Generative Refinement Networks for Visual Synthesis

A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.

PyTorch code and models for VJEPA2 self-supervised learning from video.

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Ongoing research training transformer models at scale

code & model for arxiv paper "Autoregressive Image Generation with Masked Bit Modeling"

BitDance & UniWeTok: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model.

UEval: A Benchmark for Unified Multimodal Generation

ViPE: Video Pose Engine for Geometric 3D Perception

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

NEO Series: Native Vision-Language Models from First Principles

This repo provides the official code for : 1) TransBTS: Multimodal Brain Tumor Segmentation Using Transformer (https://arxiv.org/abs/2103.04430) , accepted by MICCAI2021. 2) TransBTSV2: Towards Bet…

Democratizing Reinforcement Learning for LLMs

Native Multimodal Models are World Learners

Grounding Image Matching in 3D with MASt3R

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

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Open-source unified multimodal model

MAGI-1: Autoregressive Video Generation at Scale

[ICLR'24 & IJCV‘25] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

[ICLR 2025] Diffusion Feedback Helps CLIP See Better

An Open-source RL System from ByteDance Seed and Tsinghua AIR

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

Raster to Vector Graphics Converter

[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"