[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"
-
Updated
Feb 13, 2026 - Python
#
think-with-image
Here are 4 public repositories matching this topic...
🔍 OpenSearch-VL provides a fully open recipe for training strong multimodal deep search agents through high-quality data curation, diverse visual/search tools, and fatal-aware agentic reinforcement learning.
-
Updated
May 7, 2026 - Python
[CVPR 2026] AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
visual-reasoning vision-language-model multimodal-large-language-models multimodal-reasoning think-with-image vision-token-compression
-
Updated
Apr 27, 2026 - Python
[ICML 2026] A think-with-image GUI visual grounding model.
-
Updated
Oct 7, 2025 - Python
Improve this page
Add a description, image, and links to the think-with-image topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the think-with-image topic, visit your repo's landing page and select "manage topics."