Lei Chen

VoG: Enhancing LLM Reasoning through Stepwise Verification on Knowledge Graphs

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning

Grouped-head latenT Attention

Finding the Thread: Context-Driven Incremental Compression for Multi-Turn Dialogue

LoopServe: An Adaptive Dual-phase LLM Inference Acceleration System for Multi-Turn Dialogues

DENSE-RAG: Measuring and Improving Context Understanding for Consistent Retrieval-Augmented Generation

ReasonIE: better LLMs for Scientific Information Extraction with reinforcement learning and data augmentation

Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference

ReactionLLM: Data-Centric Learning for a Compact Single-step Chemical reaction prediction model

Semi-Parametric Retrieval via Binary Bag-of-Tokens Index

Optimizing Retrieval for RAG via Reinforced Contrastive Learning

Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models

N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph Learning

A Selective Learning Method for Temporal Graph Continual Learning

Learning Towards Emergence: Paving the Way to Induce Emergence by Inhibiting Monosemantic Neurons on Pre-trained Models