@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{bo_liu_iclr_2025,
  author   = {Bo Liu and Rui Wang and Lemeng Wu and Yihao Feng and Peter Stone and qiang liu},
  title    = {Longhorn: State Space Models are Amortized Online Learners},
  booktitle = {International Conference on Learning Representations},
  year     = {2025},
  month    = {April},
  location = {Singapore},
  abstract = {The most fundamental capability of modern AI methods such as Large Language
Models (LLMs) is the ability to predict the next token in a long sequence of
tokens, known as “sequence modeling.” Although the Transformers model is the
current dominant approach to sequence modeling, its quadratic computational cost
with respect to sequence length is a significant drawback. State-space models
(SSMs) offer a promising alternative due to their linear decoding efficiency and
high parallelizability during training. However, existing SSMs often rely on
seemingly ad hoc linear recurrence designs. In this work, we explore SSM design
through the lens of online learning, conceptualizing SSMs as meta-modules for
specific online learning problems. This approach links SSM design to formulating
precise online learning objectives, with state transition rules derived from
optimizing these objectives. Based on this insight, we introduce a novel deep SSM
architecture based on the implicit update for optimizing an online regression
objective. Our experimental results show that our models outperform
state-of-the-art SSMs, including the Mamba model, on standard sequence modeling
benchmarks and language modeling tasks.
  },
}