{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/adapter","entry":"Adapter","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":28,"n_papers_ran":25,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":29,"n_samples_ran":26,"n_samples_fingerprinted":5,"n_places":29,"n_places_pointer_only":13,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":26,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.23347","paper":"/paper/arxiv-2608-23347","title":"Test-Time Adaptation for ECG Classification via SQI-Gated Self-Training and Beat-Rhythm Consistency","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Vincent-Wenhan/BeatRhythm-TTA","path":"src/method/beatrhythmtta.py","file_url":"https://github.com/Vincent-Wenhan/BeatRhythm-TTA/blob/HEAD/src/method/beatrhythmtta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0af846e96ca4517","mcp_get_code":{"code_sha256":"c0af846e96ca4517"}},{"arxiv_id":"2602.03473","paper":"/paper/arxiv-2602-03473","title":"Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"LMMMEng/CaRE","path":"backbone/vit_brmoe.py","file_url":"https://github.com/LMMMEng/CaRE/blob/HEAD/backbone/vit_brmoe.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7b7f101ebda35088","mcp_get_code":{"code_sha256":"7b7f101ebda35088"}},{"arxiv_id":"2510.20162","paper":"/paper/arxiv-2510-20162","title":"TOMCAT : Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"xud-yan/TOMCAT","path":"model/tomcat_bm.py","file_url":"https://github.com/xud-yan/TOMCAT/blob/HEAD/model/tomcat_bm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dede5fd72f1d3db4","mcp_get_code":{"code_sha256":"dede5fd72f1d3db4"}},{"arxiv_id":"2507.15542","paper":null,"title":"arXiv:2507.15542","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"ChelsieLei/HOLa","path":"hola_model.py","file_url":"https://github.com/ChelsieLei/HOLa/blob/HEAD/hola_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2c226e113276eeb","mcp_get_code":{"code_sha256":"e2c226e113276eeb"}},{"arxiv_id":"2505.10289","paper":"/paper/msci-addressing-clip-s-inherent-limitations","title":"MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning","date":"2025-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ltpwy/MSCI","path":"MSCI/code/model/Mutifuse_new.py","file_url":"https://github.com/ltpwy/MSCI/blob/HEAD/MSCI/code/model/Mutifuse_new.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8fa4ce97211a14db","mcp_get_code":{"code_sha256":"8fa4ce97211a14db"}},{"arxiv_id":"2501.13859","paper":"/paper/dual-modal-prototype-joint-learning-for","title":"Dual-Modal Prototype Joint Learning for Compositional Zero-Shot Learning","date":"2025-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codefish12-09/VP_CMJL","path":"model/VP_CMJL.py","file_url":"https://github.com/codefish12-09/VP_CMJL/blob/HEAD/model/VP_CMJL.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f0319bd275d5d4c","mcp_get_code":{"code_sha256":"9f0319bd275d5d4c"}},{"arxiv_id":"2501.04970","paper":"/paper/battling-the-non-stationarity-in-time-series","title":"Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation","date":"2025-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kimanki/tafas","path":"tta/tafas.py","file_url":"https://github.com/kimanki/tafas/blob/HEAD/tta/tafas.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"dbfcf1e68493e38e","mcp_get_code":{"code_sha256":"dbfcf1e68493e38e"}},{"arxiv_id":"2411.02175","paper":"/paper/safe-slow-and-fast-parameter-efficient-tuning","title":"SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MIFA-Lab/SAFE","path":"petl/vision_transformer_adapter.py","file_url":"https://github.com/MIFA-Lab/SAFE/blob/HEAD/petl/vision_transformer_adapter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"21ff6a76ba75a4d4","mcp_get_code":{"code_sha256":"21ff6a76ba75a4d4"}},{"arxiv_id":"2410.15364","paper":"/paper/scene-graph-generation-with-role-playing","title":"Scene Graph Generation with Role-Playing Large Language Models","date":"2024-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guikunchen/sdsgg","path":"maskrcnn_benchmark/modeling/roi_heads/relation_head/roi_relation_predictors.py","file_url":"https://github.com/guikunchen/sdsgg/blob/HEAD/maskrcnn_benchmark/modeling/roi_heads/relation_head/roi_relation_predictors.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f918a9266bdc602e","mcp_get_code":{"code_sha256":"f918a9266bdc602e"}},{"arxiv_id":"2405.11756","paper":"/paper/erasing-the-bias-fine-tuning-foundation","title":"Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gank0078/finessl","path":"model.py","file_url":"https://github.com/gank0078/finessl/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3df5cb5be41b7d33","mcp_get_code":{"code_sha256":"3df5cb5be41b7d33"}},{"arxiv_id":"2404.11677","paper":"/paper/cross-problem-learning-for-solving-vehicle","title":"Cross-Problem Learning for Solving Vehicle Routing Problems","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuoyi-lin/cross_problem_learning","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cac5ff2f23d7f0b9","mcp_get_code":{"code_sha256":"cac5ff2f23d7f0b9"}},{"arxiv_id":"2403.11549","paper":"/paper/boosting-continual-learning-of-vision","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JiazuoYu/MoE-Adapters4CL","path":"cil/clip/adapter.py","file_url":"https://github.com/JiazuoYu/MoE-Adapters4CL/blob/HEAD/cil/clip/adapter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"97237f25b2120465","mcp_get_code":{"code_sha256":"97237f25b2120465"}},{"arxiv_id":"2402.15648","paper":"/paper/mambair-a-simple-baseline-for-image","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iridescentttt/SynQT","path":"synqt.py","file_url":"https://github.com/iridescentttt/SynQT/blob/HEAD/synqt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb483d1dc27ae6fd","mcp_get_code":{"code_sha256":"bb483d1dc27ae6fd"}},{"arxiv_id":"2311.18825","paper":"/paper/cast-cross-attention-in-space-and-time-for-1","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"khu-vll/cast","path":"models/bidir_modeling_crossattn.py","file_url":"https://github.com/khu-vll/cast/blob/HEAD/models/bidir_modeling_crossattn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"857af2a7de44faaa","mcp_get_code":{"code_sha256":"857af2a7de44faaa"}},{"arxiv_id":"2310.17942","paper":null,"title":"arXiv:2310.17942","date":null,"month_inferred_from_arxiv_id":"2023-10","title_source":null,"repo":"KunyuLin/STDN","path":"ops/STDNmodule.py","file_url":"https://github.com/KunyuLin/STDN/blob/HEAD/ops/STDNmodule.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2395380355d28f44","mcp_get_code":{"code_sha256":"2395380355d28f44"}},{"arxiv_id":"2308.09160","paper":"/paper/fedperfix-towards-partial-model","title":"FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning","date":"2023-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"imguangyu/FedPerfix","path":"system/flcore/trainmodel/prefix.py","file_url":"https://github.com/imguangyu/FedPerfix/blob/HEAD/system/flcore/trainmodel/prefix.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a55dfc497d1c5564","mcp_get_code":{"code_sha256":"a55dfc497d1c5564"}},{"arxiv_id":"2307.16867","paper":"/paper/revisiting-the-parameter-efficiency-of","title":"Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JieShibo/PETL-ViT","path":"binary_adapter/adaptformer.py","file_url":"https://github.com/JieShibo/PETL-ViT/blob/HEAD/binary_adapter/adaptformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ec3a0348ce82616","mcp_get_code":{"code_sha256":"1ec3a0348ce82616"}},{"arxiv_id":"2303.18230","paper":"/paper/procedure-aware-pretraining-for-instructional","title":"Procedure-Aware Pretraining for Instructional Video Understanding","date":"2023-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/paprika","path":"models/adapter.py","file_url":"https://github.com/salesforce/paprika/blob/HEAD/models/adapter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8d0961854243064f","mcp_get_code":{"code_sha256":"8d0961854243064f"}},{"arxiv_id":"2303.10070","paper":"/paper/a-unified-continual-learning-framework-with","title":"A Unified Continual Learning Framework with General Parameter-Efficient Tuning","date":"2023-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gqk/LAE","path":"libml/model/pet/adapter.py","file_url":"https://github.com/gqk/LAE/blob/HEAD/libml/model/pet/adapter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"14200a7eb2754916","mcp_get_code":{"code_sha256":"14200a7eb2754916"}},{"arxiv_id":"2301.06267","paper":"/paper/multimodality-helps-unimodality-cross-modal","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","date":"2023-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linzhiqiu/cross_modal_adaptation","path":"engine/model/head.py","file_url":"https://github.com/linzhiqiu/cross_modal_adaptation/blob/HEAD/engine/model/head.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ca05774cdec74e8","mcp_get_code":{"code_sha256":"7ca05774cdec74e8"}},{"arxiv_id":"2206.08155","paper":"/paper/zero-shot-video-question-answering-via-frozen","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","date":"2022-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sts-vlcc/sts-vlcc","path":"model/deberta.py","file_url":"https://github.com/sts-vlcc/sts-vlcc/blob/HEAD/model/deberta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"020a7d784fec3e8b","mcp_get_code":{"code_sha256":"020a7d784fec3e8b"}},{"arxiv_id":"2205.11961","paper":"/paper/attentional-mixtures-of-soft-prompt-tuning","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","date":"2022-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akariasai/attempt","path":"attempt/adapters/adapter_modeling.py","file_url":"https://github.com/akariasai/attempt/blob/HEAD/attempt/adapters/adapter_modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d6cd262ec5300b6","mcp_get_code":{"code_sha256":"2d6cd262ec5300b6"}},{"arxiv_id":"2204.07705","paper":"/paper/benchmarking-generalization-via-in-context","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","date":"2022-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyintell/citb","path":"continual_learning/AdapterT5.py","file_url":"https://github.com/hyintell/citb/blob/HEAD/continual_learning/AdapterT5.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d4d90150a63de630","mcp_get_code":{"code_sha256":"d4d90150a63de630"}},{"arxiv_id":"2109.04810","paper":"/paper/mixture-of-partitions-infusing-large","title":"Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT","date":"2021-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/mop","path":"src/adapter-transformers/src/transformers/adapter_modeling.py","file_url":"https://github.com/cambridgeltl/mop/blob/HEAD/src/adapter-transformers/src/transformers/adapter_modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"269932f4ddbfb7e1","mcp_get_code":{"code_sha256":"269932f4ddbfb7e1"}},{"arxiv_id":"2012.15723","paper":"/paper/making-pre-trained-language-models-better-few","title":"Making Pre-trained Language Models Better Few-shot Learners","date":"2020-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/perfect","path":"fewshot/adapters/adapter_modeling.py","file_url":"https://github.com/facebookresearch/perfect/blob/HEAD/fewshot/adapters/adapter_modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"848dfe9da2a6b283","mcp_get_code":{"code_sha256":"848dfe9da2a6b283"}},{"arxiv_id":"2007.07779","paper":"/paper/adapterhub-a-framework-for-adapting","title":"AdapterHub: A Framework for Adapting Transformers","date":"2020-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"parovicm/badx","path":"src/transformers/adapters/modeling.py","file_url":"https://github.com/parovicm/badx/blob/HEAD/src/transformers/adapters/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d8b9b81138d5b50d","mcp_get_code":{"code_sha256":"d8b9b81138d5b50d"}},{"arxiv_id":"1902.00751","paper":"/paper/parameter-efficient-transfer-learning-for-nlp","title":"Parameter-Efficient Transfer Learning for NLP","date":"2019-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"osu-mlb/petl_vision","path":"model/adapter.py","file_url":"https://github.com/osu-mlb/petl_vision/blob/HEAD/model/adapter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b012e4d16a33bf8","mcp_get_code":{"code_sha256":"7b012e4d16a33bf8"}},{"arxiv_id":"1902.00751","paper":"/paper/parameter-efficient-transfer-learning-for-nlp","title":"Parameter-Efficient Transfer Learning for NLP","date":"2019-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zphang/bert_on_stilts","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/zphang/bert_on_stilts/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"69eca16a33f5afcb","mcp_get_code":{"code_sha256":"69eca16a33f5afcb"}},{"arxiv_id":"2025.findings-emnlp.28","paper":null,"title":"arXiv:2025.findings-emnlp.28","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"BUAAPY/ProPy","path":"modules/clip_propy.py","file_url":"https://github.com/BUAAPY/ProPy/blob/HEAD/modules/clip_propy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"837d9e707c819b7c","mcp_get_code":{"code_sha256":"837d9e707c819b7c"}}]}