Picture for Huawei Shen

Huawei Shen

Stop Spinning Wheels: Mitigating LLM Overthinking via Mining Patterns for Early Reasoning Exit

Add code
Aug 25, 2025
Viaarxiv icon

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models

Add code
Jul 22, 2025
Viaarxiv icon

From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment

Add code
Jun 14, 2025
Viaarxiv icon

Inference-time Alignment in Continuous Space

Add code
May 26, 2025
Viaarxiv icon

Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs

Add code
May 23, 2025
Viaarxiv icon

Distilling the Implicit Multi-Branch Structure in LLMs' Reasoning via Reinforcement Learning

Add code
May 22, 2025
Viaarxiv icon

InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning

Add code
May 07, 2025
Viaarxiv icon

Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models

Add code
Apr 01, 2025
Viaarxiv icon

MIGE: A Unified Framework for Multimodal Instruction-Based Image Generation and Editing

Add code
Feb 28, 2025
Viaarxiv icon

Revisiting Robust RAG: Do We Still Need Complex Robust Training in the Era of Powerful LLMs?

Add code
Feb 17, 2025
Viaarxiv icon