Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"

The official implementation of the paper "MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding". MMFuser addresses the limitations of current MLLMs in captur…

[arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

A high-throughput and memory-efficient inference and serving engine for LLMs

[CVPR 2025] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

A generative world for general-purpose robotics & embodied AI learning.

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"

[CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

[NeurIPS 2024] Classification Done Right for Vision-Language Pre-Training

Code for Fast Training of Diffusion Models with Masked Transformers

Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Efficient vision foundation models for high-resolution generation and perception.

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

Codebase for the paper-Elucidating the design space of language models for image generation

Scaling Diffusion Transformers with Mixture of Experts

[ICLR 2025] BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities

This repo contains the code for 1D tokenizer and generator

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

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

Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"

Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think (ICLR 2025)

Official repository for our work on micro-budget training of large-scale diffusion models.

Fast Diffusion Models with Transformers

Let us control diffusion models!

Official PyTorch implementation of ECCV 2024 Paper: ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback.

[ICLR 2025] Diffusion Feedback Helps CLIP See Better

[CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers