{"url":"/method/deq","slug":"deq","name":"DEQ","full_name":"Deep Equilibrium Models","full_name_withheld":false,"description_markdown":"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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Deep Equilibrium Models","paper":"/paper/deep-equilibrium-models","first_author":"Shaojie Bai","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deep-equilibrium-models"},"source":{"url":"https://arxiv.org/abs/1909.01377v2","title":"Deep Equilibrium Models","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Robust Training","url":"/methods/category/robust-training","pwc_aliases":[]}],"n_papers_tagged":42,"archive_num_papers":42,"papers_newest_first":[{"paper":"/paper/deep-equilibrium-models-for-poisson-imaging","title":"Deep Equilibrium models for Poisson Imaging Inverse problems via Mirror Descent","date":"2025-07-15","arxiv_id":"2507.11461","n_code_links":1,"syntology":null},{"paper":null,"title":"Restarted contractive operators to learn at equilibrium","date":"2025-06-16","arxiv_id":"2506.13239","n_code_links":0,"syntology":null},{"paper":"/paper/ddeqs-distributional-deep-equilibrium-models","title":"DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows","date":"2025-03-03","arxiv_id":"2503.01140","n_code_links":1,"syntology":null},{"paper":null,"title":"Neural Cellular Automata and Deep Equilibrium Models","date":"2025-01-07","arxiv_id":"2501.03573","n_code_links":0,"syntology":null},{"paper":"/paper/a-peaceman-rachford-splitting-approach-with","title":"A Peaceman-Rachford Splitting Approach with Deep Equilibrium Network for Channel Estimation","date":"2024-10-31","arxiv_id":"2410.23752","n_code_links":1,"syntology":null},{"paper":null,"title":"Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective","date":"2024-10-30","arxiv_id":"2410.23391","n_code_links":0,"syntology":null},{"paper":"/paper/infusing-self-consistency-into-density","title":"Infusing Self-Consistency into Density Functional Theory Hamiltonian Prediction via Deep Equilibrium Models","date":"2024-06-06","arxiv_id":"2406.03794","n_code_links":1,"syntology":{"ran":10,"of":14,"unverified":4,"pointer_only":14}},{"paper":"/paper/positive-concave-deep-equilibrium-models","title":"Positive concave deep equilibrium models","date":"2024-02-06","arxiv_id":"2402.04029","n_code_links":1,"syntology":null},{"paper":"/paper/deep-equilibrium-models-are-almost-equivalent","title":"Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures","date":"2024-02-05","arxiv_id":"2402.02697","n_code_links":1,"syntology":{"ran":11,"of":14,"unverified":3,"pointer_only":14}},{"paper":"/paper/one-step-diffusion-distillation-via-deep-1","title":"One-Step Diffusion Distillation via Deep Equilibrium Models","date":"2023-12-12","arxiv_id":"2401.08639","n_code_links":1,"syntology":{"ran":4,"of":6,"unverified":2,"pointer_only":0}},{"paper":"/paper/accelerating-hierarchical-associative-memory","title":"Accelerating Hopfield Network Dynamics: Beyond Synchronous Updates and Forward Euler","date":"2023-11-27","arxiv_id":"2311.15673","n_code_links":2,"syntology":null},{"paper":"/paper/deep-equilibrium-diffusion-restoration-with","title":"Deep Equilibrium Diffusion Restoration with Parallel Sampling","date":"2023-11-20","arxiv_id":"2311.11600","n_code_links":1,"syntology":{"ran":19,"of":22,"unverified":3,"pointer_only":22}},{"paper":"/paper/torchdeq-a-library-for-deep-equilibrium","title":"TorchDEQ: A Library for Deep Equilibrium Models","date":"2023-10-28","arxiv_id":"2310.18605","n_code_links":1,"syntology":{"ran":7,"of":13,"unverified":6,"pointer_only":0}},{"paper":null,"title":"On the Neural Tangent Kernel of Equilibrium Models","date":"2023-10-21","arxiv_id":"2310.14062","n_code_links":0,"syntology":null},{"paper":null,"title":"Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models","date":"2023-10-16","arxiv_id":"2310.10767","n_code_links":0,"syntology":null},{"paper":"/paper/deep-equilibrium-object-detection","title":"Deep Equilibrium Object Detection","date":"2023-08-18","arxiv_id":"2308.09564","n_code_links":1,"syntology":{"ran":7,"of":7,"unverified":0,"pointer_only":7}},{"paper":null,"title":"Revisiting Implicit Models: Sparsity Trade-offs Capability in Weight-tied Model for Vision Tasks","date":"2023-07-16","arxiv_id":"2307.08013","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep Equilibrium Multimodal Fusion","date":"2023-06-29","arxiv_id":"2306.16645","n_code_links":0,"syntology":null},{"paper":"/paper/a-closer-look-at-the-adversarial-robustness-1","title":"A Closer Look at the Adversarial Robustness of Deep Equilibrium Models","date":"2023-06-02","arxiv_id":"2306.01429","n_code_links":1,"syntology":null},{"paper":"/paper/improving-adversarial-robustness-of-deqs-with","title":"Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamics","date":"2023-06-02","arxiv_id":"2306.01435","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":null,"title":"Deep Equilibrium Models Meet Federated Learning","date":"2023-05-29","arxiv_id":"2305.18646","n_code_links":0,"syntology":null},{"paper":null,"title":"Lyapunov-Stable Deep Equilibrium Models","date":"2023-04-25","arxiv_id":"2304.12707","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-training-of-deep-equilibrium-models","title":"Efficient Training of Deep Equilibrium Models","date":"2023-04-23","arxiv_id":"2304.11663","n_code_links":1,"syntology":{"ran":5,"of":8,"unverified":3,"pointer_only":2}},{"paper":"/paper/recurrence-without-recurrence-stable-video","title":"Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models","date":"2023-04-02","arxiv_id":"2304.00600","n_code_links":1,"syntology":{"ran":6,"of":10,"unverified":4,"pointer_only":10}},{"paper":"/paper/deep-equilibrium-learning-of-explicit","title":"Deep Equilibrium Learning of Explicit Regularizers for Imaging Inverse Problems","date":"2023-03-09","arxiv_id":"2303.05386","n_code_links":1,"syntology":null},{"paper":"/paper/deep-equilibrium-models-as-estimators-for","title":"Deep equilibrium models as estimators for continuous latent variables","date":"2022-11-11","arxiv_id":"2211.05943","n_code_links":1,"syntology":null},{"paper":null,"title":"Robustness of Deep Equilibrium Architectures to Changes in the Measurement Model","date":"2022-11-01","arxiv_id":"2211.00531","n_code_links":0,"syntology":null},{"paper":"/paper/deep-equilibrium-approaches-to-diffusion","title":"Deep Equilibrium Approaches to Diffusion Models","date":"2022-10-23","arxiv_id":"2210.12867","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Self-Supervised Deep Equilibrium Models for Inverse Problems with Theoretical Guarantees","date":"2022-10-07","arxiv_id":"2210.03837","n_code_links":0,"syntology":null},{"paper":"/paper/online-deep-equilibrium-learning-for","title":"Online Deep Equilibrium Learning for Regularization by Denoising","date":"2022-05-25","arxiv_id":"2205.13051","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":3},{"task":"/task/denoising","name":"Denoising","papers":3},{"task":"/task/language-modeling","name":"Language Modeling","papers":3},{"task":"/task/language-modelling","name":"Language Modelling","papers":3},{"task":"/task/adversarial-defense","name":"Adversarial Defense","papers":2},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/bilevel-optimization","name":"Bilevel Optimization","papers":1},{"task":"/task/decoder","name":"Decoder","papers":1},{"task":"/task/face-alignment","name":"Face Alignment","papers":1},{"task":"/task/federated-learning","name":"Federated Learning","papers":1},{"task":"/task/gaussian-processes","name":"Gaussian Processes","papers":1},{"task":"/task/generalization-bounds","name":"Generalization Bounds","papers":1},{"task":"/task/hyperparameter-optimization","name":"Hyperparameter Optimization","papers":1},{"task":"/task/image-restoration","name":"Image Restoration","papers":1},{"task":"/task/meta-learning","name":"Meta-Learning","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/optical-flow-estimation","name":"Optical Flow Estimation","papers":1}],"tasks_shown":20,"n_tasks":29,"usage_by_year":[{"year":"2019","papers":1},{"year":"2021","papers":7},{"year":"2022","papers":9},{"year":"2023","papers":16},{"year":"2024","papers":5},{"year":"2025","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/deq"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}