Multimodal Synthetic Dataset and Multi-Task Reinforcement Learning Document Parser
AI & ML interests
None defined yet.
Recent Activity
-
TIGER-Lab/VL-Rethinker-7B
Image-Text-to-Text • 8B • Updated • 464 • 15 -
TIGER-Lab/VL-Rethinker-72B
Visual Question Answering • 73B • Updated • 11 • 5 -
TIGER-Lab/ViRL39K
Preview • Updated • 489 • 41 -
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 45
OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs.
Multimodal Synthetic Dataset and Multi-Task Reinforcement Learning Document Parser
LLM-based dense retrieval models for EN & ZH (also effective in other languages)
-
TIGER-Lab/VL-Rethinker-7B
Image-Text-to-Text • 8B • Updated • 464 • 15 -
TIGER-Lab/VL-Rethinker-72B
Visual Question Answering • 73B • Updated • 11 • 5 -
TIGER-Lab/ViRL39K
Preview • Updated • 489 • 41 -
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 45
Reinforcement Learning Document Parser and High-Quality Synthetic Dataset.
OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs.