#
Lists (6)
Starred repositories
causal-falsify: A Python library with algorithms for falsifying unconfoundedness assumption in a composite dataset from multiple sources.
Official implementation of Inductive Moment Matching
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
gDel3D is the fastest 3D Delaunay triangulation algorithm. It uses the GPU for massive parallelism.
Tools to Build Equivariant Tensors
OpenEquivariance: a fast, open-source GPU JIT kernel generator for the Clebsch-Gordon Tensor Product.
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
Implementation and explorations into Blackbox Gradient Sensing (BGS), an evolutionary strategies approach proposed in a Google Deepmind paper for Table Tennis
A repository used to compare the KVP and NVP emulators for two-body scattering in momentum space. This code was used to generate results for the paper ''Wave-function-based emulation for nucleon-nu…
High-performance retrieval engine for unstructured data
Python package for solving multistage stochastic programming problems. Capable in handling general convex and hierarchical problems as well as parallel processing (via multithreading).
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
3DGS-to-PC: Convert a 3D Gaussian splatting scene into a dense point cloud or basic mesh with advanced customisation options and high-accuracy rendered point colours
Python tool for converting files and office documents to Markdown.
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural n…
Implementation of language-level autograd compiler for Julia
Official implementation of Diffusion Autoencoders
PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks
Code for paper E(n)-Equivariant Topological Neural Networks
Official implementation of the paper "Light Transport-aware Diffusion Posterior Sampling for Single View Reconstruction of Volumes"
collection of diffusion model papers categorized by their subareas
Julia package to seamlessly integrate Mathematica's MathLink with Julia's native Symbolics package
A FlashAttention implementation for JAX with support for efficient document mask computation and context parallelism.
Toolkit for linearizing PDFs for LLM datasets/training
Noise Conditional Score Networks (NeurIPS 2019, Oral)
egui: an easy-to-use immediate mode GUI in Rust that runs on both web and native