MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in SuperpositionNicolas MenetMichael Herscheet al.2023NeurIPS 2023
Limits of Transformer Language Models on Learning to Compose AlgorithmsJonathan ThommAleksandar Terzicet al.2024NeurIPS 2024
Recurrent Transformers Trade-off Parallelism for Length Generalization on Regular LanguagesPaul SoulosAleksandar Terzicet al.2024NeurIPS 2024
TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence ProcessingAleksandar TerzicMichael Herscheet al.2023NeurIPS 2023
Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic ArchitecturesMichael HerscheFrancesco Di Stefanoet al.2023NeurIPS 2023
On the role of noise in factorizers for disentangling distributed representationsKumudu Geethan KarunaratneMichael Herscheet al.2024NeurIPS 2024
Generalized Key-Value Memory to Flexibly Adjust Redundancy in Memory-Augmented NetworksDenis KleykoKumudu Geethan Karunaratneet al.2022IEEE TNNLS
RETRO-LI: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift GeneralizationGentiana RashitiKumudu Geethan Karunaratneet al.2024ECAI 2024
Towards Learning Abductive Reasoning using VSA Distributed RepresentationsGiacomo CamposampieroMichael Herscheet al.2024NeSy 2024