Radu-Sebastian Amarie eek
- Bucharest, Romania
-
02:37
(UTC +03:00) - https://starzero.ai
- https://huggingface.co/eek
- @raduamarie
- in/raduamarie
Highlights
Stars
Python SDK for ProgramAsWeights β compile natural language specs into neural programs that run locally
DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
Warp is an agentic development environment, born out of the terminal.
Skills for Real Engineers. Straight from my .agents directory.
PyTorch code and models for VJEPA2 self-supervised learning from video.
SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles
OmniShotCut is a sensitive and more informative SoTA on Shot Boundary Detection task.
The headless browser for AI agents and web scraping
Fast, accurate & comprehensive text measurement & layout
TIPSv2 (CVPR'26) and TIPS (ICLR'25)
Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.
The agent that grows with you
UniFace: A Unified Face Analysis Library for Python | Detection, alignment, landmarks, face-mesh, recognition, parsing, gaze, attributes and anti-spoofing under one API.
A lightweight library for normalizing speech transcripts before computing WER
Client side vector search using EmbeddingGemma with Web AI (LiteRT.js, TensorFlow.js, and Transformers.js)
Unalome Agent Firewall is a free, open-source desktop app that gives you complete visibility into what your AI agents are doing on your machine β in plain language anyone can understand.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
[CVPR 2026π₯] π§βπ¨ OmniLottie, an open-sourced multi-modal instructed vector animation generator that produces Lottie JSONs.
EdegQuake π High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation
The official repo for "Vidi: Large Multimodal Models for Video Understanding and Editing"
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how tβ¦
Check if an email address exists without sending any email, written in Rust. Comes with a βοΈ HTTP backend.
π₯ [ICCV 2025 Highlight] Official open-source repo for LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages