[ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
Ollama based Benchmark with detail I/O token per second. Python with Deepseek R1 example.
Real-time guardrail that shows token spend & kills runaway LLM/agent loops.
GraphRAG / From Local to Global: A Graph RAG Approach to Query-Focused Summarization
Knowledge work automation with AI agents
Evaluation tools for Retrieval-augmented Generation (RAG) methods.
A Python Telegram bot powered by Google's gemini-pro LLM API
Multi-agent LLM system for intelligent replenishment decisions in manufacturing supply chains
Run any Large Language Model behind a unified API
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
共 3888 条 · 第 112 / 195 页