Native and Compact Structured Latents for 3D Generation

A Cross-Platform Backend for High-Performance Sparse Convolutions

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

SAM 3D Objects

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

A part-based 3D generation framework & the largest and most comprehensively annotated 3D part dataset.

High-throughput tensor loading for PyTorch

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

rCM: SOTA Diffusion Distillation & Few-Step Video Generation based on sCM/MeanFlow

A minimal implementation of DeepMind's Genie world model

[ICLR 2025 Oral] Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

[PG2025] PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

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

Nano vLLM

This repo contains the code for 1D tokenizer and generator

An open-source AI agent that brings the power of Gemini directly into your terminal.

Differentiable Tool for Mesh2Occupancy & Mesh2SDF

Efficient Part-level 3D Object Generation via Dual Volume Packing

[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

Efficient triton implementation of Native Sparse Attention.

[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / U…

[NeurIPS 2025] Official implementation for our paper "Scaling Diffusion Transformers Efficiently via μP".

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training