Action-BED recasts BED as expected future loss on actions, producing singly intractable objectives jointly optimized for design and action policies via stochastic gradients without explicit posterior estimation.
hub
Shannon, Communication theory of secrecy systems, The Bell System Technical Journal 28 (1949) 656 –715
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
representative citing papers
HiPolicy is a new hierarchical multi-frequency action chunking method for imitation learning that jointly generates coarse and fine action sequences with entropy-guided execution to improve performance and efficiency in robotic manipulation.
Derives a Boltzmann-like distribution over actions via maximum entropy subject to a mean-action constraint, producing a Markovian stochastic propagator that matches Brownian motion and remains covariant at relativistic speeds.
Hamm-grams are a new class of fixed-length regular expressions over bytes with single-character wildcards, mined efficiently with LSH and clustering to yield more robust features than n-grams for malware classification and detection.
Constructs 15-fold symmetric parity proofs of the Bell-Kochen-Specker theorem by turning Coxeter's triacontagonal projections of the 600-cell, 120-cell and Gosset polytope into Kochen-Specker diagrams.
CodeQ aggregates token rationales into code categories to enable global interpretability of LLMs, claiming over 50% entropy reduction and revealing model preference for syntactic cues plus human misalignment in a 37-person study.
Genetic algorithm with Walsh-Hadamard Spectrum cost function generates 8x8 S-boxes with nonlinearity 104 in average 49,399 iterations at 100% success rate, matching best-known methods.
Ensemble voting strategies for change point detection improve F1-score by 11% over Mozilla's T-test method on a new ground-truth dataset of 174 performance time series annotated by practitioners.
Space-time grooved metal surfaces with uniform-velocity modulations support gain, non-reciprocity, non-Foster response, and one-way propagation channels.
Correlated sensing with thermal-state resonant detectors enables statistical tests via symmetric correlators to reveal quantum noise characteristics of gravitons in two- and three-detector tabletop configurations.
Von Neumann Networks create self-engineered neural architectures on cellular arrays using learned roles and diffusion processes, extending neural operators and proving computational universality while showing better efficiency than standard MLPs on basic tasks.
LLMs classify Gaza War headlines as strongly negative while fine-tuned Arabic BERT models favor neutral labels, producing measurable non-random divergences in sentiment distributions.
The zentropy approach receives a statistical-physics foundation via recursive entropy maximization, yielding partition functions for coarse-grained configurations and clarifying temperature-dependent states in thermodynamic systems.
Reformulates MST as PUBO, applies FALQON to optimize prototypes for OPF classifiers, and reports accuracies comparable to classical Prim's algorithm on real datasets.
HCFSSNet uses convolutional layers plus a Vision Frequency State Space block with omni-directional scanning and frequency reweighting to reach competitive rate-distortion performance in learned image compression.
citing papers explorer
-
Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives
Action-BED recasts BED as expected future loss on actions, producing singly intractable objectives jointly optimized for design and action policies via stochastic gradients without explicit posterior estimation.
-
HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning
HiPolicy is a new hierarchical multi-frequency action chunking method for imitation learning that jointly generates coarse and fine action sequences with entropy-guided execution to improve performance and efficiency in robotic manipulation.
-
Stochastic dynamics from maximum entropy in action space
Derives a Boltzmann-like distribution over actions via maximum entropy subject to a mean-action constraint, producing a Markovian stochastic propagator that matches Brownian motion and remains covariant at relativistic speeds.
-
Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes
Hamm-grams are a new class of fixed-length regular expressions over bytes with single-character wildcards, mined efficiently with LSH and clustering to yield more robust features than n-grams for malware classification and detection.
-
Triacontagonal proofs of the Bell-Kochen-Specker theorem
Constructs 15-fold symmetric parity proofs of the Bell-Kochen-Specker theorem by turning Coxeter's triacontagonal projections of the 600-cell, 120-cell and Gosset polytope into Kochen-Specker diagrams.
-
Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation
CodeQ aggregates token rationales into code categories to enable global interpretability of LLMs, claiming over 50% entropy reduction and revealing model preference for syntactic cues plus human misalignment in a 37-person study.
-
Evolutionary Approach to S-box Generation: Optimizing Nonlinear Substitutions in Symmetric Ciphers
Genetic algorithm with Walsh-Hadamard Spectrum cost function generates 8x8 S-boxes with nonlinearity 104 in average 49,399 iterations at 100% success rate, matching best-known methods.
-
Exploring Statistical Change Point Detection Techniques for Performance Anomaly Detection at Mozilla
Ensemble voting strategies for change point detection improve F1-score by 11% over Mozilla's T-test method on a new ground-truth dataset of 174 performance time series annotated by practitioners.
-
Gain and One-Way Propagation in Synthetically Moving non-Foster Gratings
Space-time grooved metal surfaces with uniform-velocity modulations support gain, non-reciprocity, non-Foster response, and one-way propagation channels.
-
Correlated Quantum Sensing at the Seemingly Classical Limit
Correlated sensing with thermal-state resonant detectors enables statistical tests via symmetric correlators to reveal quantum noise characteristics of gravitons in two- and three-detector tabletop configurations.
-
Von Neumann Networks
Von Neumann Networks create self-engineered neural architectures on cellular arrays using learned roles and diffusion processes, extending neural operators and proving computational universality while showing better efficiency than standard MLPs on basic tasks.
-
Sentiment Classification of Gaza War Headlines: A Comparative Analysis of Large Language Models and Arabic Fine-Tuned BERT Models
LLMs classify Gaza War headlines as strongly negative while fine-tuned Arabic BERT models favor neutral labels, producing measurable non-random divergences in sentiment distributions.
-
Recursive entropy in thermodynamics: expounding the statistical-physics basis of the zentropy approach
The zentropy approach receives a statistical-physics foundation via recursive entropy maximization, yielding partition functions for coarse-grained configurations and clarifying temperature-dependent states in thermodynamic systems.
-
PUBO Formulation for MST and Application to Optimum-Path Forest
Reformulates MST as PUBO, applies FALQON to optimize prototypes for OPF classifiers, and reports accuracies comparable to classical Prim's algorithm on real datasets.
-
A Compact Hybrid Convolution--Frequency State Space Network for Learned Image Compression
HCFSSNet uses convolutional layers plus a Vision Frequency State Space block with omni-directional scanning and frequency reweighting to reach competitive rate-distortion performance in learned image compression.
- RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry