Models trained using GRPO for enhanced Chart Reasoning
Sanchit Sinha
sanchit97
AI & ML interests
VLMs, RL, XAI
Recent Activity
upvoted
a
collection
11 days ago
Qwen3-VL
upvoted
a
paper
14 days ago
From Pixels to Words -- Towards Native Vision-Language Primitives at
Scale
liked
a model
about 1 month ago
internlm/CapRL-3B
Organizations
None yet