Lets make video diffusion practical!

Muon is Scalable for LLM Training

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

SEED-Voken: A Series of Powerful Visual Tokenizers

a curated list of high-quality papers on resource-efficient LLMs 🌱

PyTorch native post-training library

PyTorch implementation for "Parallel Sampling of Diffusion Models", NeurIPS 2023 Spotlight

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Inference code for Llama models

[NeurIPS 2023] Code for "Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives"

Official implementation of NeurIPS 2022 paper: "Embodied Scene-aware Human Pose Estimation".

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

My code of SuperTrack: Motion Tracking for Physically Simulated Characters using Supervised Learning

[CVPR 2024] SAI3D: Segment Any Instance in 3D Scenes

gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstruction, CVPR 2023.

The official implementation of the paper "Human Motion Diffusion as a Generative Prior"

(CVPR 2023) Official code of MACARONS: Mapping And Coverage Anticipation with RGB ONline Self-supervision. Also contains an updated and improved implementation of our previous work SCONE (NeurIPS 2…

Official code for "HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion"

[ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation

Official Code for DragGAN (SIGGRAPH 2023)

PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces (CVPR 2023)

Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.

ImageBind One Embedding Space to Bind Them All

[SIGGRAPH 2023] Composite Motion Learning with Task Control

Official PyTorch implementation of the paper "TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis" ICCV 2023

This is the code for the paper PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation

Toolbox for ExPI dataset