NEO Series: Native Vision-Language Models from First Principles
- agi
- encoder-free-vlm
- large-language-models
- multimodal
107,098 visible repositories in the index
697–720 of 900 · Most stars
NEO Series: Native Vision-Language Models from First Principles
Ai Resume Analyzer is a tool which parses information from a resume using natural language processing and finds the keywords, cluster them onto sectors based on their keywords. And lastly show recommendations, predictions, analytics to the applicant based on keyword matching.
Fast inference from large lauguage models via speculative decoding
Video generation from text&image, 1st-gen
Extract text from any image, video, QR Code and etc.
inferring sql queries from plain-text questions about tables
A pass extension for importing data from most existing password managers
NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.
Bulk download your favourite anime episodes from your favourite anime websites
AI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知
GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)
Small command-line program to download videos from some streaming sites.
Realtime Data From National Stock Exchange (India)
Tools for downloading and preserving wikis. We archive wikis, from Wikipedia to tiniest wikis. As of 2026, WikiTeam has preserved more than 600,000 wikis.
Implementing LLM architectures from scratch in PyTorch
Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
Flexible command line tool to create graphs from CSV data
Video Chain of Thought, Codes for ICML 2024 paper: "Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition"
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.
Official implementation of FlowHMR, a generative model for physically plausible motion capture from monocular video.
Agent skill for narrated cinematic films built entirely from code: one continuous camera over photos, maps and cards, timed to the voice. Claude Code, Codex, Cursor, Gemini CLI.
open source tools to generate mypy stubs from protobufs
A 'resilient' asynchronous MQTT driver. Recovers from WiFi and broker outages.