Methods › Computer Vision › Image Model Blocks › Mixer Layer
MLP-Mixer Layer
Mixer Layer
Introduced by Ilya Tolstikhin et al. in MLP-Mixer: An all-MLP Architecture for Vision
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Mixer layer is a layer used in the MLP-Mixer architecture proposed by Tolstikhin et. al (2021) for computer vision. Mixer layers consist purely of MLPs, without convolutions or attention. It takes an input of embedded image patches (tokens), with its output having the same shape as its input, similar to that of a Vision Transformer encoder. As suggested by its name, Mixer layers "mix" tokens and channels through its "token mixing" and "channel mixing" MLPs contained the layer. It utilizes previous techniques by other architectures, such as layer normalization, skip-connections, and regularization methods.
Image credit: Tolstikhin, I. O., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., ... & Dosovitskiy, A. (2021). Mlp-mixer: An all-mlp architecture for vision. Advances in Neural Information Processing Systems, 34, 24261-24272.
In Syntology for a different name, 'MixER', about another paper, arXiv:2502.05335: verified reference implementation at level V2; retrieve with get_reference_implementation(name='MixER'). The lookup matched a different name in Syntology's graph, 'MixER' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:2502.05335, while the archive credits arXiv:2105.01601.
Origin paper of this answer, arXiv:2502.05335 (its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 7 · with a code link: 5 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 7 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 7 of 7, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather 25 Aug 2024 · 1 repository · arXiv:2408.13802
-
SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognition 11 Jul 2024 · 1 repository · arXiv:2407.08260
-
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series 8 Jan 2024 · 2 repositories · arXiv:2401.03955Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)
-
Spatio-Temporal Graph Mixformer for Traffic Forecasting 15 Oct 2023 · 1 repository
-
Graph-Guided MLP-Mixer for Skeleton-Based Human Motion Prediction 7 Apr 2023 · 0 repositories · arXiv:2304.03532
-
MB-DECTNet: A Model-Based Unrolled Network for Accurate 3D DECT Reconstruction 1 Feb 2023 · 0 repositories · arXiv:2302.00577
-
MLP-Mixer: An all-MLP Architecture for Vision 4 May 2021 · 49 repositories · arXiv:2105.01601Syntology official: harvested, nothing ran · 114 ran (of which 77 constructed an object rather than computing a result; 104 with no instrument failure: 2 honoured, 1 violated, 101 with no contract checked; 10 where Syntology's instrument failed) · 20 unverified (of 134 harvested samples) · 40 pointer-only (licence)
Tasks archive 2025-07-28
16 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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