Home › Code › Adapter

Adapter

Syntologyentry name in harvested coderead from the graph 2026-09-24

Adapter appears in the code Syntology harvested for 28 papers, as 29 distinct code bodies found in 29 places (a place is one code body under one paper). At least one of them ran in 25 of the papers; 5 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named Adapter do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 26 of the 29 distinct code bodies named Adapter; 3 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
26ran
3unverified
5fingerprinted

Licence is a property of each copy, so it is counted per place: 13 of the 29 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “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, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

28 papers shown of 28, newest first; 29 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 3 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's 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.

PaperDateFileStatus SyntologyLicence
Test-Time Adaptation for ECG Classification via SQI-Gated Self-Training and Beat-Rhythm Consistency added by Syntology 2026-08 (from id) Vincent-Wenhan/BeatRhythm-TTA/src/method/beatrhythmtta.py c0af846e96ca4517 ran MIT (permissive)
Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts added by Syntology 2026-02 (from id) LMMMEng/CaRE/backbone/vit_brmoe.py 7b7f101ebda35088 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
TOMCAT : Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning added by Syntology 2025-10 (from id) xud-yan/TOMCAT/model/tomcat_bm.py dede5fd72f1d3db4 ran · metamorphic tier: invariant fingerprinted MIT (permissive)
arXiv:2507.15542 2025-07 (from id) ChelsieLei/HOLa/hola_model.py e2c226e113276eeb unverified no licence file found · pointer only
MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning 15 May 2025 ltpwy/MSCI/MSCI/code/model/Mutifuse_new.py 8fa4ce97211a14db ran · metamorphic tier: deterministic no licence file found · pointer only
Dual-Modal Prototype Joint Learning for Compositional Zero-Shot Learning 23 Jan 2025 codefish12-09/VP_CMJL/model/VP_CMJL.py 9f0319bd275d5d4c ran · metamorphic tier: deterministic no licence file found · pointer only
Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation 9 Jan 2025 kimanki/tafas/tta/tafas.py dbfcf1e68493e38e unverified licence not identified · pointer only
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models 4 Nov 2024 MIFA-Lab/SAFE/petl/vision_transformer_adapter.py 21ff6a76ba75a4d4 ran · metamorphic tier: deterministic MIT (permissive)
Scene Graph Generation with Role-Playing Large Language Models 20 Oct 2024 guikunchen/sdsgg/maskrcnn_benchmark/modeling/roi_heads/relation_head/roi_relation_predictors.py f918a9266bdc602e ran MIT (permissive)
Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning 20 May 2024 gank0078/finessl/model.py 3df5cb5be41b7d33 ran no licence file found · pointer only
Cross-Problem Learning for Solving Vehicle Routing Problems 17 Apr 2024 zhuoyi-lin/cross_problem_learning/nets/attention_model.py cac5ff2f23d7f0b9 ran · metamorphic tier: deterministic MIT (permissive)
Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters 18 Mar 2024 JiazuoYu/MoE-Adapters4CL/cil/clip/adapter.py 97237f25b2120465 ran no licence file found · pointer only
MambaIR: A Simple Baseline for Image Restoration with State-Space Model 23 Feb 2024 iridescentttt/SynQT/synqt.py bb483d1dc27ae6fd ran · metamorphic tier: invariant MIT (permissive)
CAST: Cross-Attention in Space and Time for Video Action Recognition 30 Nov 2023 khu-vll/cast/models/bidir_modeling_crossattn.py 857af2a7de44faaa unverified licence not identified · pointer only
arXiv:2310.17942 2023-10 (from id) KunyuLin/STDN/ops/STDNmodule.py 2395380355d28f44 ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only
FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning 17 Aug 2023 imguangyu/FedPerfix/system/flcore/trainmodel/prefix.py a55dfc497d1c5564 ran · metamorphic tier: deterministic no licence file found · pointer only
Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy 31 Jul 2023 JieShibo/PETL-ViT/binary_adapter/adaptformer.py 1ec3a0348ce82616 ran MIT (permissive)
Procedure-Aware Pretraining for Instructional Video Understanding 31 Mar 2023 salesforce/paprika/models/adapter.py 8d0961854243064f ran Apache-2.0 (permissive)
A Unified Continual Learning Framework with General Parameter-Efficient Tuning 17 Mar 2023 gqk/LAE/libml/model/pet/adapter.py 14200a7eb2754916 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models 16 Jan 2023 linzhiqiu/cross_modal_adaptation/engine/model/head.py 7ca05774cdec74e8 ran fingerprinted MIT (permissive)
Zero-Shot Video Question Answering via Frozen Bidirectional Language Models 16 Jun 2022 sts-vlcc/sts-vlcc/model/deberta.py 020a7d784fec3e8b ran · metamorphic tier: deterministic Apache-2.0 (permissive)
ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts 24 May 2022 akariasai/attempt/attempt/adapters/adapter_modeling.py 2d6cd262ec5300b6 ran MIT (permissive)
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks 16 Apr 2022 hyintell/citb/continual_learning/AdapterT5.py d4d90150a63de630 ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only
Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT 10 Sep 2021 cambridgeltl/mop/src/adapter-transformers/src/transformers/adapter_modeling.py 269932f4ddbfb7e1 ran fingerprinted no licence file found · pointer only
Making Pre-trained Language Models Better Few-shot Learners 31 Dec 2020 facebookresearch/perfect/fewshot/adapters/adapter_modeling.py 848dfe9da2a6b283 ran · metamorphic tier: invariant Apache-2.0 (permissive)
AdapterHub: A Framework for Adapting Transformers 15 Jul 2020 parovicm/badx/src/transformers/adapters/modeling.py d8b9b81138d5b50d ran Apache-2.0 (permissive)
Parameter-Efficient Transfer Learning for NLP 2 Feb 2019 osu-mlb/petl_vision/model/adapter.py 7b012e4d16a33bf8 ran no licence file found · pointer only
Parameter-Efficient Transfer Learning for NLP 2 Feb 2019 zphang/bert_on_stilts/pytorch_pretrained_bert/modeling.py 69eca16a33f5afcb ran · metamorphic tier: invariant Apache-2.0 (permissive)
arXiv:2025.findings-emnlp.28 BUAAPY/ProPy/modules/clip_propy.py 837d9e707c819b7c ran · metamorphic tier: deterministic no licence file found · pointer only

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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