Ming Yan

Instructor@Alibaba Group·中国·OpenReview

研究方向

dialogue · multimodal learning · vision-language pre-training · pre-trained language models · machine reading comprehension · attention · question answering

Ming Yan

WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

Perception-Aware Policy Optimization for Multimodal Reasoning

SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models

SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization

OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents

UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding

UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

WebSailor: Navigating Super-human Reasoning for Web Agent

Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

VLM-R³: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought

mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Endowing Visual Reprogramming with Adversarial Robustness

Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization

Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models

Enabling Weak LLMs to Judge Response Reliability via Meta Ranking

Enhancing Multi-Agent Learning in Real-World Interactive Environments through Process Reward Decomposition