# raminmh/liquid_time_constant_networks

Code Repository for Liquid Time-Constant Networks (LTCs)

Repository: https://github.com/raminmh/liquid_time_constant_networks
Canonical: https://ross.abutalabs.com/products/liquid_time_constant_networks
Homepage: https://arxiv.org/abs/2006.04439
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, liquid-neural-networks, recurrent-neural-networks, sequence-modeling, state-space-models, time-series
Last push: 2024-06-03T17:18:14+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2296, "days_push": 821, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1857, forks 335 (observed 2026-08-28T04:05:44.997671+00:00)

## What it is
Official code repository for Liquid Time-Constant Networks (LTCs), a class of continuous-time recurrent neural networks with varying time-constants, from the AAAI-21 paper. It provides TensorFlow implementations of LTCs alongside Neural ODEs, CT-RNNs, and continuous-time GRUs, with training scripts for several time-series datasets.

## Use cases
- train liquid time-constant networks on time-series data
- compare LTCs against LSTMs and CT-RNNs for sequence modeling
- reproduce results from the LTC research paper
- experiment with continuous-time recurrent models like neural ODEs
- benchmark RNN variants on activity recognition and forecasting datasets

## When to choose
- you want to experiment with or reproduce research on liquid neural networks and continuous-time RNNs
- you need reference TensorFlow 1.x implementations of LTC, Neural ODE, CT-RNN, and CT-GRU models
- you are doing academic work on time-series sequence modeling

## When to avoid
- you need a production-ready or maintained library - use the sister repository mlech26l/ncps with PyTorch support instead
- you are on modern TensorFlow 2.x or PyTorch and cannot use TensorFlow 1.14
- you need general-purpose deep learning tooling rather than research code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, data-science, time-series
- platform: python
- tags: liquid-neural-networks, recurrent-neural-networks, neural-odes, time-series, research-code, tensorflow, state-space-models, linux

## Member repositories
- raminmh/liquid_time_constant_networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:44.997671+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:16:37.483647+00:00, confidence not recorded.
  - readme: https://github.com/raminmh/liquid_time_constant_networks (fetched 2026-08-28T04:05:44.997671+00:00, sha d8a4ab7c6877)
  - homepage: https://arxiv.org/abs/2006.04439 (fetched 2026-08-29T10:55:36.283894+00:00, sha f1d30d2acd39)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T10:55:36.293243+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T10:55:36.296781+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T10:55:36.298726+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T10:55:36.295021+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.