Skip to main content
Ryan Orban

Ryan Orban

Subject
6 entries

Microsoft

Bookmarks

  1. AgentRC: context engineering and AI-readiness for repos

    AgentRC (formerly Primer) measures and generates AI-readiness for repos — scoring across 9 pillars, generating instruction files, and running CI drift detection so agent context stays current as code evolves.

  2. monitors4codegen — Monitor-Guided Decoding

    Monitor-Guided Decoding uses LSP (Language Server Protocol) static analysis as a 'monitor' during code LM generation to enforce semantic validity — identifiers must exist, types must match. NeurIPS 2023 paper from Microsoft with the multispy Python library for building LSP-backed code gen applications.

  3. JARVIS / HuggingGPT: LLM as AI Model Orchestrator

    Microsoft JARVIS (also published as HuggingGPT) uses ChatGPT as a task planner that routes subtasks to specialized Hugging Face models — an early demonstration that LLMs could orchestrate other AI models as tools. A prototype of the multi-model agent pattern.

  4. Image as a Foreign Language: BEIT-3 Pretraining for All Vision and Vision-Language Tasks

    Wang, Bao, Dong et al. at Microsoft introduce BEIT-3, a general-purpose multimodal foundation model that treats images as a 'foreign language' and applies masked language modeling uniformly across images, text, and image-text pairs. BEIT-3 achieves state-of-the-art across seven vision and vision-language benchmarks including COCO, ImageNet, VQA, and NLVR2.

  5. ZeRO: Memory Optimizations Toward Training Trillion Parameter Models

    ZeRO (Zero Redundancy Optimizer) eliminates memory redundancy in distributed training by partitioning optimizer states, gradients, and parameters across data-parallel processes rather than replicating them. It enables training models 8x larger than prior methods on the same hardware and forms the foundation of Microsoft's DeepSpeed library.

  6. MLOps Maturity Models: Google and Microsoft Frameworks

    ZenML's overview of MLOps maturity models from Google and Microsoft — frameworks for thinking about how ML organizations can systematically improve how they develop and deploy models. Useful if you're trying to level up a team's ML practices from ad-hoc to automated.

All bookmarks