wizardlancet
Follow
Stars
cantinilab / scPRINT
Forked from jkobject/scPRINT🏃 The go-to single-cell Foundation Model
Memory for AI Agents in 6 lines of code
Get your documents ready for gen AI
Processed / Cleaned Data for Paper Copilot
A python module to repair invalid JSON from LLMs
LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…
OpenTelemetry wrapper for Claude Code CLI that logs tool calls, token usage, costs, and execution traces to Logfire, Sentry, Honeycomb, or Datadog. Drop-in replacement that swaps 'claude' command f…
Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development
LaTeX package that makes mathematical formulae accessible via screen reader and braille display
Convert PDF to markdown + JSON quickly with high accuracy
DoctorRAG is a medical AI that mimics doctor-like reasoning by combining textbook knowledge with insights from similar patient cases, using "textual gradients" to refine its answers for improved ac…
🚀 Efficient implementations of state-of-the-art linear attention models
User Profile-Based Long-Term Memory for AI Chatbot Applications.
A virtual clinical environment for self‑evolving LLM diagnostic agents.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
CleanPatrick is a large-scale, real-world image data-cleaning benchmark with 496,377 binary annotations from 933 medical crowd workers for ranking off-topic, near-duplicate, and label-error issues.
[ACL 2025 Findings] "Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA"
Revisiting Mid-training in the Era of Reinforcement Learning Scaling
The absolute trainer to light up AI agents.
NVDA, the free and open source Screen Reader for Microsoft Windows
Modern photo gallery for photographers, with S3/GitHub sync, EXIF details, maps, and a WebGL viewer.
[MIDL 2025] Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders