EXPLORE / 06
Terms index
Specialized AI and software-development terms with concise explanations
Entity records
4603 records · 78/116
- 3081
Data Quality
Metrics assessing accuracy, completeness, consistency, and usability of datasets
Website pending - 3082
Document VQA
A task that combines image and text information to answer questions about document content
Website pending - 3083
Open LLM
Large language models with publicly available weights allowing free modification and use
Website pending - 3084
GAIA Benchmark
A benchmark evaluating general-purpose AI assistants' ability to solve real-world problems.
Website pending - 3085
Protein Language Model
Deep learning models using NLP techniques to predict protein structure and function
Website pending - 3086
Preference Optimization
Training method aligning model outputs with user preferences using human feedback
Website pending - 3087
TGI
A production-grade LLM inference server by Hugging Face designed for efficient deployment.
Website pending - 3088
VQA
Combines computer vision and NLP to answer questions about image content
Website pending - 3089
Multilinguality
The capability to understand and generate text across multiple natural languages
Website pending - 3090
Diffusion Transformer (DiT)
A technique applying Transformer architecture as the backbone of diffusion models
Website pending - 3091
Model Inference
The process of using a trained model to make predictions on new data
Website pending - 3092
Serverless
A cloud computing execution model where the provider dynamically manages allocation of machine resources
Website pending - 3093
Data Augmentation
Technique that generates new samples by transforming original data to improve model generalization
Website pending - 3094
Data Version Control
Technology for tracking and managing datasets similar to how Git manages code.
Website pending - 3095
Model Deployment
The process of integrating trained models into production environments for actual use
Website pending - 3096
Infini-Attention
An attention mechanism achieving linear complexity for long sequences via compressed historical states
Website pending - 3097
Data Packing
Concatenating multiple short sequences into fixed-length long sequences to reduce padding waste
Website pending - 3098
Hugging Face
A community and company hosting open-source models and datasets
Website pending - 3099
Video Encoding
Process of converting raw video into compressed formats
Website pending - 3100
Mixed Precision
Combining different floating-point precisions to optimize memory and speed
Website pending - 3101
Data Deduplication
Technology that identifies and eliminates duplicate copies of data to save storage space
Website pending - 3102
Parquet
A columnar binary file format commonly used for big data storage and analytics
Website pending - 3103
Server CPU
High-core-count, reliable central processing units designed for data centers
Website pending - 3104
Gradient Accumulation
A technique that accumulates gradients over multiple forward/backward passes to simulate larger batch sizes
Website pending - 3105
Keras
A high-level neural networks API written in Python, often used for rapid prototyping
Website pending - 3106
Parser
Program component for validating and transforming text structures, here referring to constrained decoding logic
Website pending - 3107
Structured Generation
Technique constraining LLM outputs to strictly follow specific formats like JSON or regex
Website pending - 3108
WASM
A binary instruction format enabling efficient execution of non-JavaScript code in browsers.
Website pending - 3109
Static Analysis
Method of checking source code or binaries for vulnerabilities without executing them
Website pending - 3110
Model Security
Measures protecting ML models from tampering, reverse engineering, or adversarial attacks
Website pending - 3111
Long Video QA
Question answering tasks targeting videos with longer durations and complex temporal information
Website pending - 3112
Adversarial Dataset Refinement
A method using adversarial mechanisms or strong models to generate distractors for filtering and optimizing dataset quality
Website pending - 3113
Zero-configuration
Mechanism that automates deployment and optimization without manual parameter setup.
Website pending - 3114
Sampling Strategy
Methods determining how LLMs select the next token from probability distributions.
Website pending - 3115
Multilingual LLM
Large language models capable of processing multiple natural languages
Website pending - 3116
Assistant Model
A smaller model that provides preliminary predictions or drafts during the main model's inference process.
Website pending - 3117
Open Dataset
Machine learning data collections freely accessible, usable, and modifiable by the public
Website pending - 3118
Human Preference Alignment
Training process that aligns model behavior with human values and preferences.
Website pending - 3119
Early Exit
A strategy allowing data to yield results at shallower network layers, thereby reducing computation and accelerating inference.
Website pending - 3120
Self-Attention
Mechanism allowing parallel processing and focusing on relationships between parts
Website pending