zghhui/Janus-Pro-1B-GCPO-Geneval

Model

This repository hosts a [Janus-Pro 1B] trained by GCPO. The reward model is Geneval.

zghhui/Janus-Pro-7B-GCPO-HPS

Model

This repository hosts a [Janus-Pro 7B] trained by GCPO. The reward model is HPS.

zghhui/Janus-Pro-1B-GCPO-HPS

Model

This repository hosts a [Janus-Pro-1B] trained by GCPO. The reward model is GenEval.

zghhui/LlamaGen-T2I-GCPO

Model

This repository hosts a [LlamaGen-T2I (256)] trained by GCPO. The reward model is HPS.

deepseek-ai/Janus-Pro-7B

Model

1. Introduction

Franklin0/ReasonGen-R1-SFT

Model

Model Card for ReasonGen-R1 (SFT Only)

CaraJ/T2I-R1

Model

🌟🔥 T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

FreedomIntelligence/Janus-4o-7B

Model

Janus-4o-7B

zghhui/GCPO

[ICLR 2026] Code for "Group Critical-token Policy Optimization for Autoregressive Image Generation"