Methods › General › Model Compression › Soups
Model Soups
Soups
Introduced by Mitchell Wortsman et al. in Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Compress an ensemble of models into a single one by averaging their weights (under certain pre-conditions).
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: LT-Soups; Local Superior Soups.
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.
Papers archive 2025-07-28
archive papers tagged: 19 · with a code link: 10 · where Syntology ran a sample: 3 (3 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 (3 of 19 tagged: 3 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 19 of 19, 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.
-
UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality 10 Mar 2025 · 0 repositories · arXiv:2503.10669
-
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning 31 Oct 2024 · 1 repository · arXiv:2410.23660Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified (of 12 harvested samples) · 12 pointer-only (licence)
-
Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automation 10 Oct 2024 · 1 repository · arXiv:2410.08371
-
Robust Biharmonic Skinning Using Geometric Fields 1 Jun 2024 · 0 repositories · arXiv:2406.00238
-
Cross-Dataset Generalization For Retinal Lesions Segmentation 14 May 2024 · 0 repositories · arXiv:2405.08329
-
How Much You Ate? Food Portion Estimation on Spoons 12 May 2024 · 0 repositories · arXiv:2405.08717
-
FissionFusion: Fast Geometric Generation and Hierarchical Souping for Medical Image Analysis 20 Mar 2024 · 1 repository · arXiv:2403.13341
-
RADIN: Souping on a Budget 31 Jan 2024 · 0 repositories · arXiv:2401.17790
-
Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers 25 Dec 2023 · 0 repositories · arXiv:2312.15681
-
Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning 21 Nov 2023 · 1 repository · arXiv:2311.13612
-
Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging 29 Jun 2023 · 1 repository · arXiv:2306.16788
-
Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication 18 Jun 2023 · 1 repository · arXiv:2306.10466Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Pre-training Language Model as a Multi-perspective Course Learner 6 May 2023 · 0 repositories · arXiv:2305.03981
-
Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts 20 Feb 2023 · 0 repositories · arXiv:2302.10164
-
Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation 27 Jan 2023 · 1 repository · arXiv:2301.11503
-
Model soups to increase inference without increasing compute time 24 Jan 2023 · 1 repository · arXiv:2301.10092
-
Revisiting adapters with adversarial training 10 Oct 2022 · 0 repositories · arXiv:2210.04886
-
Bag of Tricks for Domain Adaptive Multi-Object Tracking 31 May 2022 · 1 repository · arXiv:2205.15609
-
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time 10 Mar 2022 · 6 repositories · arXiv:2203.05482Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified (of 17 harvested samples)
Tasks archive 2025-07-28
20 shown of 22 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