Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

A cross-agent research paper toolkit that transforms papers into learning environments with summaries, code demos, and a local web viewer for Claude Code, Codex, OpenCode, and DeepSeek Harness.

AI agent skill to generate editable PowerPoint presentations from papers, code, or documents using Codex or Claude Code.

Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.

Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations. Use for 学术论文降重、查重后修改、重复段落重写、paraphrasing, similarity-report remediation, abstracts, literature reviews, methods, results, discussions, theses, and manuscripts in DOCX, Markdown, or plain text. Do not use to disguise plagiarism, fabricate sources, or evade academic-integrity review.

[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models

monolish: MONOlithic LInear equation Solvers for Highly-parallel architecture

Convert born-digital, scanned, or mixed PDFs into auditable Markdown while preserving reading order, equations, source-page anchors, and information-bearing images as adjacent non-original text descriptions. Use this skill whenever a user asks to transcribe, OCR, understand, or convert a PDF into Markdown, especially for scanned PDFs, image-heavy pages, formulas, multi-column layouts, page or section ranges, or token-efficient reuse. LT2MD (Long Transcribe to Markdown) is a workflow contract, not a replacement for a PDF parser or OCR/VLM backend.

[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models