Issue Triaging
code ai
Issue Triaging is the code AI task of automatically classifying, prioritizing, assigning, and de-duplicating bug reports and feature requests in software issue trackers — enabling…
15,418 technical terms and definitions
code ai
Issue Triaging is the code AI task of automatically classifying, prioritizing, assigning, and de-duplicating bug reports and feature requests in software issue trackers — enabling…
ai safety
Iterated Amplification is an AI alignment technique that bootstraps human oversight by iteratively using AI assistance to solve increasingly complex evaluation tasks — starting…
ai safety
Iterated Amplification is an alignment approach where hard tasks are recursively decomposed into easier subproblems humans can supervise - It is a core method in modern AI safety…
iterated local search, iterated local, local search
Iterated Local Search Introduction & Motivation Iterated Local Search addresses a central problem in ml process control and solution-quality-vs-time prediction: how to Predict…
batch, mini-batch training
Training Terminology: Epochs, Batches, Iterations Definitions Batch A subset of training examples processed together: Iteration (Step) One forward + backward pass on a single…
model training
An iteration or step is one update of model weights after processing one batch, the atomic unit of training. Definition: Forward pass on batch, compute loss, backward pass…
model optimization
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
Iterative Magnitude Pruning Introduction & Motivation Iterative Magnitude Pruning addresses a central problem in reducing the size and cost of compression models: how to Reduce…
Iterative Magnitude Pruning (Extended Study) Introduction & Motivation Iterative Magnitude Pruning (Extended Study) addresses a central problem in reducing the size and cost…
Iterative Magnitude Pruning (Extended Study) Introduction & Motivation Iterative Magnitude Pruning (Extended Study) addresses a central problem in reducing the size and cost…
model optimization
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
Iterative Pseudo-Label Refinement with Memory Queues Introduction & Motivation Iterative Pseudo-Label Refinement with Memory Queues addresses a central problem in semisupervised…
bypass, safety
Jailbreaking is the practice of crafting prompts that bypass an AI model's safety filters and content policies — exploiting gaps between the model's alignment training and its…
ai safety
Jailbreak is a class of adversarial interaction patterns that attempt to circumvent model safety and policy controls - It is a core method in modern LLM training and safety…
ai safety
Jailbreak detection identifies attempts to bypass AI safety guardrails or content policies. What are jailbreaks?: Prompts designed to make models ignore safety training, generate…
ai safety
Jailbreak Prompts are adversarial inputs designed to circumvent safety guardrails and content policies in language models — exploiting vulnerabilities in instruction-following…
ai safety
Jailbreaking attempts is the effort to bypass model safety policies using crafted prompts that coerce prohibited behavior or outputs - jailbreak pressure is an ongoing adversarial…
Jaro-Winkler Metric for Prefix-Biased Name Matching Introduction & Motivation Jaro-Winkler Metric for Prefix-Biased Name Matching addresses a central problem in {subject}…
java virtual machine portability, java virtual machine, virtual machine portability, java virtual, virtual machine, machine portability
Java Virtual Machine Portability Introduction & Motivation Java Virtual Machine Portability addresses a central problem in programming process control and startup-time-warmup-jit…
javascript node ecosystem, javascript node, node ecosystem
JavaScript Node Ecosystem Introduction & Motivation JavaScript Node Ecosystem addresses a central problem in programming process control and single-threaded-limitation prediction…
jax jit, jax grad, jax vmap, jax pmap, jax lax scan, jax xla, jax autodiff, jax functional, jax tpu, jax neural network, jax numpy, jax checkpoint, jax flax
JAX is a numerical computing library that applies four composable function transformations—`jit` (XLA compilation), `grad` (automatic differentiation), `vmap` (vectorization)…
jedec reliability qualification prediction machine learning, jedec reliability, qualification prediction machine, jedec, jedec reliability qualification prediction
JEDEC Reliability Qualification Prediction with Machine Learning Introduction & Motivation JEDEC Reliability Qualification Prediction with Machine Learning addresses a central…
Jensen-Shannon Divergence for Symmetric Probability Drift Introduction & Motivation Jensen-Shannon Divergence for Symmetric Probability Drift addresses a central problem…
jesd47 qualification stress prediction, jesd47 qualification stress, qualification stress prediction, jesd47 qualification, qualification stress, stress prediction
JESD47 Qualification Stress Prediction with Machine Learning Introduction & Motivation JESD47 Qualification Stress Prediction with Machine Learning addresses a central problem…
jet impingement cooling uniformity prediction, jet impingement cooling, impingement cooling uniformity, cooling uniformity prediction, jet impingement, impingement cooling
Jet Impingement Cooling Uniformity Prediction with Machine Learning Introduction & Motivation Jet Impingement Cooling Uniformity Prediction with Machine Learning addresses…
Jigsaw Puzzle Solving Pretext Introduction & Motivation Jigsaw Puzzle Solving Pretext addresses a central problem in selfsupervised and puzzle-configuration-design architecture…
jit, model optimization
JIT Compilation is just-in-time compilation that generates optimized machine code during model execution - It adapts code generation to runtime shapes and execution context. What…
jit, supply chain & logistics
JIT manufacturing is just-in-time production that minimizes inventory by synchronizing supply with demand timing - Materials arrive close to use point to reduce holding cost…
jitter accumulation pll cascaded prediction, jitter accumulation pll, accumulation pll cascaded, pll cascaded prediction, jitter accumulation, accumulation pll, pll cascaded
Jitter Accumulation PLL Cascaded Prediction with Machine Learning Introduction & Motivation Jitter Accumulation PLL Cascaded Prediction with Machine Learning addresses a central…
jitter analysis and control, jitter analysis control, jitter analysis, analysis control
Jitter Analysis and Control Introduction & Motivation Jitter Analysis and Control addresses a central problem in real-time-systems process control and jitter-magnitude-nanoseconds…
jitter budget analysis drift prediction, jitter budget analysis, budget analysis drift, analysis drift prediction, jitter budget, budget analysis, analysis drift, drift prediction
Jitter Budget Analysis Drift Prediction with Machine Learning Introduction & Motivation Jitter Budget Analysis Drift Prediction with Machine Learning addresses a central problem…
jitter elimination and control, jitter elimination control, jitter elimination, elimination control
Jitter Elimination and Control Introduction & Motivation Jitter Elimination and Control addresses a central problem in real-time process control and jitter-magnitude-cycles…
jitter and variance analysis in system performance, jitter variance analysis, variance analysis system, analysis system performance, jitter variance, variance analysis, analysis system
Jitter and Variance Analysis in System Performance Introduction & Motivation Jitter and Variance Analysis in System Performance addresses a central problem in timing process…
jodie, graph neural networks
JODIE is a temporal interaction model using coupled user and item recurrent embeddings. - It captures co-evolving user-item behavior in recommendation-style dynamic interaction…
domain adaptation
Joint Distribution Adaptation (JDA) is an early, profoundly influential shallow mathematical framework in transfer learning designed specifically to align two divergent…
jem, generative models
JEM (Joint Energy-Based Models) is an approach that reinterprets a standard classifier as an energy-based model — the logit outputs of a classification network define an energy…
josephson junction critical current prediction, josephson junction critical, junction critical current, critical current prediction, josephson junction, junction critical
Josephson Junction Critical Current Prediction with Machine Learning Introduction & Motivation Josephson Junction Critical Current Prediction with Machine Learning addresses…
josephson junction critical current uniformity prediction, josephson junction critical, junction critical current, critical current uniformity
Josephson Junction Critical Current Uniformity Prediction with Machine Learning Introduction & Motivation Josephson Junction Critical Current Uniformity Prediction with Machine…
jsma, ai safety
JSMA (Jacobian-based Saliency Map Attack) is a targeted adversarial attack that greedily selects the most effective pixels to modify — using the Jacobian matrix of the network…
json parsing schema validation, json parsing schema, parsing schema validation, json parsing, parsing schema, schema validation
JSON Parsing Schema Validation Introduction & Motivation JSON Parsing Schema Validation addresses a central problem in programming process control…
JSON and Structured Schema Generation Introduction & Motivation JSON and Structured Schema Generation addresses a central problem in generative generation…
jt-vae, graph neural networks
JT-VAE is junction-tree variational autoencoder for chemically valid molecular graph generation. - It generates scaffold structures first, then assembles molecular graphs…
ieee 1149, scan chain jtag, tap controller, board level test
Design-for-test architectures, automatic test pattern generation, and structural fault modeling constitute the digital verification and manufacturing test disciplines engineered…
jtag boundary scan test coverage prediction machine learning, jtag boundary, scan test coverage, jtag, jtag boundary scan test coverage prediction, jtag boundary scan
JTAG Boundary Scan Test Coverage Prediction with Machine Learning Introduction & Motivation JTAG Boundary Scan Test Coverage Prediction with Machine Learning addresses a central…
jtag debugging interface, jtag debugging, debugging interface
JTAG Debugging Interface Introduction & Motivation JTAG Debugging Interface addresses a central problem in verification process control and scan-latency-microseconds prediction…
jtag tap controller timing prediction, jtag tap controller, tap controller timing, controller timing prediction, jtag tap, tap controller, controller timing, timing prediction
JTAG TAP Controller Timing Prediction with Machine Learning Introduction & Motivation JTAG TAP Controller Timing Prediction with Machine Learning addresses a central problem…
jump detection discontinuity, jump detection, detection discontinuity
Jump Detection Discontinuity Introduction & Motivation Jump Detection Discontinuity addresses a central problem in timeseries process control and jump-point-sudden-change…
junction capacitance bias dependence modeling prediction, junction capacitance bias, capacitance bias dependence, bias dependence modeling, dependence modeling prediction
Junction Capacitance Bias Dependence Modeling Prediction with Machine Learning Introduction & Motivation Junction Capacitance Bias Dependence Modeling Prediction with Machine…
diffusion
Junction depth control precisely manages the depth of doped regions through optimized implantation and thermal processing to meet device specifications. Definition: Junction depth…
junction depth control drift prediction machine learning, junction depth, control drift prediction, sims, junction depth control drift prediction, junction depth control
Junction Depth Control Drift Prediction with Machine Learning Introduction & Motivation Junction Depth Control Drift Prediction with Machine Learning addresses a central problem…