EXPLORE / 06
Terms index
Specialized AI and software-development terms with concise explanations
Entity records
4626 records · 84/116
- 3321
VRAM Optimization
Techniques to reduce video memory usage during deep learning training
Website pending - 3322
LLM Fine-tuning
Further training a pre-trained LLM on specific data to adapt it for downstream tasks
Website pending - 3323
GGML
A lightweight C library for tensor operations in machine learning
Website pending - 3324
On-Device Optimization
Techniques like quantization and pruning to enable efficient local execution of large models
Website pending - 3325
Asynchronous Training
A training mode that decouples data generation from model updates to overlap computation wait times.
Website pending - 3326
DeepSpeed
Microsoft's open-source library for large model training optimization and distributed parallelism.
Website pending - 3327
FlashAttention
An IO-aware efficient attention algorithm that significantly reduces memory usage.
Website pending - 3328
Sequence Parallelism
A distributed strategy that splits input sequences across multiple devices for parallel computation.
Website pending - 3329
Rollout
The process of generating trajectory data by interacting with the environment using the current policy during RL training.
Website pending - 3330
Group Relative Policy Optimization
An RL algorithm variant that estimates advantages via intra-group relative comparisons without requiring a value network.
Website pending - 3331
Optimizer State
Internal variables recording gradient momentum and other auxiliary info in DL training
Website pending - 3332
Checkpoint
A snapshot of model parameters and optimizer states saved during training
Website pending - 3333
Autoregressive Generation
A generation method that predicts the next element or action step-by-step based on preceding sequences.
Website pending - 3334
VLA
End-to-end multimodal models combining vision, language understanding, and physical action control.
Website pending - 3335
Spearman Correlation
A non-parametric measure of rank correlation that assesses how well the relationship between two variables can be described using a monotonic function.
Website pending - 3336
End-to-End Evaluation
Comprehensive testing method assessing performance and quality from input to final output.
Website pending - 3337
llama.cpp
A C++ library for efficiently running large language models on CPUs.
Website pending - 3338
Inference Providers
A service layer that calls various LLM backends through a unified interface.
Website pending - 3339
Codon Optimization
The process of modifying synonymous codons in a gene sequence to improve expression efficiency or stability.
Website pending - 3340
Perplexity
A metric measuring how well a probability model predicts a sample; lower values indicate better prediction accuracy.
Website pending - 3341
API Stability
A commitment that software interfaces remain backward compatible and unchanged
Website pending - 3342
Hybrid Attention Mask
A masking strategy combining different attention mechanism patterns to optimize context understanding for specific tasks
Website pending - 3343
Open-Vocabulary Segmentation
Identifying and segmenting objects based on arbitrary natural language descriptions, not limited to predefined classes
Website pending - 3344
SSE
An HTTP-based unidirectional communication mechanism often used for real-time updates
Website pending - 3345
Open-Vocabulary
Ability to recognize categories not present in training data
Website pending - 3346
Early Fusion
Combining different modalities at the input stage before processing
Website pending - 3347
Tensor
Multi-dimensional array data structure, basic unit of deep learning computation
Website pending - 3348
Pickle
Python object serialization module with arbitrary code execution risks
Website pending - 3349
Reranker Model
A model that re-scores initial retrieval results to improve relevance ranking.
Website pending - 3350
Real-time Rendering
Technology generating images quickly enough to support immediate user interaction.
Website pending - 3351
Visual Document Retrieval
Retrieving relevant pages or snippets directly from document images.
Website pending - 3352
Reranker
A model that refines the ranking of retrieved candidates to improve precision.
Website pending - 3353
Verifiable Rewards
Algorithmic or rule-based automatic correctness signals for RL feedback
Website pending - 3354
Skill
Pre-defined reusable capability modules or instruction sets for AI agents.
Website pending - 3355
Code Agent
AI systems capable of autonomously writing, debugging, and executing programming tasks.
Website pending - 3356
DAPO
An improved policy optimization algorithm for LLMs designed to enhance training stability and efficiency.
Website pending - 3357
RLVR
Reinforcement learning method that uses rules or external tools to automatically verify output correctness for reward signals.
Website pending - 3358
Forward Pass
The process of computing outputs from inputs in a neural network
Website pending - 3359
Content Script
JavaScript files injected into web pages to manipulate the DOM and execute specific logic.
Website pending - 3360
Service Worker
A script that runs in the background of a web application, handling asynchronous tasks independently.
Website pending