EXPLORE / 06
Terms index
Specialized AI and software-development terms with concise explanations
RECORDS
Entity records
3371 records · 40/85
- 1561
Vertical Adaptation
The process of adjusting model capabilities and safety policies to meet specific industry needs.
Website pending - 1562
Alignment Assessment
The process of verifying that an AI model's behavior aligns with human intent and values
Website pending - 1563
CRISPR
A gene-editing technology derived from bacterial immune systems that precisely cuts specific DNA sequences.
Website pending - 1564
Uncharacterized Protein Families
Protein groups with known sequences but whose functional mechanisms have not yet been experimentally confirmed or detailed
Website pending - 1565
Legacy System Modernization
Process of refactoring or migrating outdated IT infrastructure using new technologies to improve efficiency
Website pending - 1566
Single-Stream Architecture
Model structure where all inputs are processed uniformly in one backbone network
Website pending - 1567
Causal Masking
An attention constraint limiting the model to focus only on current and previous positions
Website pending - 1568
Mixed-Granularity Attention
A mechanism applying different mask granularities to modalities to balance accuracy and efficiency
Website pending - 1569
Long-context Disambiguation
Capability to resolve ambiguities in current utterances using historical dialogue context.
Website pending - 1570
LAAL
A metric measuring the speed of streaming speech recognition or translation, indicating average delay per word.
Website pending - 1571
Flow Matching
A generative model training method learning continuous vector fields from noise to data
Website pending - 1572
BEV Perception
Technique converting multi-view camera images into top-down 3D spatial representations
Website pending - 1573
Deterministic Environment
A simulation environment where identical states and actions always produce identical outcomes
Website pending - 1574
Feedback Loop
Mechanism where system outputs are re-inputted to optimize subsequent decisions
Website pending - 1575
Sparse MoE
A model structure that improves training and inference efficiency by dynamically routing inputs to activate only a subset of expert networks.
Website pending - 1576
Cross-Embodiment Learning
Method transferring skills across robots of different morphologies
Website pending - 1577
Image Generation Foundation Model
A general-purpose model pre-trained to support various downstream visual tasks.
Website pending - 1578
Multimodal Alignment
The process of making data from different modalities correspond in feature space.
Website pending - 1579
Cross-embodiment Training
Joint training on data from diverse robot morphologies to enable generalization across different hardware
Website pending - 1580
Heterogeneous Data Alignment
Process of mapping data from different sources or formats into a unified space
Website pending - 1581
Long-Horizon Autonomous Execution
The ability of a model to maintain goal consistency and logical coherence across multi-step, extended-duration tasks.
Website pending - 1582
Zero-shot Generalization
The ability of a model to perform tasks in unseen scenarios without prior training on them.
Website pending - 1583
Vision-Language Navigation (VLN)
Task where an agent navigates to a target location in a visual scene based on natural language instructions.
Website pending - 1584
Embodied Question Answering (EQA)
An agent navigates through physical or virtual environments to answer questions about them.
Website pending - 1585
Simultaneous Interpretation
The process or technology of translating speech in real-time while the speaker is talking
Website pending - 1586
Streaming Output
Technology that returns results chunk-by-chunk during generation rather than waiting for completion
Website pending - 1587
Continual Pre-Training (CPT)
Further unsupervised pre-training of a base model on domain-specific data
Website pending - 1588
Language World Model (LWM)
A language model trained to explicitly predict and simulate environmental state transitions
Website pending - 1589
Multi-View Geometric Consistency
Ensuring generated images or videos from different angles maintain logical unity in 3D structure and object relationships.
Website pending - 1590
Visual Reference Coding
A technique that generates corresponding frontend code directly from provided images or video screenshots.
Website pending - 1591
MMDiT
Multimodal Diffusion Transformer for image and video generation
Website pending - 1592
Emergent Abilities
New capabilities that suddenly appear when model scale increases, which smaller models lack
Website pending - 1593
Cross-Embodiment Alignment
Enabling data from robots with different morphologies to coexist and mutually enhance in a unified feature space
Website pending - 1594
Cross-Embodiment Transfer
The capability to apply policies learned on one robot morphology to another with different hardware.
Website pending - 1595
OOD Generalization
The model's ability to adapt to new scenarios or tasks not covered in the training data.
Website pending - 1596
Cross-framework Generalization
The ability of a model to maintain stable performance across different software architectures or development frameworks without significant adjustments.
Website pending - 1597
Dual-Stream Diffusion Model
Diffusion architecture processing parallel streams of modalities or features to enhance conditional control
Website pending - 1598
Visual Code Generation
Technology that automatically generates corresponding code based on visual cues from images or videos.
Website pending - 1599
Multimodal Agent
An AI system capable of processing multiple input modalities and autonomously planning task execution.
Website pending - 1600
Trajectory Prediction
Inferring a sequence of future actions or positions based on current state and goals
Website pending