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

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Official Repository of Absolute Zero Reasoner

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

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

OpenVLA: An open-source vision-language-action model for robotic manipulation.

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

Generative Agents: Interactive Simulacra of Human Behavior

12 Lessons to Get Started Building AI Agents

A list of AI autonomous agents

A curated list of reinforcement learning with human feedback resources (continually updated)

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Official repository of paper “IML-ViT: Benchmarking Image manipulation localization by Vision Transformer”

Official PyTorch implementation for "Large Language Diffusion Models"

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models

CODA: Repurposing Continuous VAEs for Discrete Tokenization

[ICLR2025] Halton Scheduler for Masked Generative Image Transformer

High-Resolution Image Synthesis with Latent Diffusion Models

NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

[ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

[NeurIPS25 & ICML25 Workshop on Reliable and Responsible Foundation Models] A Simple Baseline Achieving Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1. Paper at: https:/…

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

The Next Step Forward in Multimodal LLM Alignment

MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & TIS & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"