Methods › Computer Vision › Vision Transformers › T2T-ViT
Tokens-To-Token Vision Transformer
T2T-ViT
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
T2T-ViT (Tokens-To-Token Vision Transformer) is a type of Vision Transformer which incorporates 1) a layerwise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 13 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'Tokens-To-Token Vision Transformer (T2T-ViT)' (resolution: alias); this answer is about that name. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2101.11986) is about this method is not checked.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- Fast T2T · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Fast T2T')
Origin paper of this answer, arXiv:2101.11986 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 26 harvested samples) · 8 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
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: 11 · with a code link: 9 · where Syntology ran a sample: 6 (4 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 11 tagged: 4 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 11 of 11, 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.
-
Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs 15 Mar 2025 · 0 repositories · arXiv:2503.12211
-
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers 15 Mar 2024 · 1 repository · arXiv:2403.10030Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)
-
USDC: Unified Static and Dynamic Compression for Visual Transformer 17 Oct 2023 · 0 repositories · arXiv:2310.11117
-
KDEformer: Accelerating Transformers via Kernel Density Estimation 5 Feb 2023 · 1 repository · arXiv:2302.02451Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples)
-
Unified Visual Transformer Compression 15 Mar 2022 · 1 repository · arXiv:2203.08243Syntology official (archive's flag): 7 ran · 9 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 16 harvested samples) · 3 pointer-only (licence)
-
BViT: Broad Attention based Vision Transformer 13 Feb 2022 · 1 repository · arXiv:2202.06268
-
Multi-Dimensional Model Compression of Vision Transformer 31 Dec 2021 · 1 repository · arXiv:2201.00043
-
Dynamic Token Normalization Improves Vision Transformers 5 Dec 2021 · 1 repository · arXiv:2112.02624Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)
-
Scatterbrain: Unifying Sparse and Low-rank Attention Approximation 28 Oct 2021 · 1 repository · arXiv:2110.15343Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Scatterbrain: Unifying Sparse and Low-rank Attention 21 May 2021 · 1 repository
-
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet 28 Jan 2021 · 13 repositories · arXiv:2101.11986Syntology official (archive's flag): 4 ran · 21 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 26 harvested samples) · 8 pointer-only (licence)
Tasks archive 2025-07-28
17 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