Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"
- diffusion-models
- efficient-inference
- high-resolution
- image-generation
Repository Index
56,139 visible repositories in the index
697–720 of 915 · Most stars
This repo is the official implementation of "F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation".
Continuity for the agent itself. An MCP server that gives an AI agent a memory of its own, written in its own words and kept on your machine, so it wakes as itself every session.
A dual-agent framework leveraging left-brain logic (structured coding, syntax validation, debugging) and right-brain intuition (macro architecture, creative patterns, UX flows). It splits cognitive loads to boost LLM development efficiency, preventing hallucination while maximizing system scalability.
Dreamento (DReam ENgenieering TOolbox): a Python-based software for dream engineering while monitoring/analyzing real-time EEG data.
- automatic-sleep-analysis
- dream
- eeg-analysis
- lucid-dreaming
GasPot originally released at Blackhat 2015 - Updated for the same stuff 2026
Accurate and efficient spot detection for microscopy data
Hierarchical Attentive Recurrent Tracking
- neural-nets
- object-tracking
- attention-mechanism
- rnn
A dataset of 2D imagery, 3D point cloud data, and 3D vehicle bounding box labels all generated using the Grand Theft Auto 5 game engine.
BIA Bob is a Jupyter+LLM-based assistant for interacting with image data and for working on Bio-image Analysis tasks.
Auto-updated tech internships in India from 160+ company career pages, with Telegram alerts. Serverless on GitHub Actions.
- github-actions
- india
- internships
- job-board
Python library for handling audio datasets.
- audio
- speech-recognition
- corpus-tools
- dataset-manager
Python histogram library - histograms as updateable, fully semantic objects with visualization tools. [P]ython [HYST]ograms.
- histogram
- plotting
- python
- visualization
TranslatedTurn your NetEase Cloud Music playlists and listening rankings into a deep self-portrait — a Skill for local data collection and AI profile analysis, supporting Windows / macOS
- agent-skills
- ai-tools
- music-data
- netease-cloud-music
ENIGMA HALFpipe is a user-friendly software that facilitates reproducible analysis of fMRI data
- neuroimaging
- reproducibility
- pipeline
- meta-analysis
The power of Chart.js with Python
- python
- jupyter-notebook
- jupyter
- ipywidgets
Generate the smallest test dataset that provably catches broken data-mapping rules in ETL pipelines.
TranslatedMcDonald's meal pairing decision Skill | Computes the top three optimal choices out of 1881 combinations, and tells you why they are not the others. Calorie control, dietary restrictions, and max-min fair allocation for group orders; the LLM does not take part in calculating money, and every number is traceable.
A Macau food recommendation Agent built on Thompson Sampling + StackedPareto weight fusion, with a full evaluation pipeline (5-fold CV, bootstrap CIs, stress tests) on 5,000 simulated users and 100k interactions. Competition entry for the QwenPaw AI Developer Challenge.
Python script to monitor Oracle Databases
- python
- monitoring
- oracle-database
- zabbix
Field-level assurance for data pipelines: mapping-driven source-to-target validation, fault-injection test scoring and explainable risk-adaptive test prioritization.
TranslatedA conversational AI Skill based on McDonald's official MCP, supporting meal recommendations, store price comparison, coupon lookup, nutrition calculation, and exploration records, and generating voxel-style shareable images through Python.
- ai-agent
- ai-skill
- coupons
- data-visualization
A CLI tool to reduce the friction between data scientists by reducing git conflicts removing notebook metadata and gracefully resolving git conflicts.
- cli
- jupyter-notebook
- helper-tool
- pydantic
Python/FastAPI application for monitoring Brazilian public-sector IT opportunities, with automated data collection, job filters, and official-source tracking.