An LLM-enhanced Viterbi decoder achieves roughly 1.5 dB extra coding gain in block error rate and over 50% better semantic similarity than conventional Viterbi for constraint-length-3 convolutional codes on AWGN channels.
hub
A mathematical theory of communication
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
years
2026 10roles
method 1polarities
use method 1representative citing papers
HealthPoint represents clinical events as points in a 4D space (content, time, modality, case) and applies low-rank relational attention to achieve state-of-the-art mortality prediction from multi-level incomplete multimodal EHRs.
An achievability result is derived for empirical coordination under finite blocklength constraints, yielding both an exact rate bound and its asymptotic expansion.
Decoder-provided pilots reuse decoded codewords to track time-varying channels, with information-theoretic limits derived and simulations showing performance gains over conventional training.
A synonymous source coding architecture and variational inference framework derive the rate-distortion-perception tradeoff by treating perception as recovery of any admissible synonymous sample.
SPATE encodes data via spike trains mapped to quantum phases, yielding stronger feature representations than angle or amplitude encoding on datasets like Blobs and Moons.
ACF structurally decouples covert communication from semantic reasoning in agent networks using a shared steganographic configuration to maintain performance under cognitive asymmetry.
Risk-Calibrated Learning reduces critical error rates in medical AI by 20-92% across four imaging datasets by embedding a severity matrix into the optimization.
Proposes a three-layer framework using formal AI reasoning for verification, derivation, and discovery in wireless communications theory.
Tutorial overview of electromagnetic signal and information theory for continuous-aperture array wireless systems, emphasizing the shift from discrete to continuous models.
citing papers explorer
-
LLM-Viterbi: Semantic-Aware Decoding for Convolutional Codes
An LLM-enhanced Viterbi decoder achieves roughly 1.5 dB extra coding gain in block error rate and over 50% better semantic similarity than conventional Viterbi for constraint-length-3 convolutional codes on AWGN channels.
-
A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs
HealthPoint represents clinical events as points in a 4D space (content, time, modality, case) and applies low-rank relational attention to achieve state-of-the-art mortality prediction from multi-level incomplete multimodal EHRs.
-
Empirical coordination in the finite blocklength regime: an achievability result---Extended version
An achievability result is derived for empirical coordination under finite blocklength constraints, yielding both an exact rate bound and its asymptotic expansion.
-
The Benefit of Decoder-Provided Pilots in Highly Dynamic Channels
Decoder-provided pilots reuse decoded codewords to track time-varying channels, with information-theoretic limits derived and simulations showing performance gains over conventional training.
-
A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff
A synonymous source coding architecture and variational inference framework derive the rate-distortion-perception tradeoff by treating perception as recovery of any admissible synonymous sample.
-
SPATE: Spiking-Phase Adaptive Temporal Encoding for Quantum Machine Learning
SPATE encodes data via spike trains mapped to quantum phases, yielding stronger feature representations than angle or amplitude encoding on datasets like Blobs and Moons.
-
ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry
ACF structurally decouples covert communication from semantic reasoning in agent networks using a shared steganographic configuration to maintain performance under cognitive asymmetry.
-
Risk-Calibrated Learning: Minimizing Fatal Errors in Medical AI
Risk-Calibrated Learning reduces critical error rates in medical AI by 20-92% across four imaging datasets by embedding a severity matrix into the optimization.
-
Rethinking Wireless Communications through Formal Mathematical AI Reasoning
Proposes a three-layer framework using formal AI reasoning for verification, derivation, and discovery in wireless communications theory.
-
Electromagnetic Signal and Information Theory: A Continuous-Aperture Array Perspective
Tutorial overview of electromagnetic signal and information theory for continuous-aperture array wireless systems, emphasizing the shift from discrete to continuous models.