ASID-Caption

AI & ML interests

Video Understanding, Audio-Visual, Multimodal LLMs, Video Captioning, Instruction Tuning, Dataset Curation, Qwen-based, Open-source, Fully-Open-MLLMs

Recent Activity

lyhisme  submitted a paper 2 days ago

Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought

lyhisme  updated a model 15 days ago

AudioVisual-Caption/ASID-Captioner-7B

lyhisme  updated a model 15 days ago

AudioVisual-Caption/ASID-Captioner-3B

View all activity

Papers

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions

View all Papers

Team members 1