Yinhan He

Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping

GCSGNN: Towards Global Counterfactual-Based Self-Explainable Graph Neural Networks

Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

Scaling Epidemic Inference on Contact Networks: Theory and Algorithms

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models

Edge Prompt Tuning for Graph Neural Networks

Understanding Prejudice and Fidelity of Diverge-to-Converge Multi-Agent Systems

Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning