Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
Zhang Xingjian
Zhang199
AI & ML interests
Large Multimodal Models
Organizations
None yet
A Simple Framework of Small-scale LMMs for Video Understanding.
-
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-16-512
Video-Text-to-Text • 4B • Updated • 81 • 1 -
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512
Video-Text-to-Text • 4B • Updated • 187 -
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Naive-16-512
Video-Text-to-Text • 4B • Updated • 17 -
Zhang199/TinyLLaVA-Video-Phi2-Naive-16-512
Video-Text-to-Text • 3B • Updated • 24
Towards Smaller LMMs for Video Reasoning.
-
Zhang199/TinyLLaVA-Video-R1
Video-Text-to-Text • 4B • Updated • 20 • 4 -
Zhang199/TinyLLaVA-Video-Coldstart_NextQA_16
Video-Text-to-Text • 4B • Updated • 16 • 1 -
Zhang199/TinyLLaVA-Video-R1-training-data
Updated • 32 • 1 -
TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
Paper • 2504.09641 • Published • 16
A Framework of Small-scale Large Multimodal Models.
Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
Towards Smaller LMMs for Video Reasoning.
-
Zhang199/TinyLLaVA-Video-R1
Video-Text-to-Text • 4B • Updated • 20 • 4 -
Zhang199/TinyLLaVA-Video-Coldstart_NextQA_16
Video-Text-to-Text • 4B • Updated • 16 • 1 -
Zhang199/TinyLLaVA-Video-R1-training-data
Updated • 32 • 1 -
TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
Paper • 2504.09641 • Published • 16
A Simple Framework of Small-scale LMMs for Video Understanding.
-
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-16-512
Video-Text-to-Text • 4B • Updated • 81 • 1 -
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512
Video-Text-to-Text • 4B • Updated • 187 -
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Naive-16-512
Video-Text-to-Text • 4B • Updated • 17 -
Zhang199/TinyLLaVA-Video-Phi2-Naive-16-512
Video-Text-to-Text • 3B • Updated • 24
A Framework of Small-scale Large Multimodal Models.