Stars
The Scene Language: Representing Scenes with Programs, Words, and Embeddings (arXiv preprint)
A logger, server and visualization dashboard for ML projects
Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
A lightweight DeepPotentialMD with JAX backend, and more than that! Built for both performance and flexibility in pure Python.
A native PyTorch Library for large model training
Writing AI Conference Papers: A Handbook for Beginners
Efficient Triton Kernels for LLM Training
Open-MAGVIT2: Democratizing Autoregressive Visual Generation
🏠[ECCV 2024] GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.
The hub for EleutherAI's work on interpretability and learning dynamics
[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
[CSUR] A Survey on Video Diffusion Models
an unofficial 2DGS implementation based on GauStudio
CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets
The simplest, fastest repository for training/finetuning medium-sized GPTs.
🚀 跃问YueWen 多模态大模型逆向API白嫖测试【特长：超强多模态】，支持高速流式输出、联网搜索、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。
Code for ICLR 2024 paper "Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment"
Open source implementation and models of One-step Diffusion with Distribution Matching Distillation