[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

An Indoor Air Quality Monitor Powered by ESP32, SCD40, and SEN54

get the lemmas and conjugation of verbs in lithuanian

From-scratch implementation of OpenAI's GPT-OSS model in Python. No Torch, No GPUs.

Contexts Optical Compression

map all words to single-syllable version

Lietuvos partijų populiarumo reitingai

Projects motion of pixels to a voxel

Waldo Vision | Cheat detection

Various mostly Lithuanian language related things

Open source image background removal model

Real time visual saliency detection ✨

revolutionary new technology that turns any image into obama

Portable file server with accelerated resumable uploads, dedup, WebDAV, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file, no deps

[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.

A comprehensive list of document parsers, covering PDF-to-text conversion and layout extraction. Each tested for support of tables, equations, handwriting, two-column layouts, and multi-column layo…

Official code for the paper: Depth Anything At Any Condition

[NeurIPS 2025] Official implementation of "XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation".

Image to ascii converter

OmniGen2: Exploration to Advanced Multimodal Generation.

Track and display mouse, keyboard and gamepad information for different applications.

Official implementation of "Text-Aware Image Restoration with Diffusion Models"

Implemeting Meta AI's VGGT as a FiftyOne Remote Zoo Model

Tiny data-over-sound library

Modified version of Chatterbox that accepts text files as input and no character restrictions. I use it to make audiobooks, especially for my kids.

Official PyTorch Implementation of Ctrl-Crash 💥

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos