29,068 technical terms and definitions
attention mechanisms, transformers deep dive, cnn glue pe qk rnn wmt14, attention mechanisms & transformers deep dive, attention mechanisms transformers, mechanisms transformers deep, deep dive
Attention Mechanisms & Transformers Deep Dive Introduction & Motivation Attention Mechanisms: focus computation on relevant elements. Scaled dot-product attention, multi-head…
attention mechanisms transformers self attention parallelization, attention mechanisms, transformers self attention, bert glue gpt nlp passed qk, mechanisms transformers
Attention Mechanisms & Transformers: Self-Attention & Parallelization Introduction & Motivation Attention weights relevant input elements for each output; Transformers stack…
Attention Mechanisms in Vision Introduction & Motivation Attention Mechanisms in Vision addresses a central problem in vision processing and channel-spatial-focus prediction: how…
Attention Mechanisms for Memory in RL Introduction & Motivation Attention Mechanisms for Memory in RL addresses a central problem in reinforcement policy learning…
Attention for Multimodal Fusion Introduction & Motivation Attention for Multimodal Fusion addresses a central problem in multimodal learning and attention-focus-quality alignment…
graph neural networks
Attention Pooling Graph is graph readout methods that weight node contributions through learned attention gates. - They prioritize informative nodes and suppress irrelevant…
Attention Head Pruning via Attribution Score Ranking Introduction & Motivation Attention Head Pruning via Attribution Score Ranking addresses a central problem in explainability…
explainable ai
Attention Rollout is a visualization technique that aggregates attention weights across all transformer layers — recursively multiplying attention matrices to reveal which input…
interpretability
Attention Rollout is an interpretability method that composes attention matrices across transformer layers to estimate token influence - It provides an aggregated view of how…
Attention Rollout for Transformer Interpretability Introduction & Motivation Attention Rollout for Transformer Interpretability addresses a central problem in interpretability…
Attention Rollout for Transformer Interpretability (Extended Study) Introduction & Motivation Attention Rollout for Transformer Interpretability (Extended Study) addresses…
Attention Rollout for Transformer Interpretability (Extended Study) Introduction & Motivation Attention Rollout for Transformer Interpretability (Extended Study) addresses…
explainable ai
Attention rollout in ViT is the layer-wise aggregation method that composes attention matrices across depth to estimate end-to-end token influence on final predictions - instead…
Attention Rollout and Flow in Vision Transformers Introduction & Motivation Attention Rollout and Flow in Vision Transformers addresses a central problem in explainability…
architecture
Attention sink is the phenomenon where certain tokens attract disproportionate attention mass, reducing effective use of other context tokens - it can degrade long-context quality…
streaming llm, infinite context, initial token attention, attention pattern
Attention Sinks and StreamingLLM are the architectural phenomenon and inference technique where the first few tokens in a sequence consistently receive disproportionately high…
model compression
Attention Transfer is a feature-based knowledge distillation method where the student is trained to mimic the teacher's spatial attention maps — ensuring the student focuses on…
Attention Transfer Distillation Introduction & Motivation Attention Transfer Distillation addresses a central problem in reducing the size and cost of compression models: how…
Attention Transfer Distillation (Extended Study) Introduction & Motivation Attention Transfer Distillation (Extended Study) addresses a central problem in reducing the size…
Attention Transfer Distillation (Extended Study) Introduction & Motivation Attention Transfer Distillation (Extended Study) addresses a central problem in reducing the size…
Attention Transfer Distillation (Extended Study) Introduction & Motivation Attention Transfer Distillation (Extended Study) addresses a central problem in reducing the size…
Attention Transfer Learning Introduction & Motivation Attention Transfer Learning addresses a central problem in transfer learning and {target} adaptation: how to Apply {subject}…
ai safety
Attention visualization displays attention weights to understand what the model focuses on during prediction. What attention shows: Which input tokens/positions influence each…
interpretability
Attention Visualization is a visualization approach that renders attention weights over tokens or regions - It helps inspect interaction patterns in transformer-based models. What…
data analysis
Attention Visualization in defect detection is the visualization of which spatial regions a neural network focuses on when making classification decisions — using attention maps…
explainable ai
Attention visualization in ViT is the process of mapping attention weights to image space so engineers can inspect where each head and layer allocates focus - it is a core…
Attention Mechanism Visualization Introduction & Motivation Attention Mechanism Visualization addresses a central problem in explainability interpretation and model understanding…
attention visualization model focus prediction, attention visualization model, visualization model focus, model focus prediction, attention visualization, visualization model
Attention Visualization Model Focus Prediction with Machine Learning Introduction & Motivation Attention Visualization Model Focus Prediction with Machine Learning addresses…
Attention Weight Visualization Introduction & Motivation Attention Weight Visualization addresses a central problem in interpretability and explanation of xai predictions: how…
Attention Weight Visualization (Extended Study) Introduction & Motivation Attention Weight Visualization (Extended Study) addresses a central problem in interpretability…
Attention Weight Visualization (Extended Study) Introduction & Motivation Attention Weight Visualization (Extended Study) addresses a central problem in interpretability…
neural architecture search
AttentionNAS is neural architecture search including attention-block placement and configuration as search variables. - It discovers where and how attention modules should be…
data augmentation
Attentive CutMix is a CutMix variant that uses attention maps to guide where the cut region is placed — preferring to paste over less important regions of the target image and…
neural architecture search
AttentiveNAS is a hardware-aware once-for-all NAS method that prioritizes Pareto-critical subnetworks during training. - Training attention is focused on weak frontier regions…
attpsm, attenuated psm, phase shift mask, phase-shift mask, psm, lithography photomask
Photomask fabrication, phase-shift mask engineering, and nanoscopic defect repair constitute the foundational master-patterning technologies that enable optical projection…
attenuator temperature coefficient prediction, attenuator temperature coefficient, temperature coefficient prediction, attenuator temperature, temperature coefficient
Attenuator Temperature Coefficient Prediction with Machine Learning Introduction & Motivation Attenuator Temperature Coefficient Prediction with Machine Learning addresses…
quality & reliability
Attribute Agreement is an assessment of consistency in pass-fail or categorical inspection decisions across appraisers and references - It verifies reliability of subjective…
generative models
Attribute manipulation is the controlled editing of specific visual properties in generated or inverted images while preserving other content - it is a core function of modern…
Attributed Graph Neural Networks Introduction & Motivation Attributed Graph Neural Networks addresses a central problem in graph network representation…
spc
Attributes control charts is the SPC chart family for discrete count or proportion data such as defectives and defect counts - they are used when continuous metrology is…
rag
Attribution traces which retrieved sources support each part of a generated answer, enabling verification. Motivation: Users need to verify AI claims, trust requires transparency…
evaluation
Attribution is the mapping of specific model claims to supporting evidence sources or passages - It is a core method in modern AI fairness and evaluation execution. What Is…
evaluation
Attribution accuracy is the correctness of assigning generated statements to the proper originating evidence source, author, or document context - it ensures the system does not…
rag
Attribution in generation is the linking of generated claims to specific source evidence so users can verify where information came from - strong attribution improves transparency…
Causal Attribution and Contribution Introduction & Motivation Causal Attribution and Contribution addresses a central problem in causal inference and {target} analysis: how…
explainable ai
Attribution patching is the approximate patching method that estimates intervention effects using gradient-based attribution rather than exhaustive full patches - it accelerates…
Feature Attribution Priors for Neural Network Guidance Introduction & Motivation Feature Attribution Priors for Neural Network Guidance addresses a central problem…
auc-roc curve performance and threshold-agnostic evaluation, auc-roc curve performance, curve performance threshold-agnostic, performance threshold-agnostic evaluation, auc-roc curve
AUC-ROC Curve Performance and Threshold-Agnostic Evaluation Introduction & Motivation AUC-ROC Curve Performance and Threshold-Agnostic Evaluation addresses a central problem…
Auction Design and Mechanism Learning Introduction & Motivation Auction Design and Mechanism Learning addresses a central problem in reinforcement policy learning…
speech, asr, tts, voice, whisper, speech recognition, text to speech, voice ai
Audio and Speech AI encompasses technologies for speech recognition (ASR), text-to-speech synthesis (TTS), and voice-based AI interfaces — using deep learning models to convert…