Henry-Who321/RAdaR

RAdaR is an RL-native adaptive reasoning framework for VLMs that dynamically selects between Thinking and Instant modes.

/ 100

Experimental

No License No Package No Dependents

Maintenance 13 / 25

Adoption 5 / 25

Maturity 5 / 25

Community 6 / 25

Stars

Forks

Language

Python

License

—

Last pushed

Apr 10, 2026

Commits (30d)

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/multimodal/Henry-Who321/RAdaR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

starVLA/starVLA

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

vortex-data/vortex

An extensible, state-of-the-art framework for columnar compression, and the fastest FOSS...

motis-project/motis

multimodal routing, geocoding, and map tiles

zai-org/GLM-V

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

neka-nat/cad3dify

2D to 3D CAD Conversion Using VLM