EXPLORE / 06
Terms index
Specialized AI and software-development terms with concise explanations
Entity records
4517 records · 82/113
- 3241
Real-time Rendering
Technology generating images quickly enough to support immediate user interaction.
Website pending - 3242
Visual Document Retrieval
Retrieving relevant pages or snippets directly from document images.
Website pending - 3243
Reranker
A model that refines the ranking of retrieved candidates to improve precision.
Website pending - 3244
Verifiable Rewards
Algorithmic or rule-based automatic correctness signals for RL feedback
Website pending - 3245
Skill
Pre-defined reusable capability modules or instruction sets for AI agents.
Website pending - 3246
Code Agent
AI systems capable of autonomously writing, debugging, and executing programming tasks.
Website pending - 3247
DAPO
An improved policy optimization algorithm for LLMs designed to enhance training stability and efficiency.
Website pending - 3248
RLVR
Reinforcement learning method that uses rules or external tools to automatically verify output correctness for reward signals.
Website pending - 3249
Forward Pass
The process of computing outputs from inputs in a neural network
Website pending - 3250
Content Script
JavaScript files injected into web pages to manipulate the DOM and execute specific logic.
Website pending - 3251
Service Worker
A script that runs in the background of a web application, handling asynchronous tasks independently.
Website pending - 3252
Benchmark Overfitting
Phenomenon where models optimize specifically for test sets, degrading real-world performance
Website pending - 3253
Serverless Inference
Model serving architecture that auto-scales on demand without managing underlying infrastructure.
Website pending - 3254
Benchmaxxing
Over-optimizing models specifically for test datasets to boost scores rather than improving general capability.
Website pending - 3255
Policy Ratio
Ratio of probabilities under new and old policies for the same action, central to PPO updates
Website pending - 3256
Logprobs
Natural logarithm of probabilities for each output token, used for loss calculation and policy gradients
Website pending - 3257
Train-Inference Mismatch
Discrepancy between probability distributions used in training and actual sampling distributions in inference
Website pending - 3258
ModernBERT
A new generation bidirectional Transformer architecture optimized for long context and efficiency
Website pending - 3259
MTEB Benchmark
A standardized benchmark suite evaluating text embedding models across various downstream tasks like retrieval and classification.
Website pending - 3260
Matryoshka Representation Learning
A technique allowing users to truncate embedding dimensions to trade off accuracy for computational efficiency within a single model.
Website pending - 3261
Inference Backend
Underlying software engine responsible for executing model computations to generate predictions
Website pending - 3262
CrossEncoder
Neural network structure that processes query and document together to output a relevance score.
Website pending - 3263
Reranking
Technique that refines initial retrieval results by scoring them for optimal final ordering.
Website pending - 3264
Delta Update
An optimization strategy that transmits only changed data parts rather than the full dataset.
Website pending - 3265
Harness
The infrastructure layer responsible for managing model execution, tool invocation, and state maintenance.
Website pending - 3266
Parameter Delta
The difference in model weights between two consecutive optimization steps.
Website pending - 3267
Weight Synchronization
The process of transmitting updated model parameters from the training side to the inference side.
Website pending - 3268
Asynchronous RL
An RL paradigm where trainer and inference engine work in parallel without strict synchronous waiting.
Website pending - 3269
Cascaded Pipeline
An architecture chaining multiple independent models sequentially to complete complex tasks.
Website pending - 3270
Scaffold
Structured code or toolsets used to support and simplify complex processes in software development or model training.
Website pending - 3271
Computer Use Agent
An agent that controls a computer via mouse and keyboard based on visual interface recognition, mimicking human operation.
Website pending - 3272
Rejection Sampling
A data generation technique that filters candidate samples meeting specific criteria
Website pending - 3273
Direct Preference Optimization (DPO)
A method to optimize language models directly using preference data without training a separate reward model
Website pending - 3274
Reasoning Traces
Records of the logical steps a model takes from input to final conclusion, used to explain decision-making processes.
Website pending - 3275
RFC
A document mechanism used to solicit community feedback on technical designs or standards
Website pending - 3276
Gaussian Splatting
A 3D scene representation technique for real-time radiance field rendering
Website pending - 3277
CI
Automated build and test practice for code changes
Website pending - 3278
Operator Fusion
Combining multiple consecutive operations into a single kernel to reduce memory access and launch overhead
Website pending - 3279
Environment Interface
Standardized data formats and control protocols defining how agents interact with external environments.
Website pending - 3280
Resource Discovery
The process of automatically identifying, locating, and retrieving available services or components
Website pending