Xinyi Li

The paper proposes UniRule, a novel agentic RAG framework that unifies the detection rule generation process by mapping context and language to rules, significantly outperforming pure LLM generation.

The paper proposes PrefixMem, a dedicated encoder for Semantic IDs (SIDs), demonstrating that structured, prefix-conditioned representations significantly improve the accuracy and recall of generative recommendation systems.

The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distribution towards conciseness and certainty.

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to existing LLM-based methods.

TrafficRAG is a multimodal retrieval-augmented framework that automates traffic accident liability determination by integrating visual evidence, structured legal knowledge, and advanced LLM reasoning.