Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

verl: Volcano Engine Reinforcement Learning for LLMs

A PyTorch native platform for training generative AI models

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference

Official implementation of LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment.

Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.

DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support

Unified Multimodal Model for image generation/editing/understanding

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"

Official code for ICCV 2025 paper, X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation

A framework that allows you to apply Sparse AutoEncoder on any models

讨贼王云鹤檄文

SigLIP-based Aesthetic Score Predictor

Open protocol for communication between AI agents, applications, and humans.

Official Implementation of Paper Transfer between Modalities with MetaQueries

DeepDubber-V1: Towards High Quality and Dialogue, Narration, Monologue Adaptive Movie Dubbing Via Multi-Modal Chain-of-Thoughts Reasoning Guidance

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning

Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)

Open-source unified multimodal model

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

Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"

[ICML 2025] This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"

这个仓库有1426个star，不信你试试

[ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation

[CVPR 2025] EgoLife: Towards Egocentric Life Assistant