Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity
Zhang Xingjian
Zhang199
AI & ML interests
Large Multimodal Models
Recent Activity
updated
a model
1 day ago
Zhang199/EDGE-GRPO-Qwen-1.5B
updated
a model
1 day ago
Zhang199/EDGE-GRPO-Qwen-7B
Organizations
None yet
Towards Smaller LMMs for Video Reasoning.
-
Zhang199/TinyLLaVA-Video-R1
Video-Text-to-Text • 4B • Updated • 67 • 2 -
Zhang199/TinyLLaVA-Video-Coldstart_NextQA_16
Video-Text-to-Text • 4B • Updated • 147 -
Zhang199/TinyLLaVA-Video-R1-training-data
Updated • 44 • 1 -
TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
Paper • 2504.09641 • Published • 16
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 • 67 • 2 -
Zhang199/TinyLLaVA-Video-Coldstart_NextQA_16
Video-Text-to-Text • 4B • Updated • 147 -
Zhang199/TinyLLaVA-Video-R1-training-data
Updated • 44 • 1 -
TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
Paper • 2504.09641 • Published • 16
models
11
Zhang199/EDGE-GRPO-Qwen-1.5B
Text Generation
•
2B
•
Updated
•
27
Zhang199/EDGE-GRPO-Qwen-7B
Text Generation
•
8B
•
Updated
•
10
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-16-512
Video-Text-to-Text
•
4B
•
Updated
•
2.32k
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Naive-16-512
Video-Text-to-Text
•
4B
•
Updated
•
10
Zhang199/TinyLLaVA-Video-Phi2-Naive-16-512
Video-Text-to-Text
•
3B
•
Updated
•
2.27k
Zhang199/TinyLLaVA-Qwen2-0.5B-SigLIP
Image-Text-to-Text
•
1B
•
Updated
•
27
•
4
Zhang199/TinyLLaVA-Qwen2.5-3B-SigLIP
Image-Text-to-Text
•
4B
•
Updated
•
65
Zhang199/TinyLLaVA-Video-R1
Video-Text-to-Text
•
4B
•
Updated
•
67
•
2
Zhang199/TinyLLaVA-Video-Coldstart_NextQA_16
Video-Text-to-Text
•
4B
•
Updated
•
147
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512
Video-Text-to-Text
•
4B
•
Updated
•
59