LLM agents built for control. Designed for real-world use. Deployed in minutes.

Offical Implementation of SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

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

Wan: Open and Advanced Large-Scale Video Generative Models

Web crawler and scraper for Rust

Hierarchical Reasoning Model Official Release

Biomni: a general-purpose biomedical AI agent

SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

[NeurIPS 2025] Official resources of "HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation".

[ICCV 2025] Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction

Generative Models by Stability AI

A python library that makes AMR parsing, generation and visualization simple.

SPRING is a seq2seq model for Text-to-AMR and AMR-to-Text (AAAI2021).

Diagnostic Reasoning Knowledge Graph for Large Language Model Diagnosis Prediction

Demo of integrating and exploring SemMedDB

Precision Medicine Knowledge Graph (PrimeKG)

Hetionet: an integrative network of disease

A curated list of biomedical knowledge graphs and of resources for their construction.

Clinical Knowledge Graph (CKG) is a platform with twofold objective: 1) build a graph database with experimental data and data imported from diverse biomedical databases 2) automate knowledge disco…

AutoML for causal inference.

iBKH: The integrative Biomedical Knowledge Hub

A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.

[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research

[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …

MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025