internlm
/

CapRL-3B

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

yuhangzang commited on Sep 25, 2025

Commit

fdee6ca

·

verified ·

1 Parent(s): cdaad41

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -17,7 +17,6 @@ This is the first study of applying Reinforcement Learning with Verifiable Rewar
 open-ended and subjective image captioning task. Unlike traditional Supervised Fine-Tuning, which
 can lead to models memorizing a limited set of annotated captions, our method allows the model to
 explore and generate a broader range of creative and general descriptions.
 CapRL is a new training paradigm featuring a decoupled two-stage pipeline. The initial
 stage uses LVLMs to generate rich and accurate captions. Subsequently, the second stage evaluates
 caption quality by using a vision-only LLM to perform the QA task. We also created a specific QA

 open-ended and subjective image captioning task. Unlike traditional Supervised Fine-Tuning, which
 can lead to models memorizing a limited set of annotated captions, our method allows the model to
 explore and generate a broader range of creative and general descriptions.
 CapRL is a new training paradigm featuring a decoupled two-stage pipeline. The initial
 stage uses LVLMs to generate rich and accurate captions. Subsequently, the second stage evaluates
 caption quality by using a vision-only LLM to perform the QA task. We also created a specific QA