Popular Terms
Community-favorited, most-read and recently-added AI terms.
⭐ Community Favorites
Most upvoted terms
Not enough votes yet.
🔥 Most Read
All-time view leaders
- 1🧮
Aggregate Table
2,431A table structure that stores summarized results derived from detailed data in order to accelerate analytical queries.
- 2➡️
Autoregressive Decoding
2,337A generation mode in which the model produces output token by token using previous outputs as context.
- 3🏥
Domain-Adaptive Fine-Tuning
2,333An approach that adapts a model to the terminology and usage style of specific domains such as law, healthcare, or finance.
- 4📈
Mean Average Precision
2,272A core evaluation metric that summarizes object detection performance across classes and threshold settings.
- 5📍
Embedding
2,260A learned dense vector representation that carries the meaning of a word, document, image, or another entity.
- 6➡️
Vector
2,253A quantity with direction and magnitude, and one of the most fundamental representations in linear algebra.
- 7⚡
Speculative Decoding
2,241A decoding approach that speeds up generation by validating proposals from a smaller fast model with a larger model.
- 8🧠
Mixture of Experts
2,239An approach in which only relevant expert subnetworks are activated for each input to achieve scale and efficiency.
- 9📉
Post-Training Quantization
2,232A quantization approach that reduces a pretrained model to lower-bit precision to gain memory and speed benefits.
- 10🛑
Abstention
2,219The ability of a model to avoid fabricating certainty and instead decline or express uncertainty when it is not confident.
- 11⚖️
AIC
2,206An information criterion that supports model selection by balancing model fit against model complexity.
- 12🔮
Action Anticipation
2,206A task that attempts to predict a future action from a partially observed video stream before it fully unfolds.
📈 Trending
Highest views-per-day in last 60 days
No new terms in last 60 days.
🆕 Recently Added
Newest published terms
- 1🖼️
Text-to-Image Generation
01.04.2026A generative modeling approach that synthesizes new images from natural language prompts.
- 2🧠
Multimodal Transformer
01.04.2026A model design that processes different data types such as text, images, audio, or video within a shared attention architecture.
- 3📏
Uncertainty Calibration
01.04.2026A quality approach aimed at making model confidence better aligned with actual correctness.
- 4🛑
Abstention
01.04.2026The ability of a model to avoid fabricating certainty and instead decline or express uncertainty when it is not confident.
- 5📌
Factuality
01.04.2026A quality dimension describing how well generated content aligns with real-world facts, source data, or verifiable truth.
- 6🌫️
Hallucination
01.04.2026The phenomenon in which a model generates fluent but unsupported or incorrect content.
- 7🏆
Reward Model
01.04.2026An auxiliary model that estimates how preferable generated outputs are and provides signals for alignment.
- 8📜
Constitutional AI
01.04.2026An alignment approach that tries to guide model behavior through explicit principle sets and normative rules.
- 9⚖️
Direct Preference Optimization
01.04.2026A simpler alignment approach that learns directly from preference pairs.
- 10🎛️
Reinforcement Learning from Human Feedback
01.04.2026An alignment approach that uses reward signals to make model outputs more consistent with human preferences.
- 11✅
Verification Loop
01.04.2026A workflow pattern that attempts to validate model output through additional checks, source review, or second-stage verification.
- 12🔗
Citation Grounding
01.04.2026An approach that improves trust by explicitly showing the source passages supporting the generated answer.