Papers › Multi-Scale Finetuning for Encoder-based Time Series Foundation Models

Multi-Scale Finetuning for Encoder-based Time Series Foundation Models

17 Jun 2025arXiv:2506.14087archive 2025-07-28

Zhongzheng Qiao, Chenghao Liu, Yiming Zhang, Ming Jin, Quang Pham, Qingsong Wen, P. N. Suganthan, Xudong Jiang, Savitha Ramasamy

Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting. However, an important yet underexplored challenge is how to effectively finetune TSFMs on specific downstream tasks. While naive finetuning can yield performance gains, we argue that it falls short of fully leveraging TSFMs' capabilities, often resulting in overfitting and suboptimal performance. Given the diverse temporal patterns across sampling scales and the inherent multi-scale forecasting capabilities of TSFMs, we adopt a causal perspective to analyze finetuning process, through which we highlight the critical importance of explicitly modeling multiple scales and reveal the shortcomings of naive approaches. Focusing on encoder-based TSFMs, we propose Multiscale finetuning (MSFT), a simple yet general framework that explicitly integrates multi-scale modeling into the finetuning process. Experimental results on three different backbones (\moirai, \moment and \units) demonstrate that TSFMs finetuned with MSFT not only outperform naive and typical parameter efficient finetuning methods but also surpass state-of-the-art deep learning methods.

PaperPDFCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 13 samples from 1 repository, 7 ran (3 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-27 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zqiao11/MSFT found in paper text by SyntologyNOASSERTIONSyntology: 13 samples, 7 ran (4 instrument-failed) · 6 unverified 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

13 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
4ran · our draft was wrong
2ran
6unverified

Licence: 13 of the 13 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 zqiao11/MSFT. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zqiao11/MSFT found in paper text by Syntology 13 samples, 7 ran (4 instrument-failed) · 6 unverified
convert_to_container src/uni2ts/distribution/_base.py ran · our draft was wrong no licence file found · pointer only · 5eec453ad4817229 · report fixture: signature tree:callable/0/? · returned dict · level recorded 2026-09-25
convert_to_module src/uni2ts/distribution/_base.py ran · our draft was wrong no licence file found · pointer only · 654eb783e0d83910 · report fixture: signature tree:dict/0/? · returned ModuleDict · level recorded 2026-09-25
get_path_var src/uni2ts/common/env.py ran · our draft was wrong no licence file found · pointer only · bcafdb774fca0219 · report fixture: signature var:str/0/str · returned PosixPath · level recorded 2026-09-25
mask_fill in 8 papers src/uni2ts/common/torch_util.py ran no licence file found · pointer only · 3918737cb9502b15 · report fixture: signature tensor:Tensor/2/float, mask:Tensor/1/bool, value:Tensor/1/float · returned Tensor · level recorded 2026-09-25
packed_attention_mask src/uni2ts/common/torch_util.py ran · our draft was wrong no licence file found · pointer only · 9411bf15db0f1fa2 · report fixture: signature sample_id:Tensor/2/int · returned Tensor · level recorded 2026-09-25
resolve_as_tuple src/uni2ts/common/hydra_util.py ran · violated contract no licence file found · pointer only · 568a5b54144b7946 · report fixture: returned tuple · level recorded 2026-09-27
safe_div in 29 papers src/uni2ts/common/torch_util.py ran fingerprinted licence not identified · pointer only · 5ae38533a6777347 · report fixture: signature numer:Tensor/2/float, denom:Tensor/2/float · returned Tensor · level recorded 2026-09-25
beta_binomial_sampler src/uni2ts/common/sampler.py unverified no licence file found · pointer only · dd639b004340cd07 · report
binomial_sampler src/uni2ts/common/sampler.py unverified no licence file found · pointer only · e56544092cf931bd · report
register_resolver src/uni2ts/common/hydra_util.py unverified no licence file found · pointer only · 28ebfb3011b4bfaf · report
resolve_cls_getattr src/uni2ts/common/hydra_util.py unverified no licence file found · pointer only · 603ae909b9308e4e · report
tree_map_multi src/uni2ts/distribution/_base.py unverified no licence file found · pointer only · fa3ea93fdf7ea89a · report
uniform_sampler in 5 papers src/uni2ts/common/sampler.py unverified no licence file found · pointer only · 47a7fdcc8c3ab2d0 · report

Tasks

Time SeriesTime Series Forecasting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ADOPT

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