Panda ASCII art

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Grindcore special issue

deepinsight/insightface — State-of-the-art 2D and 3D Face Analysis Project

UPC-ViRVIG/pymotion — A Python library for working with motion data in numpy or PyTorch

Pose Representations for Deep Skeletal Animation, code

aahung/BeeVeeH — BeeVeeH - another BVH Player + some BVH APIs

mkkellogg/GaussianSplats3D — Three.js-based implementation of 3D Gaussian splatting

nerfstudio-project/gsplat — CUDA accelerated rasterization of gaussian splatting

ianyh/Amethyst — Automatic tiling window manager for macOS à la xmonad.

google/python-fire — Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

microsoft/graphrag — A modular graph-based Retrieval-Augmented Generation (RAG) system

UM-ARM-Lab/pytorch_kinematics — Robot kinematics implemented in pytorch

BUT-FIT/whisper-ATC-czech-full — fine-tuned openai/whisper-medium on Czech and English air traffic

divakaivan/glaswegian_audio

Libriheavy: A 50,000 Hours ASR Corpus with Punctuation Casing and Context, code

guestdaniel/tdklatt — Implementation of the Klatt synthesizer in Python 3

Can Learned Optimization Make Reinforcement Learning Less Difficult?, code

Learning to (Learn at Test Time): RNNs with Expressive Hidden States, code, pytorch

Big, beautiful goals – but can’t be bothered? 11 great productivity tips for lazy people

mistralai/Mathstral-7B-v0.1

Mathstral: A 7B Parameter LLM for Math and Science

Zielon/CPURasterizer — CPU Based Rasterizer Engine

MrNeRF/awesome-3D-gaussian-splatting

Zielon/ParallelQSlim — Shape Aware Parallel Mesh Simplification Algorithm

ingra14m/Deformable-3D-Gaussians — [CVPR 2024] Official implementation of “Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction”

threestudio-project/threestudio — A unified framework for 3D content generation.

openai/point-e — Point cloud diffusion for 3D model synthesis

openai/shap-e — Generate 3D objects conditioned on text or images

Ig Nobel prize winners including: Factors Involved in the Ejection of Milk

On the Continuity of Rotation Representations in Neural Networks

Moshi: a speech-text foundation model for real time dialogue, code, models

AudioSR: Versatile Audio Super-resolution at Scale, code

A Beginners Guide to Dual-Quaternions

RWKV/rwkv.cpp — INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

monatis/clip.cpp — CLIP inference in plain C/C++ with no extra dependencies

skeskinen/bert.cpp — ggml implementation of BERT

hpcaitech/Open-Sora — Democratizing Efficient Video Production for All

Phonetic potential in the extant apes and extinct hominins

hustvl/Vim — Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

High-Fidelity Audio Compression with Improved RVQGAN, code

HPLT Datasets v2