Lists (4)
Stars
PaperBanana: Automating Academic Illustration For AI Scientists
All of source code of Floorp 12, the most Advanced and Fastest Firefox derivative 🦊
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Free and open source library for AI object detection and semantic segmentation in geospatial rasters. 🚀
Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
A runtime fault injection tool for PyTorch 🔥
Application Level Fault Injection for Pytorch
Parallel Out-of-Core Tabular Data Preprocessing in Julia
The batteries-included agent harness.
SGLang is a high-performance serving framework for large language models and multimodal models.
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
For calculating global feature importance using Shapley values.
Fast, Accurate and Memory-Efficient Principal Component Analysis All in One For Large-scale Dataset
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Distribute and run LLMs with a single file.
TeraPCA is a multithreaded C++ software suite based on Intel's MKL library (or any other BLAS and/or LAPACK distribution). TeraPCA features no dependencies to external libraries and combines the ro…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)