EXPLORE / 06
Terms index
Specialized AI and software-development terms with concise explanations
RECORDS
Entity records
3381 records · 56/85
- 2201
Earth Observation Model
Deep learning models specialized in processing geospatial data like satellite imagery
Website pending - 2202
Earth Observation
Technology using satellites and sensors to monitor Earth's surface and atmosphere.
Website pending - 2203
Embedding Vector
A numerical representation that maps high-dimensional discrete data into a lower-dimensional continuous space.
Website pending - 2204
Agent Evolution
Process of iteratively optimizing AI agents to adapt to new tasks or environments
Website pending - 2205
GPU Utilization
A performance metric measuring the percentage of time GPU cores are actively processing workloads.
Website pending - 2206
FIFO Scheduling
A queue mechanism where tasks are executed in the order they were submitted.
Website pending - 2207
Draft Model
A smaller auxiliary model used in speculative decoding to rapidly generate preliminary token sequences.
Website pending - 2208
Query Embedding
Technique converting search queries into vector representations.
Website pending - 2209
Vector Search
Technology finding nearest neighbors in multi-dimensional space based on semantic similarity.
Website pending - 2210
Inference Endpoint
A managed cloud interface hosting models for low-latency predictions.
Website pending - 2211
REST API
An architectural style using HTTP for standard system-to-system interaction
Website pending - 2212
DAG
A non-cyclic graphical structure used to represent data flow and dependencies.
Website pending - 2213
Model Compression
Techniques like pruning, distillation, or quantization to reduce model parameter size.
Website pending - 2214
Dense Model
A neural network architecture where all parameters are activated during every forward pass.
Website pending - 2215
4-bit Precision
An ultra-low bit quantization format where each weight is represented by only 4 bits
Website pending - 2216
Multi-Vector Embedding
Encoding text into multiple vectors instead of a single one to capture richer semantics.
Website pending - 2217
Local Inference
The process of running models for prediction on user devices rather than cloud servers.
Website pending - 2218
Kernel
A specific program unit executed in parallel on the GPU.
Website pending - 2219
Prompt
Text instructions input into an LLM to trigger specific outputs
Website pending - 2220
Late Interaction
A technique in retrieval systems that preserves fine-grained features for interaction during the matching stage.
Website pending - 2221
Late-Interaction Embeddings
Embedding technique performing fine-grained feature matching only at the late stage of retrieval.
Website pending - 2222
Masked Discrete Diffusion
A training method combining masked modeling and diffusion processes for generating discrete data.
Website pending - 2223
Bidirectional Transformer
An attention-based architecture allowing information flow in both directions within a sequence.
Website pending - 2224
Multimodal Encoder
A neural network module mapping multi-modal data into a unified vector space.
Website pending - 2225
Execution Traces
Detailed log sequences recording every step, decision, and intermediate state during agent tasks
Website pending - 2226
Agent Memory
Mechanism for agents to store, retrieve, and utilize past interaction data for long-term consistency
Website pending - 2227
ControlNet
An additional neural network structure used to precisely control diffusion model generation results.
Website pending - 2228
Workflow Engine
A software system that defines task execution order and data flow via node connections.
Website pending - 2229
Image-to-Image
Diffusion model technique generating new images based on reference images and prompts
Website pending - 2230
NCCL
NVIDIA's standard library for high-speed multi-GPU communication, commonly used for gradient synchronization in distributed training.
Website pending - 2231
Agent Consistency
The ability of an AI agent to maintain stable behavioral logic and results when executing the same task multiple times.
Website pending - 2232
GRPO
An RL algorithm for LLM alignment that reduces variance by comparing within groups
Website pending - 2233
GPU Parallel Decoding
Using GPU parallel computing capabilities to simultaneously process multiple Token-to-text conversions
Website pending - 2234
GPU Decoding
Using GPU parallel computing capabilities for text reconstruction
Website pending - 2235
Tokenizer
A tool that converts raw text into numerical sequences (Token IDs) understandable by models
Website pending - 2236
Local AI
AI models running on user devices rather than cloud servers
Website pending - 2237
MLX
A machine learning framework optimized for Apple Silicon by Apple
Website pending - 2238
Vision-Language Model (VLM)
Multimodal AI models capable of processing and understanding both image and text data simultaneously.
Website pending - 2239
RL Environment
A system that provides states to an agent, accepts actions, and returns rewards.
Website pending - 2240
GGUF
A universal file format for large language models used by llama.cpp.
Website pending