-
Microsoft Research
- Seattle, WA
- https://naoto-usuyama.github.io
- in/naoto-usuyama
- @naotous
Lists (2)
Sort Name ascending (A-Z)
Starred repositories
Voice-to-text app for macOS to transcribe what you say to text almost instantly
Simple & Scalable Pretraining for Neural Architecture Research
Press shortcut → speak → get text. Free and open source. More local-first apps soon ❤️
Official implementation of LLaVa-Rad, a small multimodal model for chest X-ray findings generation.
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
AI chat assistant for Obsidian with contextual awareness, smart writing assistance, and one-click edits. Features vault-aware conversations, semantic search, and local model support.
Quickly design beautiful screenshots and open graph images
Train transformer language models with reinforcement learning.
A Python package that makes it easy for developers to create AI apps powered by various AI providers.
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Code examples that accompany various MDN DOM and Web API documentation pages
Bringing BERT into modernity via both architecture changes and scaling
AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ
Powerful, open-source AI tools for digital pathology.
BiomedParse: A Foundation Model for Joint Segmentation, Detection, and Recognition of Biomedical Objects Across Nine Modalities
A bibliography and survey of the papers surrounding o1
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
POC Port of the openai-realtime-console to streamlit.
A utility to list and activate Azure Entra ID Privileged Identity Management roles from the CLI
[npj digital medicine] The official codes for "Towards Evaluating and Building Versatile Large Language Models for Medicine"