541 technical terms and definitions
visual inertial odometry, visual inertial, inertial odometry
Visual Inertial Odometry Introduction & Motivation Visual Inertial Odometry addresses a central problem in vision process control and inertial-measurement-unit-imu prediction: how…
Visual Instruction Following Introduction & Motivation Visual Instruction Following addresses a central problem in multimodal learning and instruction-accuracy-compliance…
multimodal ai
Visual Instruction Tuning is the training process that teaches Multimodal LLMs to follow human instructions — transforming valid pre-trained models (which might just describe…
vlm, llava, gpt4v, multimodal llm, vision language model, image question answering
The Vision Transformer (ViT) showed that the Transformer architecture built for language works just as well on images, and that insight is the bridge to today's multimodal models.…
quality & reliability
Visual Management is the use of visible cues that communicate process status, abnormalities, and priorities at a glance - It is a core method in modern semiconductor operational…
robotics
Visual navigation is the capability of robots to navigate through environments using visual information from cameras — enabling autonomous movement by interpreting visual scenes…
3d vision
Visual odometry (VO) is the real-time estimation of a camera or robot trajectory from sequential visual observations - it computes incremental motion between frames to track pose…
multimodal ai
Visual Prompting is an interaction technique for computer vision models — where users provide visual cues (points, boxes, scribbles, or reference images) as inputs to guide…
prompting techniques
Visual Prompting is a technique that uses visual markers or structured visual cues to direct model attention within images - It is a core method in modern LLM execution workflows.…
multimodal ai
Advanced visual question answering is the multimodal task where models answer complex questions about images by combining object recognition, relation understanding, and language…
Visual Question Answering in Dialogue Introduction & Motivation Visual Question Answering in Dialogue addresses a central problem in multimodal learning…
visual question answering, visual question, question answering
Visual Question Answering Introduction & Motivation Visual Question Answering addresses a central problem in vision process control and vqa-task-image-question-answer prediction…
visual question answering, vqa, multimodal ai
Visual Question Answering (VQA) is a multimodal AI task where a system receives an image and a natural language question about that image and must produce an accurate natural…
visual question, question answering, 1m ai coco gqa id passed, visual question answering (vqa), visual question answering, question answering (vqa), answering (vqa)
Visual Question Answering (VQA) Introduction & Motivation Visual Question Answering: answer natural language questions about images. Vision-language reasoning; multimodal…
Visual Question Generation Introduction & Motivation Visual Question Generation addresses a central problem in multimodal learning and question-relevance-answerability alignment…
Visual Rationale Generation for Visual Question Answering Introduction & Motivation Visual Rationale Generation for Visual Question Answering addresses a central problem…
multimodal ai
Visual reasoning is the process of drawing logical conclusions from visual inputs by analyzing objects, attributes, relations, and scene context - it extends computer vision…
evaluation
Visual Reasoning Benchmarks are standardized datasets designed to evaluate a model's ability to think, logic, and reason about visual inputs — moving beyond simple object…
Visual Relationship Detection Introduction & Motivation Visual Relationship Detection addresses a central problem in multimodal learning and relationship-accuracy-specificity…
Visual Relationship Reasoning Introduction & Motivation Visual Relationship Reasoning addresses a central problem in multimodal learning and relationship-inference-accuracy…
Visual-Semantic Embedding Quality Introduction & Motivation Visual-Semantic Embedding Quality addresses a central problem in multimodal learning…
Visual-Semantic Embedding Space Introduction & Motivation Visual-Semantic Embedding Space addresses a central problem in multimodal learning and embedding-alignment-preservation…
Visual Semantic Role Labeling Introduction & Motivation Visual Semantic Role Labeling addresses a central problem in multimodal learning and role-labeling-accuracy alignment: how…
robotics
Visual SLAM (vSLAM) is the SLAM specialization that relies primarily on camera imagery to estimate trajectory and build maps - it spans monocular, stereo, and RGB-D setups…
visual slam camera based, visual slam camera, slam camera based, visual slam, slam camera, camera based
Visual SLAM Camera Based Introduction & Motivation Visual SLAM Camera Based addresses a central problem in robotics process control and simultaneous-localization-mapping…
Visual-to-Sound Generation Introduction & Motivation Visual-to-Sound Generation addresses a central problem in multimodal learning and sound-plausibility-quality alignment: how…
audio & speech
Visual speech recognition is speech recognition using visual facial motion cues, often combined with or independent of audio - Temporal visual features from lips and face are…
audio & speech
Visual Speech Synthesis is generation of photorealistic talking-face video conditioned on speech audio. - It maps speech content and timing to synchronized facial articulation…
multimodal ai
Visual Storytelling is the generative multimodal task where an AI creates a coherent, multi-sentence narrative from a sequence of images — moving beyond literal visual description…
multimodal ai
Visual storytelling is the multimodal generation task that creates narrative stories from one or more images by combining observation with temporal and emotional context - it…
quality & reliability
Visual Work Instruction is a work-instruction format that emphasizes images, diagrams, and cues to improve execution clarity - It is a core method in modern semiconductor…
vision transformer vit, patch transformer
The Vision Transformer (ViT) showed that the Transformer architecture built for language works just as well on images, and that insight is the bridge to today's multimodal models.…
computer vision
ViT-22B is a 22 billion parameter Vision Transformer that represents the largest dense vision model ever trained — demonstrating that extreme scaling of vision transformers…
computer vision
ViT feature maps are the spatial token representations extracted from intermediate transformer blocks that encode texture, part-level cues, and semantic layout - they provide…
computer vision
ViT-Giant is a billion-parameter-scale Vision Transformer model that demonstrates massive parameter scaling can achieve state-of-the-art visual recognition — pushing…
structured prediction
Viterbi algorithm is a dynamic-programming method that finds the highest-scoring path in sequence models - Trellis recursion computes optimal state paths efficiently under Markov…
vits, audio & speech
VITS is an end-to-end text-to-speech model that combines variational inference, adversarial learning, and normalizing flows - Latent alignment and waveform generation are trained…
video understanding
ViViT is the video vision transformer family that tokenizes clips into spatiotemporal tubelets and applies transformer attention over space and time - it extends ViT principles…
V-JEPA Video Joint-Embedding Predictive Architecture Introduction & Motivation V-JEPA Video Joint-Embedding Predictive Architecture addresses a central problem in selfsupervised…
pic-mcc plasma modeling, eedf energy distribution, ccp icp plasma kinetic transport, boltzmann transport pde, plasma sheath collision kinetics
Vlasov–Maxwell–Boltzmann Kinetic Transport Dynamics and PIC-MCC Simulation in Semiconductor Etch/CVD Plasma Reactors Executive Summary The Vlasov–Boltzmann kinetic equation…
vliw instruction packing efficiency and scheduling, vliw instruction packing, instruction packing efficiency, packing efficiency scheduling, vliw instruction, instruction packing
VLIW Instruction Packing Efficiency and Scheduling Introduction & Motivation VLIW Instruction Packing Efficiency and Scheduling addresses a central problem in isa process control…
tgi, inference engine
LLM Inference Engines: vLLM and TGI vLLM What is vLLM? High-throughput LLM serving engine with PagedAttention for efficient KV cache management. Key Features Feature Description…
deployment
PagedAttention is a memory-management technique for LLM inference that applies operating-system-style virtual-memory paging to the attention key-value (KV) cache. Introduced…
inference
vLLM serving system is the high-performance open-source LLM inference runtime designed for efficient serving through paged attention, continuous batching, and optimized memory…
vm vs containerization, vm vs, vs containerization
VM vs Containerization Introduction & Motivation VM vs Containerization addresses a central problem in cloud process control and overhead-memory-footprint prediction: how…
vmi, supply chain & logistics
VMI is vendor-managed inventory where suppliers monitor and replenish customer stock levels - Suppliers use consumption and forecast data to plan replenishment within agreed…
vna, signal & power integrity
VNA measurement is vector network analyzer characterization of multiport RF and high-speed channels - VNAs sweep frequency to capture magnitude and phase response for insertion…
voc, environmental & sustainability
VOC Abatement is control and reduction of volatile organic compound emissions from industrial processes - It is required for air-permit compliance and worker-environment…
nlp vocabulary, model vocabulary, vocabulary design, subword vocabulary, bpe vocabulary, vocabulary training, token vocabulary, embedding matrix, vocabulary size tradeoff
A vocabulary is not a list of words; it is a compression codebook that determines how many tokens a model needs to represent any given text, and that token count directly controls…
nlp
Vocabulary size defines the number of unique tokens a model can represent, balancing coverage against efficiency. Trade-offs: Smaller vocabulary (8K-32K): Longer sequences (more…