Starred repositories
Original implementation of "3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes"
[NeurIPS 2024 Spotlight] Implementation of the paper "3D Gaussian Splatting as Markov Chain Monte Carlo"
Ongoing research training gaussian splatting at scale by distributed system
A collaboration friendly studio for NeRFs
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting (SIGGRAPH Asia 2024, TOG)
UPMEM LLM Framework allows profiling PyTorch layers and functions and simulate those layers/functions with a given hardware profile.
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
A Modular Framework for 3D Gaussian Splatting and Beyond
A hardware accelerator for General Matrix Multiply, developed in SystemC using ESP.
Repository to host and maintain scale-sim-v2 code
An AXI4 crossbar implementation in SystemVerilog
Verilog evaluation benchmark for large language model
OpenSource GPU, in Verilog, loosely based on RISC-V ISA
A generative speech model for daily dialogue.
[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving
Play ChatGPT and other LLM with Xiaomi AI Speaker
Automate Creation of YouTube Shorts using MoviePy.
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Faster Whisper transcription with CTranslate2
Letta (formerly MemGPT) is a framework for creating LLM services with memory.
中文大模型能力评测榜单:目前已囊括139个大模型,覆盖chatgpt、gpt-4o、谷歌gemini、Claude3.5、百度文心一言、千问、百川、讯飞星火、商汤senseChat、minimax等商用模型, 以及deepseek-v3、qwen2.5、llama3.1、glm4、书生internLM2.5等开源大模型。不仅提供能力评分排行榜,也提供所有模型的原始输出结果!
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf