Meng Wang

Moenupa

·

https://moenupa.github.io

AI & ML interests

MLLM Post-Training & Alignment

Recent Activity

updated a model about 5 hours ago

MLLM-CL/Qwen3-4B-Thinking-2507-SDPO5-MathChemToolCode

updated a model about 5 hours ago

MLLM-CL/Qwen3-4B-Thinking-2507-SDPO5-MathChemTool

updated a model about 5 hours ago

MLLM-CL/Qwen3-4B-Thinking-2507-SDPO5-MathChem

View all activity

Organizations

authored a paper 14 days ago

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

Paper • 2607.01763 • Published 18 days ago • 10

submitted a paper to Daily Papers 17 days ago

Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training

Paper • 2607.01763 • Published 18 days ago • 10

authored a paper 7 months ago

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?

Paper • 2512.15649 • Published Dec 17, 2025 • 7