#Theoretical Computer Science
Latest news articles tagged with "Theoretical Computer Science". Follow the timeline of events, related topics, and entities.
Articles (6)
-
🇺🇸 The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?
[USA]
arXiv:2604.06436v1 Announce Type: cross Abstract: We prove that no continuous, utility-preserving wrapper defense-a function $D: X\to X$ that preprocesses inputs before the model sees them-can make a...
Related: #AI Security, #LLM Vulnerabilities -
🇺🇸 Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse
[USA]
arXiv:2604.06228v1 Announce Type: cross Abstract: We introduce probabilistic language tries (PLTs), a unified representation that makes explicit the prefix structure implicitly defined by any generat...
Related: #Artificial Intelligence, #Data Compression -
🇺🇸 The logic of KM belief update is contained in the logic of AGM belief revision
[USA]
arXiv:2602.23302v1 Announce Type: new Abstract: For each axiom of KM belief update we provide a corresponding axiom in a modal logic containing three modal operators: a unimodal belief operator $B$, ...
Related: #Artificial Intelligence, #Logic Systems, #Belief Revision -
🇺🇸 Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function
[USA]
arXiv:2602.22255v1 Announce Type: cross Abstract: We introduce a sequence modeling framework in which the latent state is a complex-valued wave function evolving on a finite-dimensional Hilbert space...
Related: #Quantum Computing, #Machine Learning, #Natural Language Processing -
🇺🇸 VINA: Variational Invertible Neural Architectures
[USA]
arXiv:2602.20480v1 Announce Type: cross Abstract: The distinctive architectural features of normalizing flows (NFs), notably bijectivity and tractable Jacobians, make them well-suited for generative ...
Related: #Machine Learning, #Neural Networks, #Scientific Research -
🇺🇸 Rational Neural Networks have Expressivity Advantages
[USA]
arXiv:2602.12390v1 Announce Type: cross Abstract: We study neural networks with trainable low-degree rational activation functions and show that they are more expressive and parameter-efficient than ...
Related: #Neural Network Architecture, #Computational Efficiency
Key Entities (7)
- Wave function (1 news)
- Hamiltonian (1 news)
- Machine learning (1 news)
- Expressivity (1 news)
- Neural network (1 news)
- Approximation theory (1 news)
- Unified framework (1 news)
About the topic: Theoretical Computer Science
The topic "Theoretical Computer Science" aggregates 6+ news articles from various countries.