consensus mechanism
multi-agent
Consensus mechanisms enable multiple agents to reach agreement on outputs through voting or discussion. Why needed: Different agents may produce different answers, need systematic…
2,847 technical terms and definitions
multi-agent
Consensus mechanisms enable multiple agents to reach agreement on outputs through voting or discussion. Why needed: Different agents may produce different answers, need systematic…
scientific ml
Conservation Laws in Neural Networks refers to architectural constraints, loss function penalties, or structural design choices that ensure neural network outputs respect…
cql, reinforcement learning
CQL (Conservative Q-Learning) is the leading offline RL algorithm that learns a conservative (lower-bound) Q-function — penalizing Q-values for out-of-distribution actions…
Conservative Q-Learning Introduction & Motivation Conservative Q-Learning addresses a central problem in sequential decision making via deeprl: how to Learn a policy that…
Conservative Q-Learning for Offline RL Introduction & Motivation Conservative Q-Learning for Offline RL addresses a central problem in reinforcement policy learning…
Conservative Q-Learning (Extended Study) Introduction & Motivation Conservative Q-Learning (Extended Study) addresses a central problem in sequential decision making via deeprl…
Conservative Q-Learning (Extended Study) Introduction & Motivation Conservative Q-Learning (Extended Study) addresses a central problem in sequential decision making via deeprl…
inventory management, hold inventory, stock, warehousing, just in time
Yes, we offer consignment and inventory management services to help customers manage cash flow and reduce inventory risk — with consignment programs where we manufacture and hold…
supply chain & logistics
Consignment inventory is inventory owned by the supplier but stored at the customer site until consumed - Ownership transfer occurs at usage, reducing customer capital burden on…
evaluation
Consistency is the stability of model answers across equivalent prompts, repeated runs, or related reasoning paths - It is a core method in modern AI fairness and evaluation…
reasoning
Consistency checking in LLM reasoning is the technique of generating multiple answers or reasoning paths and comparing them for agreement — using the principle that consistent…
generative models
Consistency Models are a class of generative models that learn to map any point along the diffusion process trajectory directly to the trajectory's origin (the clean data point)…
generative models
Consistency models is the generative models trained so predictions at different noise levels map consistently toward the same clean sample - they enable one-step or few-step…
Consistency Models for Fast Single-Step Generation Introduction & Motivation Consistency Models for Fast Single-Step Generation addresses a central problem in generative…
Consistency Models for Fast Sampling Introduction & Motivation Consistency Models for Fast Sampling addresses a central problem in generative modeling of diffusion data: how…
Consistency Models for Fast Sampling (Extended Study) Introduction & Motivation Consistency Models for Fast Sampling (Extended Study) addresses a central problem in generative…
Consistency Models for Fast Sampling (Extended Study) Introduction & Motivation Consistency Models for Fast Sampling (Extended Study) addresses a central problem in generative…
semi-supervised learning
Consistency Regularization is a core principle of semi-supervised learning that enforces model predictions to remain invariant under realistic perturbations of unlabeled inputs…
Interpolation Consistency Regularization ICR Introduction & Motivation Interpolation Consistency Regularization ICR addresses a central problem in semisupervised…
Consistency Regularization for Semi-Supervised Introduction & Motivation Consistency Regularization for Semi-Supervised addresses a central problem in semisupervised…
testing
Consistency Testing is a model validation approach that verifies whether a model produces logically consistent predictions across related inputs — checking that the model's…
Consistency Checking Across Records Introduction & Motivation Consistency Checking Across Records addresses a central problem in {subject} assurance and {target} management: how…
consistent hashing ring, consistent hashing, hashing ring
Consistent Hashing Ring Introduction & Motivation Consistent Hashing Ring addresses a central problem in distributed-systems process control and key-distribution-balance…
3d vision
Consistent video depth is the requirement that depth predictions remain temporally coherent across consecutive frames while respecting camera motion and scene geometry - without…
cfr period, useful life
Semiconductor reliability physics and accelerated life testing constitute the statistical, thermodynamic, and mechanical disciplines engineered to predict, quantify, and guarantee…
Dennard scaling, Robert Dennard, scaling rules, voltage scaling, field-constant scaling
Constant-field scaling is the specific set of rules for shrinking a MOSFET that keeps the electric fields inside the device approximately unchanged as its dimensions get smaller…
optimization
Constant folding is the compile-time optimization that precomputes expressions involving only constants - it eliminates redundant runtime work by replacing static subgraphs…
model optimization
Constant Folding is a compiler optimization that precomputes graph expressions involving static constants - It removes runtime work by shifting deterministic computation…
constant folding and compile-time optimization, constant folding compile-time, folding compile-time optimization, constant folding, folding compile-time, compile-time optimization
Constant Folding and Compile-Time Optimization Introduction & Motivation Constant Folding and Compile-Time Optimization addresses a central problem in ml-compiler process control…
constant propagation and folding, constant propagation folding, constant propagation, propagation folding
Constant Propagation and Folding Introduction & Motivation Constant Propagation and Folding addresses a central problem in compiler-optimization process control…
reliability test, htol hast
Semiconductor reliability physics and accelerated life testing constitute the statistical, thermodynamic, and mechanical disciplines engineered to predict, quantify, and guarantee…
nlp
Constituency parsing is a syntactic analysis task that breaks a sentence into nested phrases, or constituents, such as noun phrases, verb phrases, and prepositional phrases.…
constituent parsing syntactic, constituent parsing, parsing syntactic
Constituent Parsing Syntactic Introduction & Motivation Constituent Parsing Syntactic addresses a central problem in nlp process control and constituent-parsing-tree-structure…
AI, RLHF, alignment, values
Constitutional AI (CAI) and RLHF Alignment is a training methodology that uses a predefined set of constitutional principles or values to guide model behavior through…
cai, principles
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
constitutional artificial intelligence, cai, rlaif, self critique, principle based alignment, claude alignment
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
ai safety
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
cai, ai safety
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
prompting techniques
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
training techniques
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
rlaif, ai feedback alignment, claude constitution, self critique, ai safety alignment
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
rlaif, ai feedback reinforcement, self-critique training, principle-based alignment
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
safety training, ai alignment methods, harmlessness training, red teaming defense
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
rlhf alignment technique, ai safety alignment, human feedback alignment llm, reward model alignment
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
prompting
Constitutional AI trains a model to critique and revise its own outputs against a written set of principles, replacing a large share of the human labeling that RLHF normally…
Constrained Bayesian Optimization with Expected Feasibility Introduction & Motivation Constrained Bayesian Optimization with Expected Feasibility addresses a central problem…
structured generation
Constrained beam search is a decoding algorithm that extends standard beam search with additional constraints that the generated output must satisfy. It explores multiple…
grammar, json
Constrained Decoding is a generation technique that forces LLM output to strictly conform to a predefined grammar, schema, or regular expression — filtering the vocabulary at each…
inference
Constrained decoding forces LLM outputs to follow specific rules, formats, or grammars. Mechanism: During each token selection, mask invalid tokens based on constraints, only…
optimization
Constrained Decoding is token selection with hard validity rules that block outputs violating predefined constraints - It is a core method in modern semiconductor AI serving…