Michael Hersche

65 papers A* 5A 4B 2C 6Journal 38Unranked 8

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Composable Channel-Adaptive Architecture for Seizure Classification. IEEE J. Biomed. Health Informatics Francesco S. Carzaniga, Michael Hersche, Kaspar Schindler, Abbas Rahimi
2026	J	`jnl`	Coding Agents with Environment Interaction: A Theoretical Perspective. CoRR Nicolas Menet, Michael Hersche, Andreas Krause, Abbas Rahimi
2026	J	`jnl`	Locally Coherent Parallel Decoding in Diffusion Language Models. CoRR Michael Hersche, Nicolas Menet, Ronan Tanios, Abbas Rahimi
2025	J	`jnl`	A Composable Channel-Adaptive Architecture for Seizure Classification. CoRR Francesco S. Carzaniga, Michael Hersche, Kaspar Anton Schindler, Abbas Rahimi
2025	J	`jnl`	A foundation model with multi-variate parallel attention to generate neuronal activity. CoRR Francesco S. Carzaniga, Michael Hersche, Abu Sebastian, Kaspar Anton Schindler, Abbas Rahimi
2025	C	`conf`	Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty? NeSy Giacomo Camposampiero, Michael Hersche, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
2025	J	`jnl`	Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty? CoRR Giacomo Camposampiero, Michael Hersche, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
2025	J	`jnl`	I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Models. CoRR Giacomo Camposampiero, Michael Hersche, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
2025	A*	`conf`	On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages. AAAI Aleksandar Terzic, Michael Hersche, Giacomo Camposampiero, Thomas Hofmann, Abu Sebastian, Abbas Rahimi
2025	C	`conf`	Practical Lessons on Vector-Symbolic Architectures in Deep Learning-Inspired Environments. NeSy Francesco S. Carzaniga, Michael Hersche, Kaspar Schindler, Abbas Rahimi
2025	J	`jnl`	Scalable Evaluation and Neural Models for Compositional Generalization. CoRR Giacomo Camposampiero, Pietro Barbiero, Michael Hersche, Roger Wattenhofer, Abbas Rahimi
2025	J	`jnl`	Soft-Masked Diffusion Language Models. CoRR Michael Hersche, Samuel Moor-Smith, Thomas Hofmann, Abbas Rahimi
2025	J	`jnl`	Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models. CoRR Aleksandar Terzic, Nicolas Menet, Michael Hersche, Thomas Hofmann, Abbas Rahimi
2025	A*	`conf`	The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEG. ICLR Francesco S. Carzaniga, Gary Tom Hoppeler, Michael Hersche, Kaspar Schindler, Abbas Rahimi
2025	J	`jnl`	The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEG. CoRR Francesco S. Carzaniga, Gary Tom Hoppeler, Michael Hersche, Kaspar Anton Schindler, Abbas Rahimi
2025	J	`jnl`	Thompson Sampling via Fine-Tuning of LLMs. CoRR Nicolas Menet, Aleksandar Terzic, Michael Hersche, Andreas Krause, Abbas Rahimi
2024	A	`conf`	12 mJ Per Class On-Device Online Few-Shot Class-Incremental Learning. DATE Yoga Esa Wibowo, Cristian Cioflan, Thorir Mar Ingolfsson, Michael Hersche, Leo Zhao, Abbas Rahimi, Luca Benini
2024	J	`jnl`	12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning. CoRR Yoga Esa Wibowo, Cristian Cioflan, Thorir Mar Ingolfsson, Michael Hersche, Leo Zhao, Abbas Rahimi, Luca Benini
2024	A*	`conf`	Limits of Transformer Language Models on Learning to Compose Algorithms. NeurIPS Jonathan Thomm, Giacomo Camposampiero, Aleksandar Terzic, Michael Hersche, Bernhard Schölkopf, Abbas Rahimi
2024	J	`jnl`	On the Expressiveness and Length Generalization of Selective State-Space Models on Regular Languages. CoRR Aleksandar Terzic, Michael Hersche, Giacomo Camposampiero, Thomas Hofmann, Abu Sebastian, Abbas Rahimi
2024	J	`jnl`	On the Role of Noise in Factorizers for Disentangling Distributed Representations. CoRR Geethan Karunaratne, Michael Hersche, Abu Sebastian, Abbas Rahimi
2024	J	`jnl`	Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures. CoRR Michael Hersche, Francesco Di Stefano, Thomas Hofmann, Abu Sebastian, Abbas Rahimi
2024	—	`conf`	Terminating Differentiable Tree Experts. NeSy (1) Jonathan Thomm, Michael Hersche, Giacomo Camposampiero, Aleksandar Terzic, Bernhard Schölkopf, Abbas Rahimi
2024	J	`jnl`	Terminating Differentiable Tree Experts. CoRR Jonathan Thomm, Michael Hersche, Giacomo Camposampiero, Aleksandar Terzic, Bernhard Schölkopf, Abbas Rahimi
2024	—	`conf`	Towards Learning Abductive Reasoning Using VSA Distributed Representations. NeSy (1) Giacomo Camposampiero, Michael Hersche, Aleksandar Terzic, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
2024	J	`jnl`	Towards Learning Abductive Reasoning using VSA Distributed Representations. CoRR Giacomo Camposampiero, Michael Hersche, Aleksandar Terzic, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
2024	J	`jnl`	Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning. CoRR Michael Hersche, Giacomo Camposampiero, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
2024	A	`conf`	Zero-Shot Classification Using Hyperdimensional Computing. DATE Samuele Ruffino, Geethan Karunaratne, Michael Hersche, Luca Benini, Abu Sebastian, Abbas Rahimi
2024	J	`jnl`	Zero-shot Classification using Hyperdimensional Computing. CoRR Samuele Ruffino, Geethan Karunaratne, Michael Hersche, Luca Benini, Abu Sebastian, Abbas Rahimi
2023	J	`jnl`	A neuro-vector-symbolic architecture for solving Raven's progressive matrices. Nat. Mac. Intell. Michael Hersche, Mustafa Zeqiri, Luca Benini, Abu Sebastian, Abbas Rahimi
2023	C	`conf`	Decoding Superpositions of Bound Symbols Represented by Distributed Representations. NeSy Michael Hersche, Zuzanna Opala, Geethan Karunaratne, Abu Sebastian, Abbas Rahimi
2023	J	`jnl`	Factorizers for Distributed Sparse Block Codes. CoRR Michael Hersche, Aleksandar Terzic, Geethan Karunaratne, Jovin Langenegger, Angéline Pouget, Giovanni Cherubini, Luca Benini, Abu Sebastian, Abbas Rahimi
2023	—	`ch.`	Few-Shot Continual Learning Based on Vector Symbolic Architectures. Compendium of Neurosymbolic Artificial Intelligence Geethan Karunaratne, Michael Hersche, Giovanni Cherubini, Abu Sebastian, Abbas Rahimi
2023	A*	`conf`	MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition. NeurIPS Nicolas Menet, Michael Hersche, Geethan Karunaratne, Luca Benini, Abu Sebastian, Abbas Rahimi
2023	J	`jnl`	MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition. CoRR Nicolas Menet, Michael Hersche, Geethan Karunaratne, Luca Benini, Abu Sebastian, Abbas Rahimi
2023	—	`—`	Neuro-vector-symbolic architectures: Exploring computation in superposition for perception, reasoning, and combinatorial search. Michael Hersche
2023	C	`conf`	Solving Raven's Progressive Matrices via a Neuro-vector-symbolic Architecture. NeSy Michael Hersche, Mustafa Zeqiri, Luca Benini, Abu Sebastian, Abbas Rahimi
2023	J	`jnl`	TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence Processing. CoRR Aleksandar Terzic, Michael Hersche, Geethan Karunaratne, Luca Benini, Abu Sebastian, Abbas Rahimi
2023	C	`conf`	VSA-based Positional Encoding Can Replace Recurrent Networks in Emergent Symbol Binding. NeSy Francesco S. Carzaniga, Michael Hersche, Kaspar Schindler, Abbas Rahimi
2022	J	`jnl`	A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices. CoRR Michael Hersche, Mustafa Zeqiri, Luca Benini, Abu Sebastian, Abbas Rahimi
2022	A*	`conf`	Constrained Few-shot Class-incremental Learning. CVPR Michael Hersche, Geethan Karunaratne, Giovanni Cherubini, Luca Benini, Abu Sebastian, Abbas Rahimi
2022	J	`jnl`	Constrained Few-shot Class-incremental Learning. CoRR Michael Hersche, Geethan Karunaratne, Giovanni Cherubini, Luca Benini, Abu Sebastian, Abbas Rahimi
2022	—	`conf`	In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory. ESSCIRC Geethan Karunaratne, Michael Hersche, Jovin Langenegger, Giovanni Cherubini, Manuel Le Gallo, Urs Egger, Kevin Brew, Samuel Choi, Injo Ok, Mary Claire Silvestre, Ning Li, Nicole Saulnier, Victor Chan, Ishtiaq Ahsan, Vijay Narayanan, Luca Benini, Abu Sebastian, Abbas Rahimi
2022	J	`jnl`	In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory. CoRR Geethan Karunaratne, Michael Hersche, Jovin Langenegger, Giovanni Cherubini, Manuel Le Gallo, Urs Egger, Kevin Brew, Samuel Choi, Injo Ok, Mary Claire Silvestre, Ning Li, Nicole Saulnier, Victor Chan, Ishtiaq Ahsan, Vijay Narayanan, Luca Benini, Abu Sebastian, Abbas Rahimi
2022	J	`jnl`	In-memory factorization of holographic perceptual representations. CoRR Jovin Langenegger, Geethan Karunaratne, Michael Hersche, Luca Benini, Abu Sebastian, Abbas Rahimi
2021	—	`conf`	ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network. AICAS Thorir Mar Ingolfsson, Xiaying Wang, Michael Hersche, Alessio Burrello, Lukas Cavigelli, Luca Benini
2021	J	`jnl`	ECG-TCN: Wearable Cardiac Arrhythmia Detection with a Temporal Convolutional Network. CoRR Thorir Mar Ingolfsson, Xiaying Wang, Michael Hersche, Alessio Burrello, Lukas Cavigelli, Luca Benini
2021	J	`jnl`	Energy Efficient In-Memory Hyperdimensional Encoding for Spatio-Temporal Signal Processing. IEEE Trans. Circuits Syst. II Express Briefs Geethan Karunaratne, Manuel Le Gallo, Michael Hersche, Giovanni Cherubini, Luca Benini, Abu Sebastian, Abbas Rahimi
2021	J	`jnl`	Energy Efficient In-memory Hyperdimensional Encoding for Spatio-temporal Signal Processing. CoRR Geethan Karunaratne, Manuel Le Gallo, Michael Hersche, Giovanni Cherubini, Luca Benini, Abu Sebastian, Abbas Rahimi
2021	C	`conf`	Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain-Machine Interfaces. ISCAS Xiaying Wang, Tibor Schneider, Michael Hersche, Lukas Cavigelli, Luca Benini
2021	J	`jnl`	Near-channel classifier: symbiotic communication and classification in high-dimensional space. Brain Informatics Michael Hersche, Stefan Lippuner, Matthias Korb, Luca Benini, Abbas Rahimi
2020	—	`conf`	An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computing. MeMeA Xiaying Wang, Michael Hersche, Batuhan Tömekce, Burak Kaya, Michele Magno, Luca Benini
2020	J	`jnl`	An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computing. CoRR Xiaying Wang, Michael Hersche, Batuhan Tömekce, Burak Kaya, Michele Magno, Luca Benini
2020	J	`jnl`	Binarization Methods for Motor-Imagery Brain-Computer Interface Classification. CoRR Michael Hersche, Luca Benini, Abbas Rahimi
2020	J	`jnl`	Binarization Methods for Motor-Imagery Brain-Computer Interface Classification. IEEE J. Emerg. Sel. Topics Circuits Syst. Michael Hersche, Luca Benini, Abbas Rahimi
2020	—	`conf`	Binary Models for Motor-Imagery Brain-Computer Interfaces: Sparse Random Projection and Binarized SVM. AICAS Michael Hersche, Luca Benini, Abbas Rahimi
2020	A	`conf`	Compressing Subject-specific Brain-Computer Interface Models into One Model by Superposition in Hyperdimensional Space. DATE Michael Hersche, Philipp Rupp, Luca Benini, Abbas Rahimi
2020	B	`conf`	EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces. SMC Thorir Mar Ingolfsson, Michael Hersche, Xiaying Wang, Nobuaki Kobayashi, Lukas Cavigelli, Luca Benini
2020	J	`jnl`	EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces. CoRR Thorir Mar Ingolfsson, Michael Hersche, Xiaying Wang, Nobuaki Kobayashi, Lukas Cavigelli, Luca Benini
2020	—	`conf`	Evolvable Hyperdimensional Computing: Unsupervised Regeneration of Associative Memory to Recover Faulty Components. AICAS Michael Hersche, Sara Sangalli, Luca Benini, Abbas Rahimi
2020	A	`conf`	Integrating event-based dynamic vision sensors with sparse hyperdimensional computing: a low-power accelerator with online learning capability. ISLPED Michael Hersche, Edoardo Mello Rella, Alfio Di Mauro, Luca Benini, Abbas Rahimi
2020	B	`conf`	Q-EEGNet: an Energy-Efficient 8-bit Quantized Parallel EEGNet Implementation for Edge Motor-Imagery Brain-Machine Interfaces. SMARTCOMP Tibor Schneider, Xiaying Wang, Michael Hersche, Lukas Cavigelli, Luca Benini
2020	J	`jnl`	Q-EEGNet: an Energy-Efficient 8-bit Quantized Parallel EEGNet Implementation for Edge Motor-Imagery Brain-Machine Interfaces. CoRR Tibor Schneider, Xiaying Wang, Michael Hersche, Lukas Cavigelli, Luca Benini
2018	J	`jnl`	Exploring Embedding Methods in Binary Hyperdimensional Computing: A Case Study for Motor-Imagery based Brain-Computer Interfaces. CoRR Michael Hersche, José del R. Millán, Luca Benini, Abbas Rahimi
2018	—	`conf`	Fast and Accurate Multiclass Inference for MI-BCIs Using Large Multiscale Temporal and Spectral Features. EUSIPCO Michael Hersche, Tino Rellstab, Pasquale Davide Schiavone, Lukas Cavigelli, Luca Benini, Abbas Rahimi