A curated list of recent diffusion models for video generation, editing, and various other applications.

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

The best ChatGPT that $100 can buy.

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

An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

Official GitHub repository for FLUX.1 Krea [dev].

DiffusionNFT: Online Diffusion Reinforcement with Forward Process

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

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

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

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

Enjoy the magic of Diffusion models!

The collection of awesome papers on alignment of diffusion models.

[CVPR 2025] HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

A unified inference and post-training framework for accelerated video generation.

My learning notes/codes for ML SYS.

Official Implementation of Paper Transfer between Modalities with MetaQueries

An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation [Siggraph Asian 2025]

APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

MAGI-1: Autoregressive Video Generation at Scale

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

Official repository for LTX-Video

Lets make video diffusion practical!

[NeurIPS 2025] Improving Video Generation with Human Feedback

SkyReels-A2: Compose anything in video diffusion transformers