The paper introduces a unified Physics-Informed Deep Learning (PIDL) framework that simultaneously enforces physical laws and information-theoretic bounds, demonstrating robust, domain-agnostic entrop…

This paper proves space lower bounds for entropy-efficient random sampling using i.i.d. uniform bits.

The paper proposes a Signed Entropy Integral (SEI) statistic to detect mislabeled images in training datasets by analyzing the temporal trend of prediction entropy, achieving state-of-the-art results…

The paper introduces Canopy Entropy ($ ext{CE}^ ext{*}$), a novel metric that quantifies generation uncertainty across the entire output space, demonstrating that fine-tuning improves information conv…

The paper proposes EAPO, an entropy-driven adaptive weighting method that dynamically adjusts the influence of positive samples during policy optimization to improve both response diversity and stabil…

The paper proposes an Entropy Dynamics framework to analyze the stability and failure modes of centralized orchestration in Multi-Agent Systems, identifying a 'Reasoning Trap' where complex reasoning…

The paper introduces an entropy-aware masking strategy for Masked Language Modeling (MLM) that targets informative and uncertain tokens, achieving up to a 5% performance improvement on GLUE scores.

The paper introduces the Calibrated Entropy Score (CES), a single-pass, black-box method that uses the distribution of token-level entropies to detect model hallucinations with high accuracy and forma…

This paper develops provably undetectable and robust watermarking schemes for LLM outputs even when the per-token entropy is only constant, removing previous dependencies on high entropy rates or larg…

This paper introduces a novel algorithm for generating k Hamming weight binary words in linear time while minimizing random bit consumption.

The paper proposes a novel information-geometric framework to analyze LLM stability by integrating task utility, external entropy, and internal structural proxies, showing this composite score improve…

This paper measures the lower bound for the shortest program generating a sequence, proving a conservation law and providing a deterministic engine to recover generating programs for certain sequences…

This paper proposes a thermodynamic computing stack for machine learning using stochastic analog processes and energy-based models.

AEGIS introduces a novel physics-based system that analyzes encrypted network traffic flow dynamics, achieving state-of-the-art zero-day evasion detection with high accuracy and low latency.

This paper proposes a method to describe dynamical systems using molecular and reaction concepts, making three key decisions: number of places, species determination, and transitions.

The paper analyzes the entropy dynamics of Chain-of-Thought (CoT) reasoning, identifying a transition from an exploratory Uncertainty Region to a stable Confidence Region, which enables superior early…

The paper introduces the Kerimov-Alekberli model, an information-geometric framework that uses non-equilibrium thermodynamics and stochastic control to provide a physically grounded method for detecti…