🎥 Extract insights effortlessly from multimedia content using Vidlytics, a Python package that simplifies understanding with concise summaries.

A tool for detecting hallucinations in domain-specific LLM outputs. It enables domain data import, model training, and API deployment, providing reliability assessment and evidence for evaluating LLM implementation performance.

Asto is a small but powerfull DSL designed to help CLI engineers organize, describe, and document command-line tools - clearly and efficiently.

Hova is a Domain-Specific Language designed to describe and organize entities in a clean, readable and structured way. It lets you define your data once and automatically export it as JSON, YAML or TOML.

Source code for "ExpGuard: LLM Content Moderation in Specialized Domains", ICLR 2026

vidlytics extracts text from multimedia, generates domain-specific summaries & insights from prompts, enabling quick understanding without direct video processing.

Extracts key information from unstructured news headlines into structured domain-specific summaries for business, logistics, and transportation sectors.

Comprehensive benchmarking framework for evaluating 13+ embedding models on multi-turn conversational retrieval with advanced metrics, automated visualizations, and flexible data pipeline supporting multiple formats

Dhaad (ضَاد) is the world's first **adaptive programming language** that intelligently orchestrates execution while preserving semantic intent. Named after the distinctive Arabic letter "Ḍād" that defines linguistic depth, Dhaad transforms programming from static computation to **dynamic, context-aware outcome commanding** across all computational

A Python Tool for Selecting Domain-Specific (Contextually Similar Data) for Machine Translation

도메인에 특화된 질의응답 QA 시스템을 자동 생성하는 웹 프레임워크 QA Maker 개발

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

A collection of easily digestible introductions to foundational and state-of-the-art LLM domains

Implementation of TSDS: Data Selection for Task-Specific Model Finetuning. An optimal-transport framework for selecting domain-specific and task-specific training data to improve LLM finetuning and instruction tuning.

Sparky is an interactive assistant designed to help users identify and understand various hardware and electronic components.

[EMNLP'24] This repo is official implementation for the paper "Unsupervised Named Entity Disambiguation for Low Resource Domains"

CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language Model

Repository for the paper "Exploring Image Augmentations for Siamese Representation Learning with Chest X-Rays"

📶 NetBERT: a domain-specific BERT model for computer networking.

Voila is a domain-specific language launched through CLI tool for operating with files and directories in massive amounts in a fast & reliable way.