#Information Theory
Latest news articles tagged with "Information Theory". Follow the timeline of events, related topics, and entities.
Articles (9)
-
🇺🇸 A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
[USA]
arXiv:2602.23163v1 Announce Type: new Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms....
Related: #AI Safety, #Steganography, #Machine Learning -
🇺🇸 Rethinking Disentanglement under Dependent Factors of Variation
[USA]
arXiv:2408.07016v3 Announce Type: replace-cross Abstract: Representation learning is an approach that allows to discover and extract the factors of variation from the data. Intuitively, a representat...
Related: #Machine Learning, #Representation Learning -
🇺🇸 Contextuality from Single-State Representations: An Information-Theoretic Principle for Adaptive Intelligence
[USA]
arXiv:2602.16716v1 Announce Type: new Abstract: Adaptive systems often operate across multiple contexts while reusing a fixed internal state space due to constraints on memory, representation, or phy...
Related: #Adaptive Intelligence, #Contextuality -
🇺🇸 MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions
[USA]
arXiv:2602.17308v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for diagnostic tasks in medicine. In clinical practice, the correct diagnosis can rarely be immediat...
Related: #Artificial Intelligence, #Medical Informatics, #Diagnostic Reasoning, #Human‑AI Interaction -
🇺🇸 IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentation
[USA]
arXiv:2602.15878v1 Announce Type: cross Abstract: In industrial scenarios, data augmentation is an effective approach to improve model performance. However, its benefits are not unidirectionally bene...
Related: #Data Augmentation, #Optimal Sample Size, #Industrial Machine Learning -
🇺🇸 SIT-LMPC: Safe Information-Theoretic Learning Model Predictive Control for Iterative Tasks
[USA]
arXiv:2602.16187v1 Announce Type: cross Abstract: Robots executing iterative tasks in complex, uncertain environments require control strategies that balance robustness, safety, and high performance....
Related: #Robotics, #Learning‑Based Control, #Model Predictive Control, #Safety in Automation -
🇺🇸 Information-theoretic analysis of world models in optimal reward maximizers
[USA]
arXiv:2602.12963v1 Announce Type: new Abstract: An important question in the field of AI is the extent to which successful behaviour requires an internal representation of the world. In this work, we...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Semantic Chunking and the Entropy of Natural Language
[USA]
arXiv:2602.13194v1 Announce Type: cross Abstract: The entropy rate of printed English is famously estimated to be about one bit per character, a benchmark that modern large language models (LLMs) hav...
Related: #Natural Language Processing, #Computational Linguistics -
🇺🇸 Stable but Wrong: When More Data Degrades Scientific Conclusions
[USA]
arXiv:2602.05668v1 Announce Type: cross Abstract: Modern science increasingly relies on ever-growing observational datasets and automated inference pipelines, under the implicit belief that accumulat...
Related: #Data Science, #Scientific Methodology