Ideogram 4: Open image model at the forefront of design

NVIDIA FastGen: Fast Generation from Diffusion Models

Lightweight Image Video Action Generation Inference Framework

[ICLR 2026] Official pytorch implementation of The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM

The best ChatGPT that $100 can buy.

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

Dion optimizer algorithm

NanoGPT (124M) in 90 seconds

Helios: Real Real-Time Long Video Generation Model

Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.

Muon is an optimizer for hidden layers in neural networks

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

[RSS 2026] Interactive World Simulator for Robot Policy Training and Evaluation

AI agents running research on single-GPU nanochat training automatically

Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀

🎬ActionMesh: A fast video to animated mesh model with unprecedented quality. Generate animated mesh seamlessly importable into any 3D software in less than a minute.

Depth Anything 3

Native and Compact Structured Latents for 3D Generation

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Official inference repo for FLUX.2 models

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

SAM 3D Objects

Reference PyTorch implementation and models for DINOv3

RigAnything: Template‑Free Autoregressive Rigging for Diverse 3D Assets (SIGGRAPH TOG 2025)