Stars
Production-Grade Container Scheduling and Management
Virtual whiteboard for sketching hand-drawn like diagrams
A set of NN models for evaluating object and camera motion in videos
Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)
Echo-4o: Harnessing Proprietary Models’ Synthetic Images for Improved Image Generation
🤖 Intelligent integration between Claude Code and Google Gemini for large-scale code analysis
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
High-resolution models for human tasks.
Video-Infinity generates long videos quickly using multiple GPUs without extra training.
Differentiable Iso-Surface Extraction Package (DISO)
University of Toronto thesis class for LaTeX
Implementation of DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
Multiview Compressive Coding for 3D Reconstruction
Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model
LlamaIndex is the leading document agent and OCR platform
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Latent Point Diffusion Models for 3D Shape Generation
[ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)
Official implementation of "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation"