Papers › Token Merging: Your ViT But Faster

Token Merging: Your ViT But Faster

17 Oct 2022arXiv:2210.09461archive 2025-07-28

Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, Judy Hoffman

We introduce Token Merging (ToMe), a simple method to increase the throughput of existing ViT models without needing to train. ToMe gradually combines similar tokens in a transformer using a general and light-weight matching algorithm that is as fast as pruning while being more accurate. Off-the-shelf, ToMe can 2x the throughput of state-of-the-art ViT-L @ 512 and ViT-H @ 518 models on images and 2.2x the throughput of ViT-L on video with only a 0.2-0.3% accuracy drop in each case. ToMe can also easily be applied during training, improving in practice training speed up to 2x for MAE fine-tuning on video. Training with ToMe further minimizes accuracy drop, leading to 2x the throughput of ViT-B on audio for only a 0.4% mAP drop. Qualitatively, we find that ToMe merges object parts into one token, even over multiple frames of video. Overall, ToMe's accuracy and speed are competitive with state-of-the-art on images, video, and audio.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2210.09461")

Code

Syntology Ran 4 of 5 code samples harvested from 2 repositories linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 1 sample from 1 repository, 0 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/tome officialmentioned in papermentioned on GitHubpytorch report
dbolya/tomesd mentioned on GitHubpytorch report
tanvir-utexas/PaPr mentioned on GitHubpytorch report
pwc-1/Paper-9 mindspore report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

5 samples harvested; 4 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
2ran · fixture could not drive it
1unverified

Licence: 4 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

bipartite_soft_matching facebookresearch/tome/tome/merge.py official repository ran · fixture could not drive it licence not identified · pointer only · 424049f15b90678d · report
wrap_forward PaddlePaddle/PLSC/plsc/core/recompute.py community (archive-listed) unverified Apache-2.0 (permissive) · c3b15e0d7daa5901 · report
bipartite_soft_matching_random2d identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · 50778ef0adbc3581 · report
do_nothing identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · bd041cf95d856b5d · report
mps_gather_workaround identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 16eb26a585c085e1 · report

Tasks

Efficient ViTs

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Efficient ViTs ImageNet-1K (with DeiT-S) ToMe ($r=8$) GFLOPs 3.4 #15 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) ToMe ($r=8$) Top 1 Accuracy 79.7 #15 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) ToMe ($r=13$) GFLOPs 2.7 #23 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) ToMe ($r=13$) Top 1 Accuracy 79.4 #23 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) ToMe ($r=16$) GFLOPs 2.3 #29 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-S) ToMe ($r=16$) Top 1 Accuracy 79.1 #29 of 41 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) ToMe ($r=8$) GFLOPs 0.9 #14 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) ToMe ($r=8$) Top 1 Accuracy 71.7 #14 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) ToMe ($r=12$) GFLOPs 0.8 #17 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) ToMe ($r=12$) Top 1 Accuracy 71.4 #17 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) ToMe ($r=16$) GFLOPs 0.6 #18 of 22 Archive leaderboard report
Efficient ViTs ImageNet-1K (with DeiT-T) ToMe ($r=16$) Top 1 Accuracy 70.7 #18 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

MAEPruningSPEED

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