Stefano Massaroli

Sliding Window Recurrences for Sequence Models

Garyk Brixi

Taiji Suzuki

Michael Poli

Multi-hybrid architectures are poised to take over language modeling due to better quality and performance. We introduce a hierarchical deco… (voir plus)mposition framework for linear recurrences that allows us to develop algorithms aligned with GPU memory hierarchies, yielding Sliding Window Recurrences. We focus specifically on truncating recurrences to hardware-aligned windows which are naturally jagged, limiting costly inter-warp communication. Using SWR, we develop Phalanx layers that serve as drop-in replacements for windowed attention or linear recurrences. In 1B parameter multi-hybrid models, Phalanx achieves over 10-40% speedup across 4K to 32K context length over optimized Transformers while matching perplexity.

2025-12-14

arXiv (prépublication)

doi.org

arxiv.org

Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context

Ghait Boukachab

Solar power harbors immense potential in mitigating climate change by substantially reducing CO…

2023-12-11

Advances in Neural Information Processing Systems (Accept (poster))

doi.org

openreview.net

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

Eric Nguyen

Michael Poli

Marjan Faizi

Armin W Thomas

Callum Birch-Sykes

Michael Wornow

Aman Patel

Clayton M. Rabideau

Stefano Massaroli

Yoshua Bengio

Stefano Ermon

Stephen Baccus

Christopher Re

2023-09-20

NeurIPS.cc/2023/Conference (spotlight)

doi.org

openreview.net

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions

Stefano Massaroli

Michael Poli

Daniel Y Fu

Hermann Kumbong

Rom Nishijima Parnichkun

Aman Timalsina

David W. Romero

Quinn McIntyre

Beidi Chen

Atri Rudra

Ce Zhang

Christopher Re

Stefano Ermon

Yoshua Bengio

Recent advances in attention-free sequence models rely on convolutions as alternatives to the attention operator at the core of Transformers… (voir plus). In particular, long convolution sequence models have achieved state-of-the-art performance in many domains, but incur a significant cost during auto-regressive inference workloads -- naively requiring a full pass (or caching of activations) over the input sequence for each generated token -- similarly to attention-based models. In this paper, we seek to enable

2023-09-20

NeurIPS.cc/2023/Conference (poster)

doi.org

openreview.net

Hyena Hierarchy: Towards Larger Convolutional Language Models

Michael Poli

Stefano Massaroli

Eric Nguyen

Daniel Y Fu

Tri Dao

Stephen Baccus

Yoshua Bengio