{"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/get-init-weights-vit","entry":"get_init_weights_vit","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":23,"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":15,"n_samples_ran":12,"n_samples_fingerprinted":0,"n_places":29,"n_places_pointer_only":10,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":10,"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":"2604.04420","paper":"/paper/arxiv-2604-04420","title":"Is Prompt Selection Necessary for Task-Free Online Continual Learning?","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"efficient-learning-lab/SinglePrompt","path":"models/singlePrompt.py","file_url":"https://github.com/efficient-learning-lab/SinglePrompt/blob/HEAD/models/singlePrompt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f27dd436fd97776e","mcp_get_code":{"code_sha256":"f27dd436fd97776e"}},{"arxiv_id":"2602.17559","paper":"/paper/arxiv-2602-17559","title":"Revisiting Weight Regularization for Low-Rank Continual Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"yaoyz96/low-rank-cl","path":"methods/ewclora.py","file_url":"https://github.com/yaoyz96/low-rank-cl/blob/HEAD/methods/ewclora.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1c3a1d671783f6ce","mcp_get_code":{"code_sha256":"1c3a1d671783f6ce"}},{"arxiv_id":"2507.07100","paper":"/paper/addressing-imbalanced-domain-incremental","title":"Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts","date":"2025-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lain810/DCE","path":"models/vit.py","file_url":"https://github.com/Lain810/DCE/blob/HEAD/models/vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b142ce9e26ce9b4f","mcp_get_code":{"code_sha256":"b142ce9e26ce9b4f"}},{"arxiv_id":"2505.22389","paper":"/paper/train-with-perturbation-infer-after-merging-a","title":"Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning","date":"2025-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qhmiao/P-M-for-Continual-Learning","path":"utils/vit_builder.py","file_url":"https://github.com/qhmiao/P-M-for-Continual-Learning/blob/HEAD/utils/vit_builder.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":"398c127f958b7a62","mcp_get_code":{"code_sha256":"398c127f958b7a62"}},{"arxiv_id":"2412.04786","paper":"/paper/slicing-vision-transformer-for-flexible","title":"Slicing Vision Transformer for Flexible Inference","date":"2024-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BeSpontaneous/Scala-pytorch","path":"models_scala.py","file_url":"https://github.com/BeSpontaneous/Scala-pytorch/blob/HEAD/models_scala.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac707dd1c89e5865","mcp_get_code":{"code_sha256":"ac707dd1c89e5865"}},{"arxiv_id":"2409.17978","paper":"/paper/hydravit-stacking-heads-for-a-scalable-vit","title":"HydraViT: Stacking Heads for a Scalable ViT","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ds-kiel/HydraViT","path":"timm/models/hydravit.py","file_url":"https://github.com/ds-kiel/HydraViT/blob/HEAD/timm/models/hydravit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bbab6441363adb9","mcp_get_code":{"code_sha256":"0bbab6441363adb9"}},{"arxiv_id":"2409.10956","paper":"/paper/versatile-incremental-learning-towards-class","title":"Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning","date":"2024-09-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"khu-agi/vil","path":"vision_transformer.py","file_url":"https://github.com/khu-agi/vil/blob/HEAD/vision_transformer.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":"b5dbfbeaf3d26a90","mcp_get_code":{"code_sha256":"b5dbfbeaf3d26a90"}},{"arxiv_id":"2407.20171","paper":"/paper/diffusion-feedback-helps-clip-see-better","title":"Diffusion Feedback Helps CLIP See Better","date":"2024-07-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baaivision/diva","path":"condition/SigLIP_for_timm_models_visiontransformer.py","file_url":"https://github.com/baaivision/diva/blob/HEAD/condition/SigLIP_for_timm_models_visiontransformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"42d148d34d7586d4","mcp_get_code":{"code_sha256":"42d148d34d7586d4"}},{"arxiv_id":"2407.00113","paper":"/paper/personalized-federated-continual-learning-via","title":"Personalized Federated Continual Learning via Multi-granularity Prompt","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skyofbeginning/fedmgp","path":"Models/vision_transformer.py","file_url":"https://github.com/skyofbeginning/fedmgp/blob/HEAD/Models/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c600a2f0f2361f1","mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"arxiv_id":"2406.18051","paper":"/paper/vit-1-58b-mobile-vision-transformers-in-the-1","title":"ViT-1.58b: Mobile Vision Transformers in the 1-bit Era","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dlyuangod/vit-1.58b","path":"v.py","file_url":"https://github.com/dlyuangod/vit-1.58b/blob/HEAD/v.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1a1ee1200dc36a2f","mcp_get_code":{"code_sha256":"1a1ee1200dc36a2f"}},{"arxiv_id":"2406.05658","paper":"/paper/visual-prompt-tuning-in-null-space-for","title":"Visual Prompt Tuning in Null Space for Continual Learning","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zugexiaodui/VPTinNSforCL","path":"utils/vit_builder.py","file_url":"https://github.com/zugexiaodui/VPTinNSforCL/blob/HEAD/utils/vit_builder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"398c127f958b7a62","mcp_get_code":{"code_sha256":"398c127f958b7a62"}},{"arxiv_id":"2404.14721","paper":"/paper/dynamically-anchored-prompting-for-task","title":"Dynamically Anchored Prompting for Task-Imbalanced Continual Learning","date":"2024-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chenxing6666/dap","path":"vision_transformer.py","file_url":"https://github.com/chenxing6666/dap/blob/HEAD/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c600a2f0f2361f1","mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"arxiv_id":"2403.11808","paper":"/paper/dynamic-tuning-towards-parameter-and","title":"Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nus-hpc-ai-lab/dynamic-tuning","path":"models/vision_transformer_IN21K.py","file_url":"https://github.com/nus-hpc-ai-lab/dynamic-tuning/blob/HEAD/models/vision_transformer_IN21K.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1d314401456ed7f5","mcp_get_code":{"code_sha256":"1d314401456ed7f5"}},{"arxiv_id":"2403.08568","paper":"/paper/consistent-prompting-for-rehearsal-free","title":"Consistent Prompting for Rehearsal-Free Continual Learning","date":"2024-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zhanxin-Gao/CPrompt","path":"models/cprompt.py","file_url":"https://github.com/Zhanxin-Gao/CPrompt/blob/HEAD/models/cprompt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aea2fcf3341c72f6","mcp_get_code":{"code_sha256":"aea2fcf3341c72f6"}},{"arxiv_id":"2402.00865","paper":"/paper/towards-optimal-feature-shaping-methods-for","title":"Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection","date":"2024-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qinyu-allen-zhao/optfsood","path":"model/vit_cifar.py","file_url":"https://github.com/qinyu-allen-zhao/optfsood/blob/HEAD/model/vit_cifar.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b5dbfbeaf3d26a90","mcp_get_code":{"code_sha256":"b5dbfbeaf3d26a90"}},{"arxiv_id":"2312.10136","paper":"/paper/gradient-based-parameter-selection-for","title":"Gradient-based Parameter Selection for Efficient Fine-Tuning","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FightingFighting/GPS","path":"models/vision_transformer.py","file_url":"https://github.com/FightingFighting/GPS/blob/HEAD/models/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"def23f7d7d042968","mcp_get_code":{"code_sha256":"def23f7d7d042968"}},{"arxiv_id":"2311.15264","paper":"/paper/chada-vit-channel-adaptive-attention-for","title":"ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images","date":"2023-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicoboou/chada_vit","path":"src/backbones/vit/vit_attn_viz.py","file_url":"https://github.com/nicoboou/chada_vit/blob/HEAD/src/backbones/vit/vit_attn_viz.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":"89b15c59ecb5d1c7","mcp_get_code":{"code_sha256":"89b15c59ecb5d1c7"}},{"arxiv_id":"2311.12048","paper":"/paper/one-size-fits-all-for-semantic-shifts","title":"One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning","date":"2023-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaist-dmlab/AdaPromptCL","path":"clip_vit.py","file_url":"https://github.com/kaist-dmlab/AdaPromptCL/blob/HEAD/clip_vit.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":"6c600a2f0f2361f1","mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"arxiv_id":"2310.13888","paper":"/paper/towards-a-general-framework-for-continual","title":"Towards a General Framework for Continual Learning with Pre-training","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-ml/HiDe-Prompt","path":"vits/hide_prompt_vision_transformer.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/vits/hide_prompt_vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c600a2f0f2361f1","mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"arxiv_id":"2310.13888","paper":"/paper/towards-a-general-framework-for-continual","title":"Towards a General Framework for Continual Learning with Pre-training","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-ml/HiDe-Prompt","path":"vits/hide_lora_vision_transformer.py","file_url":"https://github.com/thu-ml/HiDe-Prompt/blob/HEAD/vits/hide_lora_vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2462a444e3fa1df","mcp_get_code":{"code_sha256":"d2462a444e3fa1df"}},{"arxiv_id":"2308.09610","paper":"/paper/on-the-effectiveness-of-layernorm-tuning-for","title":"On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers","date":"2023-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tdemin16/continual-layernorm-tuning","path":"couple/vision_transformer.py","file_url":"https://github.com/tdemin16/continual-layernorm-tuning/blob/HEAD/couple/vision_transformer.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":"6c600a2f0f2361f1","mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"arxiv_id":"2308.03374","paper":"/paper/heterogeneous-forgetting-compensation-for","title":"Heterogeneous Forgetting Compensation for Class-Incremental Learning","date":"2023-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JiahuaDong/HFC","path":"vit.py","file_url":"https://github.com/JiahuaDong/HFC/blob/HEAD/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c600a2f0f2361f1","mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"arxiv_id":"2307.11342","paper":"/paper/tuning-pre-trained-model-via-moment-probing","title":"Tuning Pre-trained Model via Moment Probing","date":"2023-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingzeg/moment-probing","path":"models/vision_transformer.py","file_url":"https://github.com/mingzeg/moment-probing/blob/HEAD/models/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"def23f7d7d042968","mcp_get_code":{"code_sha256":"def23f7d7d042968"}},{"arxiv_id":"2307.02251","paper":"/paper/ranpac-random-projections-and-pre-trained","title":"RanPAC: Random Projections and Pre-trained Models for Continual Learning","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ranpac/ranpac","path":"petl/vision_transformer_ssf.py","file_url":"https://github.com/ranpac/ranpac/blob/HEAD/petl/vision_transformer_ssf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"def23f7d7d042968","mcp_get_code":{"code_sha256":"def23f7d7d042968"}},{"arxiv_id":"2303.11403","paper":"/paper/ep-alm-efficient-perceptual-augmentation-of","title":"eP-ALM: Efficient Perceptual Augmentation of Language Models","date":"2023-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mshukor/eP-ALM","path":"models/vit.py","file_url":"https://github.com/mshukor/eP-ALM/blob/HEAD/models/vit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c600a2f0f2361f1","mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"arxiv_id":"2210.08823","paper":"/paper/scaling-shifting-your-features-a-new-baseline","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongzelian/ssf","path":"models/vision_transformer.py","file_url":"https://github.com/dongzelian/ssf/blob/HEAD/models/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"def23f7d7d042968","mcp_get_code":{"code_sha256":"def23f7d7d042968"}},{"arxiv_id":"2207.12819","paper":"/paper/s-prompts-learning-with-pre-trained","title":"S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning","date":"2022-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iamwangyabin/S-Prompts","path":"models/vit.py","file_url":"https://github.com/iamwangyabin/S-Prompts/blob/HEAD/models/vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b142ce9e26ce9b4f","mcp_get_code":{"code_sha256":"b142ce9e26ce9b4f"}},{"arxiv_id":"2112.08654","paper":"/paper/learning-to-prompt-for-continual-learning-1","title":"Learning to Prompt for Continual Learning","date":"2021-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JH-LEE-KR/l2p-pytorch","path":"vision_transformer.py","file_url":"https://github.com/JH-LEE-KR/l2p-pytorch/blob/HEAD/vision_transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"6c600a2f0f2361f1","mcp_get_code":{"code_sha256":"6c600a2f0f2361f1"}},{"arxiv_id":"aaai_26216","paper":null,"title":"arXiv:aaai_26216","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"iamwangyabin/ESN","path":"models/vit.py","file_url":"https://github.com/iamwangyabin/ESN/blob/HEAD/models/vit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b142ce9e26ce9b4f","mcp_get_code":{"code_sha256":"b142ce9e26ce9b4f"}}]}