SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.03024 · ICML · 2026

Consistency Deep Equilibrium Models

Zenan Ling, Robert Qiu, Jingwen Xu, Junchao Lin

arXiv · PDF · Open in the Atlas

Code that ran

18 of 20 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 16 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.03024.json · badge: /api/ran/2602.03024.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
landrarwolf/CDEQ canonical (classifier label)
classifier basis: census
18 ran · 2 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CDEQ-src/lib/layer_utils.py
pointer only (licence: NONE) · get_code("bc359191fdd6e179")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

embedded_dropout Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
landrarwolf/CDEQ/CDEQ-src/lib/optimizations.py
pointer only (licence: NONE) · get_code("df1c4e8a21c5f2ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_free_gpus Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CDEQ-src/DEQ-Sequence/train_transformer.py
pointer only (licence: NONE) · get_code("f4e2a4a09b74b2a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

line_search Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CDEQ-src/lib/solvers.py
pointer only (licence: NONE) · get_code("cf5710371bcfb0ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

list2vec Ran
ran, honoured the contract we drafted
landrarwolf/CDEQ/CDEQ-src/lib/layer_utils.py
pointer only (licence: NONE) · get_code("e193f0d97cdfd598")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_history Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CLLM-src/llm_cdeq/analyze.py
pointer only (licence: NONE) · get_code("cb0eb480c6bc29cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

matrix_diag Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
landrarwolf/CDEQ/CDEQ-src/lib/optimizations.py
pointer only (licence: NONE) · get_code("f06524d1a24b825a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_gpu_ids Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CDEQ-src/DEQ-Sequence/train_transformer.py
pointer only (licence: NONE) · get_code("57512bacc2c28eff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_runs Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CLLM-src/llm_cdeq/analyze.py
pointer only (licence: NONE) · get_code("23889d23e4101bd8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

power_method Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CDEQ-src/lib/jacobian.py
pointer only (licence: NONE) · get_code("3c120cc50bc8c55f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

progress_to_rho_time Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CLLM-src/llm_cdeq/adaptive.py
pointer only (licence: NONE) · get_code("bb557893c9d3592b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

project_to_teacher_trajectory Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CLLM-src/llm_cdeq/adaptive.py
pointer only (licence: NONE) · get_code("0f965318218530f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

read_manifest Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CLLM-src/llm_cdeq/cache.py
pointer only (licence: NONE) · get_code("1a5025436f52b641")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rho_time_to_progress Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CLLM-src/llm_cdeq/adaptive.py
pointer only (licence: NONE) · get_code("4710c385466e8a29")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rmatvec Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CDEQ-src/lib/solvers.py
pointer only (licence: NONE) · get_code("968a8f446ad3c5b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

scalar_search_armijo Ran
ran, honoured the contract we drafted
landrarwolf/CDEQ/CDEQ-src/lib/solvers.py
pointer only (licence: NONE) · get_code("b2b5022f654ee4d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

vec2list Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CDEQ-src/lib/layer_utils.py
pointer only (licence: NONE) · get_code("bfc68a2da5929c5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

weight_norm Ran
ran; our contract draft was wrong, not the code
landrarwolf/CDEQ/CDEQ-src/lib/optimizations.py
pointer only (licence: NONE) · get_code("4bf00e788db9f349")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

jac_loss_estimate Not yet run
unverified (harvested, no recorded run)
landrarwolf/CDEQ/CDEQ-src/lib/jacobian.py
pointer only (licence: NONE) · get_code("3d07af47a6ba65bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

trajectory_curves Not yet run
unverified (harvested, no recorded run)
landrarwolf/CDEQ/CLLM-src/llm_cdeq/analyze.py
pointer only (licence: NONE) · get_code("f05c7196d352aba3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, landrarwolf/CDEQ when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 3 the same month, 0 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
scalar_search_armijo 13 other papers
12 dated earlier, 1 the same month · 4 only as an assembly brick
2006.08656 (2020-06)
Multiscale Deep Equilibrium Models
2106.00553 (2021-06)
SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models
2106.08748 (2021-06)
Input Invex Neural Network
and 10 more not named here
line_search 11 other papers
10 dated earlier, 1 the same month · 3 only as an assembly brick
2006.08656 (2020-06)
Multiscale Deep Equilibrium Models
2106.08748 (2021-06)
Input Invex Neural Network
2109.14247 (2021-09)
Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State
and 8 more not named here
rmatvec 10 other papers
9 dated earlier, 1 the same month · 5 only as an assembly brick
2006.08656 (2020-06)
Multiscale Deep Equilibrium Models
2106.00553 (2021-06)
SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models
2109.14247 (2021-09)
Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State
and 7 more not named here
conv3x3 8 other papers
8 dated earlier
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1805.11046 (2018-05)
Scalable Methods for 8-bit Training of Neural Networks
2001.07645 (2020-01)
SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation
and 5 more not named here
weight_norm 5 other papers
5 dated earlier
1810.06682 (2018-10)
Trellis Networks for Sequence Modeling
2006.08656 (2020-06)
Multiscale Deep Equilibrium Models
2111.05177 (2021-11)
On Training Implicit Models
and 2 more not named here
jac_loss_estimate 3 other papers
3 dated earlier
2106.14342 (2021-06)
Stabilizing Equilibrium Models by Jacobian Regularization
2304.11663 (2023-04)
Efficient Training of Deep Equilibrium Models
2411.00899 (2024-11)
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
power_method 3 other papers
3 dated earlier
2106.14342 (2021-06)
Stabilizing Equilibrium Models by Jacobian Regularization
2304.11663 (2023-04)
Efficient Training of Deep Equilibrium Models
2411.00899 (2024-11)
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
embedded_dropout 2 other papers
2 dated earlier
1711.03953 (2017-11)
Breaking the Softmax Bottleneck: A High-Rank RNN Language Model
2411.00899 (2024-11)
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
list2vec 1 other paper
1 dated earlier
2411.00899 (2024-11)
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
matrix_diag 1 other paper
1 dated earlier
2411.00899 (2024-11)
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
vec2list 1 other paper
1 dated earlier
2411.00899 (2024-11)
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep Equilibrium Models (DEQs) have emerged as a powerful paradigm in deep learning, offering the ability to model infinite-depth networks with constant memory usage. However, DEQs incur significant inference latency due to the iterative nature of fixed-point solvers. In this work, we introduce the Consistency Deep Equilibrium Model (C-DEQ), a novel framework that leverages consistency distillation to accelerate DEQ inference. We cast the DEQ iterative inference process as evolution along a fixed ODE trajectory toward the equilibrium. Along this trajectory, we train C-DEQs to consistently map intermediate states directly to the fixed point, enabling few-step inference while preserving the performance of the teacher DEQ. At the same time, it facilitates multistep evaluation to flexibly trade computation for performance gains. Extensive experiments across various domain tasks demonstrate that C-DEQs achieve consistent 2-20× accuracy improvements over implicit DEQs under the same few-step inference budget. Our code is available at https: //github.com/landrarwolf/CDEQ.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.03024")
get_code_for_paper("2602.03024")
have("2602.03024")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.03024.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.03024.svg)](https://syntology.ai/paper/2602.03024)

Connect an agent — have() is free.