2,311 technical terms and definitions
model calibration probability, model calibration, calibration probability
Model Calibration Probability Introduction & Motivation Model Calibration Probability addresses a central problem in systems process control…
documentation, transparency
Model Cards and AI Documentation What is a Model Card? A standardized document describing an ML model, including its capabilities, limitations, intended use, and potential risks.…
documentation, transparency
Model Cards are the standardized documentation format for machine learning models that communicates intended use cases, training data, performance evaluation results, limitations…
documentation
Model Card is the standardized documentation framework that provides essential information about a machine learning model's intended use, performance characteristics, limitations…
evaluation
Model Card is a structured documentation artifact describing model purpose, limitations, risks, and evaluation evidence - It is a core method in modern AI evaluation…
Model Card and Datasheet Automated Provenance Generator Introduction & Motivation Model Card and Datasheet Automated Provenance Generator addresses a central problem…
documentation
Model cards documentation is the structured model disclosure artifact describing intended use, performance boundaries, and risk considerations - it improves transparency…
formal verification, temporal logic, ltl, ctl, spin, nusmv, cbmc, tla+
Model checking exhaustively analyzes a formal transition-system model against temporal, safety, liveness, or reachability properties. It verifies hardware FSMs, protocols…
model checking state space, model checking state, checking state space, model checking, checking state, state space
Model Checking State Space Introduction & Motivation Model Checking State Space addresses a central problem in verification process control and state-space-size-estimation…
model optimization
Model compression reduces model size and compute requirements through techniques like pruning, quantization, and distillation. Why compress: Deployment on edge devices, reduce…
model optimization
Model Compression is a set of techniques that reduce model size and compute cost while preserving target performance - It enables efficient deployment on constrained hardware…
model optimization, quantization pruning distillation, efficient inference
Model compression refers to a family of techniques that reduce the size, memory footprint, and computational cost of neural networks while preserving as much accuracy as possible.…
model compression and accuracy preservation, model compression accuracy, compression accuracy preservation, model compression, compression accuracy, accuracy preservation
Model Compression and Accuracy Preservation Introduction & Motivation Model Compression and Accuracy Preservation addresses a central problem in ml-inference process control…
edge ai
Model Compression for Edge Deployment is the set of techniques to reduce neural network size and computational requirements — enabling deployment of powerful models on…
edge ai
Model compression for mobile encompasses techniques to reduce model size and computational requirements so that machine learning models can run efficiently on smartphones…
101245 model, model compression, cifar, residual networks & skip connections, residual networks skip, networks skip connections, residual networks, networks skip, skip connections
Residual Networks & Skip Connections Introduction & Motivation Residual Networks: enable deeper architectures. Skip connections, residual blocks. Applications: very deep networks…
model compression, pruning efficient neural, 100mb 10mb ce kl nas passed, model compression & pruning efficient neural networks, model compression pruning, compression pruning efficient
Model Compression & Pruning: Efficient Neural Networks Introduction & Motivation Model compression: reduce model size/inference cost. Pruning: remove weights; structured…
model compression pruning, model compression, compression pruning
Model Compression Pruning Introduction & Motivation Model Compression Pruning addresses a central problem in systems process control and pruning-strategy-magnitude-structured…
model compression quantization pruning knowledge distillation, model compression, quantization pruning knowledge, ar awq bert c4 ce fp16, model compression quantization
Model Compression: Quantization, Pruning, and Knowledge Distillation 1. Introduction & Motivation Model compression reduces the size, memory footprint, and inference latency…
neural network pruning, weight pruning structured, magnitude pruning lottery ticket, compression deep learning
Model Compression Techniques are the family of methods that reduce neural network size, memory footprint, and computational cost while preserving accuracy — including pruning…
model compression techniques, model compression, compression techniques
Model Compression Techniques Introduction & Motivation Model Compression Techniques addresses a central problem in ml-training process control and compression-ratio-achieved…
model optimization
Model Conversion is transforming model formats between frameworks and runtimes for deployment compatibility - It is often required to move from training stacks to production…
Model Debugging via Explanations Introduction & Motivation Model Debugging via Explanations addresses a central problem in explainability interpretation and model understanding…
inference optimization techniques, runtime optimization neural networks, deployment efficiency, production inference optimization
Model deployment is the gap between a model that works in a training notebook and a model that answers real requests under a real latency budget, and almost everything in that gap…
model deployment, deployment optimization, api aws cd ci gcp, model deployment & optimization
Model deployment is the gap between a model that works in a training notebook and a model that answers real requests under a real latency budget, and almost everything in that gap…
model deployment, deployment serving, api ml nlp onnx passed rest, model deployment & serving
Model deployment is the gap between a model that works in a training notebook and a model that answers real requests under a real latency budget, and almost everything in that gap…
doe
Model Discrimination Design is a DOE strategy specifically designed to distinguish between competing statistical models — selecting experiments that maximize the expected…
knowledge distillation efficiency, knowledge distillation, distillation efficiency
Knowledge Distillation Efficiency Introduction & Motivation Knowledge Distillation Efficiency addresses a central problem in ml-training process control and student-teacher-gap…
knowledge distillation, teacher student, soft labels, logit distillation, feature distillation
Model distillation trains a smaller student to reproduce useful behavior or internal representations of a larger teacher. It converts expensive model capability into…
Model Distillation into Interpretable Surrogates Introduction & Motivation Model Distillation into Interpretable Surrogates addresses a central problem in interpretability…
Model Distillation into Interpretable Surrogates (Extended Study) Introduction & Motivation Model Distillation into Interpretable Surrogates (Extended Study) addresses a central…
Model Distillation into Interpretable Surrogates (Extended Study) Introduction & Motivation Model Distillation into Interpretable Surrogates (Extended Study) addresses a central…
teacher student training, dark knowledge transfer, logit distillation, feature distillation
Knowledge Distillation is the model compression technique where a smaller student network is trained to replicate the behavior of a larger teacher network — learning not just…
teacher student network, knowledge transfer distillation, soft label distillation, distillation training
Knowledge Distillation is the model compression technique where a smaller "student" network is trained to mimic the behavior of a larger, more capable "teacher" network…
Rule Distillation from Complex Models Introduction & Motivation Rule Distillation from Complex Models addresses a central problem in explainability interpretation and model…
data drift, concept drift, covariate shift, population stability index, PSI, Kolmogorov-Smirnov test, model decay
Model drift is the gradual loss of a deployed machine learning model's predictive quality because the world it was trained on has changed: the inputs it receives no longer look…
model training
Model editing directly updates specific weights to fix factual errors or modify behaviors without full retraining. Motivation: Models contain factual errors, knowledge becomes…
model editing knowledge editing large language models, model editing, knowledge editing large, ceo llm memit mend mlp peft, model editing & knowledge editing in large language models
Model Editing & Knowledge Editing in Large Language Models 1. Introduction & Motivation Large language models memorize an enormous number of facts during pretraining, but that…
model ensemble inference and resource sharing overhead, model ensemble inference, ensemble inference resource, inference resource sharing, resource sharing overhead, model ensemble
Model Ensemble Inference and Resource Sharing Overhead Introduction & Motivation Model Ensemble Inference and Resource Sharing Overhead addresses a central problem in inference…
reinforcement learning advanced
Model ensemble RL is reinforcement-learning approaches that use multiple models or policies to improve robustness and uncertainty handling - Ensembles aggregate predictions…
llm evaluation, ai evaluation, mmlu, humaneval, gsm8k, benchmarking, model judge, human evaluation, goodhart law
Model evaluation measures whether a model is actually good at the thing it's being deployed to do, and the field's hardest-won lesson is that a single number almost never answers…
capability elicitation, few shot prompting evaluation, benchmark contamination
LLM Capability Elicitation and Evaluation is the systematic process of measuring what a language model can and cannot do — including prompt engineering for evaluation, avoiding…
llm evaluation framework, evaluation harness, benchmark contamination, llm benchmark design
LLM Evaluation and Benchmarking is the systematic methodology for measuring language model capabilities across diverse tasks — encompassing academic benchmarks (MMLU, HumanEval…
Aggregating Multiple Explanations Introduction & Motivation Aggregating Multiple Explanations addresses a central problem in explainability interpretation and model understanding…
interoperability, framework portability
ONNX for Model Interoperability What is ONNX? ONNX (Open Neural Network Exchange) is an open format for representing machine learning models, enabling interoperability between…
stealing, query
Model Extraction (Model Stealing) is the adversarial attack where an adversary reconstructs a functional copy of a proprietary machine learning model by systematically querying…
interpretability
Model Extraction is an attack that approximates a target model by repeatedly querying its prediction API - It can replicate decision behavior and expose intellectual property…
ai safety
Model extraction attack (also called model stealing) is a security attack where an adversary aims to recreate a proprietary ML model by systematically querying it and using…
model extraction, extraction knowledge, api ip kl, model extraction & knowledge theft, model extraction knowledge, extraction knowledge theft, knowledge theft
Model Extraction & Knowledge Theft Introduction & Motivation Model extraction: steal model knowledge via queries. Recover models via API access. Applications: security…
model extraction stealing, model extraction, extraction stealing
Model Extraction Stealing Introduction & Motivation Model Extraction Stealing addresses a central problem in systems process control and extraction-attack-query-based prediction…