Shredded-Pork

UniRL. UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

minWM. A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models

Flash-GRPO. [ICML 2026] Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

shredded-pork.github.io. HTML

World-R1. [ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

JoyAI-Image. JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

ILVR. [ACL'26 Oral] Interleaved Latent Visual Reasoning with Selective Perceptual Modeling

Awesome-Visual-Generation-Alignment-Survey. A survey for visual generation alignment

Inferix. Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

paperlists. Processed / Cleaned Data for Paper Copilot

EditScore. [ICLR 2026] EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling

Latent-PMRF. Official Implementation of "Latent Posterior-Mean Rectified Flow for Higher-Fidelity Perceptual Face Restoration"

DGPO. [ICLR 2026][Ultra Fast&Powerful Diffusion RL] Reinforcing Diffusion Models by Direct Group Preference Optimization

TempFlow-GRPO. [ICLR 26] TempFlow-GRPO (Temporal Flow GRPO), a principled GRPO framework that captures and exploits the temporal structure inherent in flow-based generation.

DFT. [ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

flow_grpo. [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

ShareGPT-4o-Image. Python

UniWorld. UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

OmniGen2. OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

awesome-alignment-of-diffusion-models. [ACM Computing Surveys] The collection of awesome papers on alignment of diffusion models.

Arinar. Python

R1-Onevision. R1-onevision, a visual language model capable of deep CoT reasoning.

fractalgen. PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

ReasonGraph. [ACL 2025 Demo] Repository for the demo and paper: ReasonGraph: Visualisation of Reasoning Paths

DCTdiff. [ICML 2025] Official code for the paper 'DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space'

ExploreCfg. [NeurIPS2023] Exploring Diverse In-Context Configurations for Image Captioning

NumPro. [CVPR2025] Number it: Temporal Grounding Videos like Flipping Manga

StoryDiffusion. Accepted as [NeurIPS 2024] Spotlight Presentation Paper

Autoregressive-Models-in-Vision-Survey. [TMLR 2025🔥] A survey for the autoregressive models in vision.