Publications

35 results for Michael Hersche

Locally Coherent Parallel Decoding in Diffusion Language Models
- - Michael Hersche
  - Nicolas Menet
  - et al.
- 2026
- ICML 2026
Conference paper
A foundation model with multi-variate parallel attention to generate neuronal activity
- - Francesco Carzaniga
  - Michael Hersche
  - et al.
- 2026
- ICLR 2026
Conference paper
Soft-Masked Diffusion Language Models
- - Michael Hersche
  - Samuel Moor
  - et al.
- 2026
- ICLR 2026
Conference paper
THOMPSON SAMPLING VIA FINE-TUNING OF LLMS
- - Nicolas Menet
  - Aleksandar Terzic
  - et al.
- 2026
- ICLR 2026
Conference paper
Scalable Evaluation and Neural Models for Compositional Generalization
- - Giacomo Camposampiero
  - Pietro Barbiero
  - et al.
- 2025
- NeurIPS 2025
Conference paper
Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
- - Aleksandar Terzic
  - Nicolas Menet
  - et al.
- 2025
- NeurIPS 2025
Conference paper
I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Models
- - Giacomo Camposampiero
  - Michael Hersche
  - et al.
- 2025
- NeurIPS 2025
Workshop paper
A foundation model with multi-variate parallel attention to generate neuronal activity
- - Francesco Carzaniga
  - Michael Hersche
  - et al.
- 2025
- NeurIPS 2025
Workshop paper
Practical Lessons on Vector-Symbolic Architectures in Deep Learning-Inspired Environments
- - Francesco Carzaniga
  - Michael Hersche
  - et al.
- 2025
- NeSy 2025
Conference paper
Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?
- - Giacomo Camposampiero
  - Michael Hersche
  - et al.
- 2025
- NeSy 2025
Conference paper