EXPLORE / 06
Terms index
Specialized AI and software-development terms with concise explanations
Entity records
4588 records · 71/115
- 2801
Embodied Question Answering (EQA)
An agent navigates through physical or virtual environments to answer questions about them.
Website pending - 2802
Simultaneous Interpretation
The process or technology of translating speech in real-time while the speaker is talking
Website pending - 2803
Streaming Output
Technology that returns results chunk-by-chunk during generation rather than waiting for completion
Website pending - 2804
Continual Pre-Training (CPT)
Further unsupervised pre-training of a base model on domain-specific data
Website pending - 2805
Language World Model (LWM)
A language model trained to explicitly predict and simulate environmental state transitions
Website pending - 2806
Multi-View Geometric Consistency
Ensuring generated images or videos from different angles maintain logical unity in 3D structure and object relationships.
Website pending - 2807
Visual Reference Coding
A technique that generates corresponding frontend code directly from provided images or video screenshots.
Website pending - 2808
MMDiT
Multimodal Diffusion Transformer for image and video generation
Website pending - 2809
Emergent Abilities
New capabilities that suddenly appear when model scale increases, which smaller models lack
Website pending - 2810
Cross-Embodiment Alignment
Enabling data from robots with different morphologies to coexist and mutually enhance in a unified feature space
Website pending - 2811
Cross-Embodiment Transfer
The capability to apply policies learned on one robot morphology to another with different hardware.
Website pending - 2812
OOD Generalization
The model's ability to adapt to new scenarios or tasks not covered in the training data.
Website pending - 2813
Cross-framework Generalization
The ability of a model to maintain stable performance across different software architectures or development frameworks without significant adjustments.
Website pending - 2814
Dual-Stream Diffusion Model
Diffusion architecture processing parallel streams of modalities or features to enhance conditional control
Website pending - 2815
Visual Code Generation
Technology that automatically generates corresponding code based on visual cues from images or videos.
Website pending - 2816
Multimodal Agent
An AI system capable of processing multiple input modalities and autonomously planning task execution.
Website pending - 2817
Trajectory Prediction
Inferring a sequence of future actions or positions based on current state and goals
Website pending - 2818
Robot Embodiment
The specific physical structure, sensor configuration, and kinematic properties of a robot.
Website pending - 2819
Tensor Core
Hardware units in NVIDIA GPUs dedicated to accelerating matrix multiplication and accumulation
Website pending - 2820
Cross-Embodiment Generalization
The ability of a policy model to transfer strategies across different types of robot hardware or embodiments.
Website pending - 2821
Sparse Model
Models that utilize only a fraction of their total parameters during inference to reduce computational overhead.
Website pending - 2822
Linear Attention
Approximation methods reducing attention computational complexity from quadratic to linear.
Website pending - 2823
Gated Delta Network
A linear attention architecture variant combining gating mechanisms with delta updates.
Website pending - 2824
Multimodal Reasoning
The ability of a model to perform logical deduction using combined inputs like text and images
Website pending - 2825
S2TT
A multimodal translation task directly converting source-language speech into target-language text
Website pending - 2826
Gating Mechanism
Neural network component controlling information flow or activation via learnable parameters.
Website pending - 2827
Gated DeltaNet
An efficient sequence modeling method combining linear recurrence with gating mechanisms.
Website pending - 2828
Residual Connection
A mechanism allowing gradients to propagate directly across layers to mitigate deep network training issues
Website pending - 2829
Gated DeltaNet (GDN)
An architecture combining linear attention and gating mechanisms to efficiently compress historical information
Website pending - 2830
Semantic Adherence
The model's ability to accurately understand and execute complex logic in prompts.
Website pending - 2831
Streaming Processing
Processing data as it arrives without waiting for complete input, suitable for real-time voice interaction.
Website pending - 2832
Agentic Training
Optimizing autonomous decision-making via environment interaction and feedback loops
Website pending - 2833
Adaptive Tool Calling
Ability to dynamically decide when and how to use external tools based on task needs
Website pending - 2834
Test-Time Scaling
A strategy increasing computation during inference to improve output quality
Website pending - 2835
RTF
Ratio of processing time to audio duration, measuring inference speed
Website pending - 2836
NAR Generation
Method generating all output tokens in parallel rather than sequentially
Website pending - 2837
Forced Alignment
Determining timestamps for each word or phoneme in audio
Website pending - 2838
Blind Test
User preference voting on outputs without knowing which specific model generated them
Website pending - 2839
Streaming Response
Technology where the model transmits data to the user as it generates content, reducing time-to-first-token latency.
Website pending - 2840
System Prompt
Initial instruction text used to define the model's role, behavioral guidelines, and output style.
Website pending