Mingyang Song's picture

Mingyang Song

hitsmy

·

AI & ML interests

LVLMs

Recent Activity

upvoted a paper 1 day ago

Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis

upvoted a paper 1 day ago

GEMS: Agent-Native Multimodal Generation with Memory and Skills

upvoted an article about 1 month ago

Your MoE Model Does Not Have to Select Fixed Number of Experts

View all activity

Organizations

commented 3 papers about 1 year ago

FastCuRL: Curriculum Reinforcement Learning with Progressive Context Extension for Efficient Training R1-like Reasoning Models

Paper • 2503.17287 • Published Mar 21, 2025 • 11 •

From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration

Paper • 2503.12821 • Published Mar 17, 2025 • 10 •

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

Paper • 2501.03124 • Published Jan 6, 2025 • 14 •