Performance Analysis of Random Linear Network Coding in Two-Source Single-Relay Networks

Theoretical Limits of Language Model Alignment

$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses

A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models

When Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time Aggregation

When Semantic Communication Meets Queueing: Cross-Layer Latency and Task Fidelity Optimization

Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation

Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees

Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval

Expert Routing for Communication-Efficient MoE via Finite Expert Banks

Contextual Memory-Enhanced Source Coding for Low-SNR Communications

Realizable Bayes-Consistency for General Metric Losses

Leveraging Code Automorphisms for Improved Syndrome-Based Neural Decoding

A Hierarchical Sampling Framework for bounding the Generalization Error of Federated Learning

Dueling DDQN-Based Adaptive Multi-Objective Handover Optimization for LEO Satellite Networks

The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy

Optimization of CV-QKD Under Practical Constraints

Benchmarking Wireless Representations: High-Dimensional vs. Compressed Embeddings for Efficiency and Robustness

Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels

SwiftChannel: Algorithm-Hardware Co-Design for Deep Learning-Based 5G Channel Estimation

Evolving Token Communication with Parametric Memory Network

Remote Action Generation: Remote Control with Minimal Communication

The (Marginal) Value of a Search Ad: An Online Causal Framework for Repeated Second-price Auctions

Stabilizing Private LASSO under Heterogeneous Covariates via Anisotropic Objective Perturbation

Linear-Readout Floors and Threshold Recovery in Computation in Superposition

Soft Graph Diffusion Transformer for MIMO Detection

Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design

Exponential families from a single KL identity

MIFair: A Mutual-Information Framework for Intersectionality and Multiclass Fairness

Diffusion-OAMP for Joint Image Compression and Wireless Transmission

Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing

Why Self-Supervised Encoders Want to Be Normal

Statistical Channel Fingerprint Construction for Massive MIMO: A Unified Tensor Learning Framework

Adaptive Transform Coding for Semantic Compression

Lightweight Quantum Agent for Edge Systems: Joint PQC and NOMA Resource Allocation

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective

Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG

Generalising maximum mean discrepancy: kernelised functional Bregman divergences

Improving Robustness of Tabular Retrieval via Representational Stability

Information-Theoretic Measures in AI: A Practical Decision Guide

A Unified Fractional Regularization Framework for Sparse Recovery

Shape of Memory: a Geometric Analysis of Machine Unlearning in Second-Order Optimizers

The Exact Replica Threshold for Nonlinear Moments of Quantum States

Semantic Error Correction and Decoding for Short Block Codes

Null-Space Flow Matching for MIMO Channel Estimation in Latency-Constrained Systems

Directional Confusions Reveal Divergent Inductive Biases Through Rate-Distortion Geometry in Human and Machine Vision

MambaCSP: Hybrid-Attention State Space Models for Hardware-Efficient Channel State Prediction

Amortized Vine Copulas for High-Dimensional Density and Information Estimation

Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms

Secure Rate-Distortion-Perception: A Randomized Distributed Function Computation Approach for Realism

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory

FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning

Ultrametric OGP - parametric RDT \emph{symmetric} binary perceptron connection

Watts-per-Intelligence Part II: Algorithmic Catalysis

AirFM-DDA: Air-Interface Foundation Model in the Delay-Doppler-Angle Domain for AI-Native 6G

Lossless Compression via Chained Lightweight Neural Predictors with Information Inheritance

Regret Tail Characterization of Optimal Bandit Algorithms with Generic Rewards

Exploiting Correlations in Federated Learning: Opportunities and Practical Limitations

A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff

Aerial Multi-Functional RIS in Fluid Antennas-Aided Full-Duplex Networks: A Self-Optimized Hybrid Deep Reinforcement Learning Approach

InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control

Endogenous Information in Routing Games: Memory-Constrained Equilibria, Recall Braess Paradoxes, and Memory Design

Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection with E-Variables

LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge Deployment

The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms

Sequential KV Cache Compression via Probabilistic Language Tries: Beyond the Per-Vector Shannon Limit

Diffusion Denoiser Achievable Analysis for Finite Blocklength Unsourced Random Access

Joint Interference Detection and Identification via Adversarial Multi-task Learning

Agentic AI-Based Joint Computing and Networking via Mixture of Experts and Large Language Models

eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization

StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing

Polynomial-Time Optimal Group Selection via the Double-Commutator Eigenvalue Problem

Algebraic Diversity: Group-Theoretic Spectral Estimation from Single Observations

The Root Theorem of Context Engineering

Continual Few-shot Adaptation for Synthetic Fingerprint Detection

The Geometry of Knowing: From Possibilistic Ignorance to Probabilistic Certainty -- A Measure-Theoretic Framework for Epistemic Convergence

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

On the Rate-Distortion-Complexity Tradeoff for Semantic Communication

Binary Flow Matching: Prediction-Loss Space Alignment for Robust Learning

A Rational Account of Categorization Based on Information Theory

Contextuality from Single-State Ontological Models: An Information-Theoretic Obstruction

A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding

On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training

Energy-Aware Routing to Large Reasoning Models

Efficient Vector Symbolic Architectures from Histogram Recovery

Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMs

What Can Be Recovered Under Sparse Adversarial Corruption? Assumption-Free Theory for Linear Measurements

Feedback Lunch: Learned Feedback Codes for Secure Communications

On the optimization dynamics of RLVR: Gradient gap and step size thresholds

Synthetic Counterfactual Labels for Efficient Conformal Counterfactual Inference

Natural Image Classification via Quasi-Cyclic Graph Ensembles and Random-Bond Ising Models at the Nishimori Temperature

Multimodal Remote Inference

Let's Measure Information Step-by-Step: AI-Based Evaluation Beyond Vibes

Best Agent Identification for General Game Playing

Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL

MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation

Biased Federated Learning under Wireless Heterogeneity

MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression

Anomaly Detection from a Tensor Train Perspective

Semantic Variational Bayes Based on Semantic Information G Theory for Solving Latent Variables

推荐订阅源

cs.IT updates on arXiv.org