-art inference performance with significant speedups.

This paper proposes FinSAgent, an evidence-grounded multi-agent framework for financial question answering over SEC filings, which improves retrieval coverage and answer correctness through corpus-side conditioning.