Cluster 647460

4 repos

Python · 2

visual-reasoning ·210

data-efficiency ·210

efficient-length-reward ·210

mathematical-reasoning ·210

multimodal-large-language-model ·210

open-source-7b-model ·210

prioritized-advantage-distillation ·210

reinforcement-learning ·210

self-reflective-chain-of-thought ·210

cold-start-initialization ·210

Related clusters

WaltonFuture/Qwen2.5VL-7b-RLCS

* 🐙 **GitHub Repo:** [waltonfuture/RL-with-Cold-Start](https://github.com/waltonfuture/RL-with-Col…

5 commits

waltonfuture/RL-with-Cold-Start

SFT+RL boosts multimodal reasoning

Python

8 commits

WaltonFuture/Qwen2.5VL-3b-RLCS

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

8 commits

CSfufu/Revisual-R1

[ICLR 2026]🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage…

Python

210

50 commits