22 repository-uri
Models and frameworks that answer natural language questions about visual content.
Distinct from Visual Question Answering Evaluation: Focuses on the actual task of answering questions, whereas the sibling focuses on the evaluation of those answers
Explore 22 awesome GitHub repositories matching artificial intelligence & ml · Visual Question Answering. Refine with filters or upvote what's useful.
This project is a systematic framework for English language acquisition that applies structured workflows and cognitive strategies to build linguistic proficiency. It focuses on the construction of a linguistic knowledge base, enabling learners to master vocabulary and grammar through methodical training. The methodology is distinguished by its use of computer science concepts, such as mental-model-based learning and memory buffers, to organize progression. It emphasizes a cognitive-translation bypass to develop target language thinking, reducing mental latency by processing information direc
Uses short question-answering exercises to build rapid auditory comprehension and reaction speed.
LAVIS is a multimodal large language model framework and vision-language model library. It provides tools for training and evaluating models that integrate visual, textual, and audio data, serving as a cross-modal feature extractor and a zero-shot visual reasoning engine. The framework distinguishes itself by using frozen-backbone integration, where pretrained encoders remain non-trainable while lightweight adapter layers are updated. It employs cross-modal feature alignment to map different representations into a shared embedding space and utilizes a modular model wrapper to swap vision and
Responds to free-form natural language questions about image content using integrated multimodal models.
Moondream is a small-scale vision language model designed to reason across images to generate captions and answer natural language questions. It functions as an edge-optimized system capable of performing visual question answering, image captioning, and object detection. The project distinguishes itself through a lightweight architecture designed for local inference on embedded devices, workstations, and air-gapped hardware. It supports the execution of models on local GPUs and Apple Silicon to ensure data privacy and low latency. The system's capabilities include identifying precise object
Allows users to ask natural language questions about the contents of an image to extract context.
Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP
Predicts tokens based on combined image and text prompts to perform visual question answering.
This project is a vision language model framework and vision-to-text pipeline designed for deploying and optimizing models that process both images and text. It provides an on-device inference engine and a vision language model framework to run quantized models locally on mobile and desktop hardware accelerators. The framework features a model quantization toolkit to reduce weight precision for lower memory footprints and increased execution speed on specialized silicon. It also includes an efficient vision encoder utilizing a hybrid encoding system to compress image tokens, which reduces pro
Implements on-device models and frameworks that answer natural language questions about visual content while maintaining privacy.
CogVLM is a multimodal large language model designed to integrate visual and textual data for reasoning about images and generating natural language. It functions as a visual question answering system that analyzes image content to provide detailed descriptions or answer specific questions. The project includes a visual grounding model capable of mapping text descriptions to precise bounding box coordinates within an image. It also features a vision-based automation agent that analyzes screen captures to generate execution plans and interaction coordinates for software interfaces. The system
Analyzes images and text to answer natural language questions and provide detailed visual descriptions.
Donut is an OCR-free document transformer and end-to-end document parser. It functions as a neural network that converts unstructured document images directly into structured data or text without the use of an external optical character recognition engine. The project includes a synthetic document generator to create artificial images and ground-truth labels for training. It employs a transformer model to perform visual question answering and document image classification based on visual layout and text. The system covers several document understanding capabilities, including structured info
Produces text answers to natural language questions by analyzing the visual and spatial content of document images.
Genkit is an open-source framework for building AI-powered applications. It provides a unified interface for connecting to hundreds of generative AI models from multiple providers, enabling text, image, audio, and video generation through a single API. The framework structures multi-step AI interactions—including chat, retrieval-augmented generation, tool use, and agentic workflows—as composable, traceable flows with built-in streaming and state management. The framework distinguishes itself through a comprehensive developer toolkit that includes a command-line interface and a local developer
Transcribes speech, answers questions, or summarizes recordings from audio files.
Everywhere is a desktop AI assistant that understands whatever is on your screen and can act across applications without requiring screenshots or manual context switching. It reads structured UI data through accessibility and automation APIs to perceive the active application and visible content, then provides context-aware help, summaries, translations, and answers to natural language questions about what you are viewing. The tool distinguishes itself by combining on-screen content analysis with a multi-LLM agent platform that routes requests to providers like OpenAI, Anthropic, and local mo
Responds to natural language queries by interpreting the captured screen context and providing relevant answers or actions.
Responds to natural-language questions about the content of video frames using a vision-language model.
MMF is a modular framework for building, training, and evaluating vision-and-language models. It provides a configuration-driven experiment system where model, dataset, and training parameters are defined through composable YAML files, alongside a curated model zoo of pretrained checkpoints for state-of-the-art multimodal architectures. The framework includes a multimodal dataset loader that downloads, processes, and batches vision-and-language data, and a vision-language model trainer supporting distributed training, mixed precision, and checkpoint-based resumption. The framework distinguish
Processes visual questions by reading text in images and combining it with visual objects to predict answers.
BLIP is a vision-language model framework that combines contrastive, matching, and language modeling objectives to align images with text. Built on a multimodal encoder-decoder architecture, it supports distributed data-parallel training with cosine learning rate scheduling and sliding-window metric tracking for training stability. The framework provides capabilities for image captioning, visual question answering, and cross-modal retrieval, scoring semantic alignment between images and text through learned embeddings. It includes toolkits for fine-tuning pre-trained models on custom datasets
Trains vision-language models to answer natural language questions about visual content.
DeepSeek-VL2 este un model de limbaj mare multimodal și un sistem vision-language conceput pentru a analiza scene vizuale și a genera text descriptiv. Funcționează ca un model de visual question answering și visual grounding, capabil să extragă informații din documente și să localizeze obiecte sau regiuni specifice în imagini pe baza descrierilor textuale. Proiectul utilizează o arhitectură mixture-of-experts pentru a procesa intrări combinate de imagine și text. Este optimizat pentru inferență prin prefilling incremental, ceea ce reduce cerințele de memorie GPU pe hardware. Modelul acoperă analiza datelor multimodale și înțelegerea documentelor vizuale, inclusiv interpretarea graficelor și a layout-urilor. Efectuează inferență vizuală și grounding pentru a potrivi interogările textuale cu conținutul vizual corespondent.
Extracts information from images and documents to answer complex natural language queries.
nanoVLM este un framework de antrenare și un set de instrumente pentru modele mici de tip vision-language. Oferă un mediu bazat pe PyTorch pentru antrenarea și fine-tuning-ul modelelor, pentru a asocia intrările de imagine cu descrieri textuale și a genera răspunsuri în limbaj natural. Proiectul include un instrument de versionare a modelelor în cloud pentru salvarea și încărcarea ponderilor modelelor în repository-uri centralizate, pentru a sincroniza activele între medii. De asemenea, dispune de o suită dedicată de evaluare pentru a măsura acuratețea și fiabilitatea modelelor vision-language față de seturi de date standard. Framework-ul acoperă planificarea resurselor GPU prin măsurarea consumului VRAM și gestionează stabilitatea antrenării cu persistența stării bazată pe checkpoint-uri și gestionarea memoriei bazată pe batch-uri.
Generates natural language answers and descriptive captions based on visual content.
Youtu Agent is an open-source framework for building, running, and evaluating autonomous agents powered by large language models. It provides the core infrastructure for creating agents that follow reasoning loops, use toolkits, and coordinate with other agents to solve complex tasks, all managed through YAML-driven configuration files. The framework distinguishes itself through its support for multi-agent orchestration, where a planner agent decomposes tasks and coordinates specialized worker agents, and through its integration with the Model Context Protocol for connecting to external toolk
Answer a user's natural-language question about the content of a given image by querying a vision-language model.
Kimi-Audio is a large language model audio foundation model designed to understand audio input and generate high-fidelity speech responses in real time. It functions as a unified system encompassing a text-to-speech synthesis engine and a speech-to-text transcription tool. The project enables real-time audio conversations through a multi-modal conversation loop and chunk-wise streaming detokenization to reduce playback latency. It provides controls over speech speed, accent, and emotional tone during conversational audio generation. The system covers audio intelligence capabilities, includin
Responds to natural-language queries about the content of an audio clip, such as identifying sounds or answering factual questions.
DeepSeek-VL este un model de limbaj mare multimodal și un motor de raționament imagine-la-text. Funcționează ca un model vision-language și un sistem de răspuns vizual la întrebări care integrează percepția vizuală cu raționamentul lingvistic pentru a înțelege și descrie imaginile. Proiectul permite înțelegerea multimodală a imaginilor și analiza imaginilor de documente, procesând în mod specific capturi de ecran ale paginilor web și diagrame tehnice. Oferă capabilități pentru AI conversațional vizual, permițând utilizatorilor să interacționeze cu datele vizuale pentru a extrage perspective și a efectua raționamente complexe pe diferite tipuri de informații vizuale. Sistemul utilizează o arhitectură de tip transformer vision-language care combină un Vision Transformer pentru codificarea vizuală cu un model de limbaj mare. Utilizează reglarea fină (fine-tuning) multimodală bazată pe instrucțiuni și un strat de proiecție pentru a alinia vectorii de caracteristici vizuale cu spațiul de embedding al modelului de limbaj pentru generarea autoregresivă de text.
Provides a system for answering natural language questions about the contents and details of visual data.
Spark NLP este un toolkit pentru analiza scalabilă a textului și machine learning, construit pe framework-ul de calcul distribuit Apache Spark. Oferă un framework de machine learning multimodal și un sistem de pipeline distribuit pentru secvențierea adnotatoarelor în vederea procesării datelor lingvistice la scară largă. Biblioteca include un procesor de text de tip transformer pentru generarea de embedding-uri vectoriale contextuale și un motor de inferență dedicat pentru gestionarea modelelor de limbaj mari (LLM). Proiectul se distinge prin capacitatea sa de a procesa tipuri de date eterogene, inclusiv text, audio și imagini, într-o arhitectură unificată vision-language. Suportă capabilități avansate de AI generativ, cum ar fi prompt engineering, extracția structurată a entităților cu output JSON constrâns și inferența locală pentru a elimina latența rețelei. În plus, oferă instrumente pentru traducerea între limbi și clasificare zero-shot pe modalități de text și imagine. Framework-ul acoperă o gamă largă de capabilități, inclusiv antrenarea modelelor supervizate pentru recunoașterea entităților și analiza sentimentelor, precum și răspunsul extractiv la întrebări și sumarizarea documentelor. Integrează suport pentru baze de date vectoriale pentru căutarea de similaritate și oferă infrastructură pentru accelerare GPU și gestionarea ciclului de viață al modelelor printr-un registru centralizat. Toolkit-ul permite distribuirea modelelor și pipeline-urilor personalizate printr-un repository public și suportă implementarea modelelor prin API-uri REST.
Generates text answers to natural language questions about an input image by merging vision and text embeddings.
SmolLM is a project dedicated to the development of small language models. It focuses on training and fine-tuning compact models that maintain high performance while utilizing fewer parameters. The project emphasizes efficient AI inference and on-device text generation, aiming to enable the deployment of lightweight models on edge devices with limited memory and processing power. It utilizes synthetic data generation to produce artificial datasets that improve the reasoning and training of these AI systems. The system supports a variety of optimization and training capabilities, including we
Interprets multiple images and text in a single conversation to perform visual question answering.
ComfyUI-nunchaku is a 4-bit diffusion inference engine and a set of nodes for running low-precision quantized diffusion models within ComfyUI visual workflows. It provides a backend that reduces memory overhead and increases generation speed for transformer models. The project includes specialized tools for identity-preserving generation and an image-to-image guidance toolkit that uses depth maps and reference images. It also features a multimodal visual question answering implementation and a utility for merging multiple quantized model files into single unified files. The engine covers a b
Provides a visual question answering implementation that processes images and text using quantized multimodal models.