Methods › General › Robust Training › DEQ

Deep Equilibrium Models

DEQ

42 papers tagged archive 2025-07-28

Introduced by Shaojie Bai et al. in Deep Equilibrium Models

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A new kind of implicit models, where the output of the network is defined as the solution to an "infinite-level" fixed point equation. Thanks to this we can compute the gradient of the output without activations and therefore with a significantly reduced memory footprint.

PaperSource

Papers archive 2025-07-28

30 shown of 42, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 29 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Adversarial Robustness3
Denoising3
Language Modeling3
Language Modelling3
Adversarial Defense2
Image Reconstruction2
Object Detection2
object-detection2
Benchmarking1
Bilevel Optimization1
Decoder1
Face Alignment1
Federated Learning1
Gaussian Processes1
Generalization Bounds1
Hyperparameter Optimization1
Image Restoration1
Meta-Learning1
Object1
Optical Flow Estimation1

Usage over time archive 2025-07-28

Papers per year tagged with DEQ: 2019 to 2025, peak 16 16 0 2019: 1 paper 2019 2020: 0 papers 2020 2021: 7 papers 2021 2022: 9 papers 2022 2023: 16 papers 2023 2024: 5 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (42 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Robust Training

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections