Scalable Evaluation and Neural Models for Compositional GeneralizationGiacomo CamposampieroPietro Barbieroet al.2025NeurIPS 2025
Structured Sparse Transition Matrices to Enable State Tracking in State-Space ModelsAleksandar TerzicNicolas Menetet al.2025NeurIPS 2025
I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning ModelsGiacomo CamposampieroMichael Herscheet al.2025NeurIPS 2025
A foundation model with multi-variate parallel attention to generate neuronal activityFrancesco CarzanigaMichael Herscheet al.2025NeurIPS 2025
Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?Giacomo CamposampieroMichael Herscheet al.2025NeSy 2025
Practical Lessons on Vector-Symbolic Architectures in Deep Learning-Inspired EnvironmentsFrancesco CarzanigaMichael Herscheet al.2025NeSy 2025
The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEGFrancesco CarzanigaGary Hoppeleret al.2025ICLR 2025
THE CASE FOR CLEANER BIOSIGNALS: HIGH-FIDELITY NEURAL COMPRESSOR ENABLES TRANSFER FROM CLEANER IEEG TO NOISIER EEGFrancesco S. CarzanigaGary Hoppeleret al.2025ICLR 2025
On the Expressiveness and Length Generalization of Selective State-Space Models on Regular LanguagesAleksandar TerzićMichael Herscheet al.2025AAAI 2025
A Composable Channel-Adaptive Architecture for Seizure ClassificationFrancesco S. CarzanigaMichael Herscheet al.2025IEEE J-BHI