Pith. sign in

REVIEW 6 cited by

Liquid Structural State-Space Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.12951 v1 pith:I3A2TYCS submitted 2022-09-26 cs.LG cs.AIcs.CLcs.CVcs.NE

Ramin Hasani , Mathias Lechner , Tsun-Hsuan Wang , Makram Chahine , Alexander Amini , Daniela Rus This is my paper
classification cs.LGcs.AIcs.CLcs.CVcs.NE
keywords state-spaceliquid-s4sequencestatestructuraltransitionachievesinference
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A proper parametrization of state transition matrices of linear state-space models (SSMs) followed by standard nonlinearities enables them to efficiently learn representations from sequential data, establishing the state-of-the-art on a large series of long-range sequence modeling benchmarks. In this paper, we show that we can improve further when the structural SSM such as S4 is given by a linear liquid time-constant (LTC) state-space model. LTC neural networks are causal continuous-time neural networks with an input-dependent state transition module, which makes them learn to adapt to incoming inputs at inference. We show that by using a diagonal plus low-rank decomposition of the state transition matrix introduced in S4, and a few simplifications, the LTC-based structural state-space model, dubbed Liquid-S4, achieves the new state-of-the-art generalization across sequence modeling tasks with long-term dependencies such as image, text, audio, and medical time-series, with an average performance of 87.32% on the Long-Range Arena benchmark. On the full raw Speech Command recognition, dataset Liquid-S4 achieves 96.78% accuracy with a 30% reduction in parameter counts compared to S4. The additional gain in performance is the direct result of the Liquid-S4's kernel structure that takes into account the similarities of the input sequence samples during training and inference.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DSSMs: State Space Models with Explicit Memory via Delay Differential Equations

    cs.LG 2026-07 conditional novelty 6.5 of 10

    Delay State Space Models augment diagonal SSMs with explicit delayed feedback, stable discrete parameterization, and FFT training, improving delayed-retrieval tasks and matching or beating S4D on most standard sequenc...

  2. Partial Ring Scan: Revisiting Scan Order in Vision State Space Models

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Ring-based scanning with selective channel routing improves accuracy, speed, and rotation robustness of vision state-space models.

  3. Systolic Array-based Accelerator for Structured State-Space Models

    cs.LG 2025-07 reject novelty 6.0 of 10

    A specialized systolic-array accelerator with a reconfigurable processing element and diagonal dataflow claims 2000x inference speedup over GPUs for S4 and Liquid-S4 state-space models.

  4. MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MUG combines manually corrected pseudo-labels, cross-modal random track recombination, and a Mamba-Transformer network to reach new state-of-the-art F1 scores on the LLP audio-visual video parsing benchmark.

  5. Prototype-Driven Structure Synergy Network for Remote Sensing Images Segmentation

    cs.CV 2025-08 conditional novelty 5.0 of 10

    PDSSNet reports state-of-the-art mIoU of 84.68, 87.55, and 56.10 on the Vaihingen, Potsdam, and LoveDA remote sensing datasets by combining GT-derived prototypes, a Mamba-style semantic-structure module, and a similar...

  6. Word2Spike: Poisson Rate Coding for Associative Memories and Neuromorphic Algorithms

    cs.NE 2025-09 reject novelty 2.0 of 10

    Word2Spike proposes a ternary quantization plus Poisson rate coding scheme for word embeddings, reporting 100% reconstruction on 10k words.

Pith tools