Qingwei Lin

Sr. Principal Researcher@Microsoft Research·中国·OpenReview

研究方向

Reinforcement Learning · LLM · GPT · Deep Learning · AIOps · Cloud Intelligence · Machine learning · Data mining · Cloud systems · Log Analysis · Anomaly Detection · Diagnosis · Root cause analysis

Qingwei Lin

Pretrain Value, Not Reward: Decoupled Value Policy Optimization

DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems

RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning

Text2Grad: Reinforcement Learning from Natural Language Feedback

WarriorMath: Empowering Mathematical Reasoning for Large Language Models via Expert Battles

Memory-Augmented Personalized Retrieval for Long-Context Egocentric Video

GUI-360° : A Comprehensive Dataset and Benchmark for Computer-Using Agents

G-KV: Decoding-Time KV Cache Eviction with Global Attention

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

Duet: Joint Exploration of User–Item Profiles

VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model

Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

RuAG: Learned-rule-augmented Generation for Large Language Models

SELF-EVOLVED REWARD LEARNING FOR LLMS

Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation

Zoomer: Enhancing MLLM Performance with Adaptive Image Focus Optimization