activity
20242026
collaborators

6 papers

cs.AI2026

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta +4

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations…

cs.LG2026

TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics

Alexander Kyuroson, Denis Kleyko, Marcus Liwicki

Recent Continuous Thought Machine architecture decouples internal computation from external inputs via neural dynamics, but relies on multi-layer perceptrons without stability guar…

cs.LG2026

Contextual Bandits for Resource-Constrained Devices using Probabilistic Learning

Marco Angioli, Kevin Johansson, Antonello Rosato +2

Contextual bandits (CB) are online sequential decision-making problems under partial feedback that underpin many adaptive services. There is a growing demand to deploy CB agents di…

cs.NE2025

Towards a Comprehensive Theory of Reservoir Computing

Denis Kleyko, Christopher J. Kymn, E. Paxon Frady +2

In reservoir computing, an input sequence is processed by a recurrent neural network, the reservoir, which transforms it into a spatial pattern that a shallow readout network can t…

cs.LG2025

Efficient Hyperdimensional Computing with Modular Composite Representations

Marco Angioli, Christopher J. Kymn, Antonello Rosato +3

The modular composite representation (MCR) is a computing model that represents information with high-dimensional integer vectors using modular arithmetic. Originally proposed as a…

cs.NE2024

On Design Choices in Similarity-Preserving Sparse Randomized Embeddings

Denis Kleyko, Dmitri A. Rachkovskij

Expand & Sparsify is a principle that is observed in anatomically similar neural circuits found in the mushroom body (insects) and the cerebellum (mammals). Sensory data are projec…