toolformer
ai agent
Toolformer is the self-supervised framework developed by Meta AI that teaches language models to autonomously decide when and how to use external tools — pioneering the concept…
1,520 technical terms and definitions
ai agent
Toolformer is the self-supervised framework developed by Meta AI that teaches language models to autonomously decide when and how to use external tools — pioneering the concept…
moe
Top-2 expert routing is the MoE policy that sends each token to the two highest-scoring experts and combines their outputs with learned weights - it improves routing smoothness…
metrology
Top-down SEM uses a scanning electron microscope to examine a patterned surface in plan view, approximately along the surface normal. It is particularly useful for lateral…
moe
Top-K Expert Selection is the gating mechanism in Mixture-of-Experts (MoE) transformer architectures that routes each input token to only the K highest-scoring expert networks…
optimization
Top-K Gradient Sparsification is the most common gradient sparsification strategy — selecting only the K gradient components with the largest magnitude for communication, where K…
rag
Top-k retrieval is the selection of the k highest-ranked retrieved candidates to pass into downstream reranking or generation - choosing k controls the recall-noise tradeoff…
architecture
Top-k Routing is routing strategy that sends each token to the highest-scoring k experts - It is a core method in modern semiconductor AI serving and inference-optimization…
truncate, random
Top-k sampling is a text generation strategy that restricts token selection to the k highest-probability tokens from the model's output distribution, then samples randomly among…
inference
When a language model finishes a forward pass it does not hand you a word. It hands you a probability distribution over its entire vocabulary, and *decoding* is the policy you use…
text generation
When a language model finishes a forward pass it does not hand you a word. It hands you a probability distribution over its entire vocabulary, and *decoding* is the policy you use…
packaging
Top mark is the identification text or symbols placed on package top surface to encode product, traceability, and handling information - it is the primary human-readable…
text generation
Top-p sampling, also called nucleus sampling, picks the next token from the smallest set of candidates whose cumulative probability reaches a threshold p — typically 0.9 to 0.95…
top-p sampling, nucleus, inference
When a language model finishes a forward pass it does not hand you a word. It hands you a probability distribution over its entire vocabulary, and *decoding* is the policy you use…
topcoat outgassing prediction, topcoat outgassing, outgassing prediction
Topcoat Outgassing Prediction with Machine Learning Introduction & Motivation Topcoat Outgassing Prediction with Machine Learning addresses a central problem in immersion…
scope, boundary
Topic Restriction (AI Guardrails) is the design pattern for confining AI assistants to a defined subject domain — ensuring a banking bot discusses only financial topics, a medical…
graph neural networks
TopK Pooling is a graph neural network pooling method that learns a scalar importance score for each node and retains only the top-k highest-scoring nodes along with their induced…
graph neural networks
TopK pooling is a graph coarsening method that retains the top-ranked nodes according to learned projection scores - Projection scores rank nodes and a fixed fraction is selected…
insulator, semiconductor, edge, states, Dirac, fermions, quantum
Topological Insulator Semiconductor is a new class of materials with insulating bulk but conducting edge/surface states protected by time-reversal symmetry, enabling robust…
topological error correction methods, topological error correction, error correction methods, topological error, error correction, correction methods
Topological Error Correction Methods Introduction & Motivation Topological Error Correction Methods addresses a central problem in quantum-error-correction process control…
topological insulator thin film uniformity prediction, topological insulator thin, insulator thin film, thin film uniformity, film uniformity prediction
Topological Insulator Thin Film Uniformity Prediction with Machine Learning Introduction & Motivation Topological Insulator Thin Film Uniformity Prediction with Machine Learning…
topological photonics for computing, topological photonics computing, topological photonics, photonics computing
Topological Photonics for Computing Introduction & Motivation Topological Photonics for Computing addresses a central problem in topological-photonics process control…
topological quantum computing, topological quantum, quantum computing
Topological Quantum Computing Introduction & Motivation Topological Quantum Computing addresses a central problem in quantum-computing process control…
topological quantum computing, topological quantum, quantum computing
Topological Quantum Computing Introduction & Motivation Topological Quantum Computing addresses a central problem in quantum process control and topological-qubit-anyons…
Majorana Nanowires, Topological Phases, and Non-Abelian Braiding 1. Topological-qubit objective Topological quantum computing seeks degrees of freedom stored nonlocally so local…
quantum ai
Topological Qubits represent the most ambitious, theoretically elegant, and intensely difficult hardware architecture in quantum computing (championed primarily by Microsoft)…
topological sort dag, topological sort, sort dag
Topological Sort DAG Introduction & Motivation Topological Sort DAG addresses a central problem in algorithms process control and ordering-validity-guarantee prediction: how…
topological sort directed acyclic prediction, topological sort directed, sort directed acyclic, directed acyclic prediction, topological sort, sort directed, directed acyclic
Topological Sort Directed Acyclic Prediction with Machine Learning Introduction & Motivation Topological Sort Directed Acyclic Prediction with Machine Learning addresses a central…
Topological Superconducting Nanowires: BdG Spectra, Majorana Zero Modes, and Zero-Bias Conductance 1. Introduction: Topological Quantum Computing and Majorana Fermions Topological…
hierarchical allreduce, ring tree hybrid allreduce, network aware collective, cluster allreduce tuning
Topology-Aware AllReduce is the collective communication strategy that maps reduction traffic to physical interconnect hierarchy. What It Covers Core concept: combines intra node…
distributed training
Topology-aware training is the distributed training placement strategy that maps communication-heavy ranks to favorable physical network paths - it minimizes hop count…
Topology: Point-Set Foundations, Compactness, Connectedness, and the Fundamental Group Topology studies properties of spaces that are preserved under continuous deformations…
engineering
Topology optimization is a computational method that finds the optimal material distribution within a design space — mathematically determining where to place material and where…
torchcompile, torch.compile, torch inductor, torchinductor, pytorch compiler, torchdynamo, torch dynamo, aot autograd, aotautograd, primtorch, graph break, pytorch 2.0, pytorch 2, pytorch performance optimization
`torch.compile` is the just-in-time graph compiler that PyTorch 2.0 wraps around an ordinary eager model to make it run as fused, optimized kernels: you write `model =…
jit, trace
TorchScript is PyTorch's intermediate representation that compiles Python models into optimized computation graphs, enabling deployment without Python runtime and improving…
infrastructure
TorchScript is PyTorch's intermediate representation (IR) system for converting dynamic Python models into serializable, optimizable, static graphs that can run in C++ production…
model optimization
TorchScript is a serialized intermediate representation of PyTorch models for optimized and portable execution - It enables deployment outside full Python training environments.…
pytorch serving, model deployment
TorchServe is a production-ready serving framework for PyTorch models — deploying trained models as REST/gRPC services with auto-scaling, batching, and version management…
toric code topological, toric code, code topological
Toric Code Topological Introduction & Motivation Toric Code Topological addresses a central problem in quantum process control and toric-code-2d-lattice-periodic prediction: how…
toroidal inductor magnetic saturation prediction, toroidal inductor magnetic, inductor magnetic saturation, magnetic saturation prediction, toroidal inductor
Toroidal Inductor Magnetic Saturation Prediction with Machine Learning Introduction & Motivation Toroidal Inductor Magnetic Saturation Prediction with Machine Learning addresses…
torus topology advantages, torus topology, topology advantages
Torus Topology Advantages Introduction & Motivation Torus Topology Advantages addresses a central problem in chip-architecture process control and hop-distance-diameter…
tco, ai tco, inference cost, ai infrastructure cost, hidden technical debt, model retraining cost, llm operating cost
Total cost of ownership (TCO) is the full cost of acquiring, deploying, operating, and eventually retiring a system over its life, as opposed to its purchase price or its most…
supply chain & logistics
Total Cost Ownership is a procurement evaluation model including acquisition, operation, risk, and lifecycle costs - It avoids narrow price decisions that increase long-term total…
total ionizing dose screening prediction, total ionizing dose, ionizing dose screening, dose screening prediction, total ionizing, ionizing dose, dose screening, screening prediction
Total Ionizing Dose Screening Prediction with Machine Learning Introduction & Motivation Total Ionizing Dose Screening Prediction with Machine Learning addresses a central problem…
signal & power integrity
Total Jitter is the combined timing uncertainty from deterministic and random jitter components at a BER target - It defines effective eye-closure and timing margin in serial link…
total power consumption prediction, total power consumption, power consumption prediction, total power, power consumption, consumption prediction
Total Power Consumption Prediction with Machine Learning Introduction & Motivation Total Power Consumption Prediction with Machine Learning addresses a central problem in total…
tpm, production
Total productive maintenance is the plant-wide maintenance system that integrates operators, technicians, and management to maximize equipment effectiveness - it aims for high…
txrf wafer surface contamination, direct txrf, vpd txrf, vapor phase decomposition txrf, metal contamination wafer
Spectroscopic ellipsometry and inline optical wafer metrology constitute the non-destructive physical measurement and defect detection disciplines that govern yield control across…
ttv, metrology
Spectroscopic ellipsometry and inline optical wafer metrology constitute the non-destructive physical measurement and defect detection disciplines that govern yield control across…
bridgeless power factor correction, GaN PFC topology
A totem-pole PFC converter is the bridgeless AC-to-DC front end that replaced the diode-bridge-plus-boost topology in high-efficiency power supplies by putting two fast switches…
touch controller sensitivity drift prediction, touch controller sensitivity, controller sensitivity drift, sensitivity drift prediction, touch controller, sensitivity drift
Touch Controller Sensitivity Drift Prediction with Machine Learning Introduction & Motivation Touch Controller Sensitivity Drift Prediction with Machine Learning addresses…