{"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/create-vit","entry":"create_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":8,"n_papers_ran":0,"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":3,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2412.03017","paper":"/paper/pixel-level-and-semantic-level-adjustable","title":"Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csslc/pisa-sr","path":"ram/models/utils.py","file_url":"https://github.com/csslc/pisa-sr/blob/HEAD/ram/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f837c334ddfa8af4","mcp_get_code":{"code_sha256":"f837c334ddfa8af4"}},{"arxiv_id":"2407.07582","paper":"/paper/tip-tabular-image-pre-training-for-multimodal","title":"TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siyi-wind/TIP","path":"models/Tip_utils/VisionTransformer_imagenet.py","file_url":"https://github.com/siyi-wind/TIP/blob/HEAD/models/Tip_utils/VisionTransformer_imagenet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1444cafc7b022c45","mcp_get_code":{"code_sha256":"1444cafc7b022c45"}},{"arxiv_id":"2312.00081","paper":"/paper/synthesize-diagnose-and-optimize-towards-fine","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjpoom/spec","path":"spec/models/blip_utils/blip.py","file_url":"https://github.com/wjpoom/spec/blob/HEAD/spec/models/blip_utils/blip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f837c334ddfa8af4","mcp_get_code":{"code_sha256":"f837c334ddfa8af4"}},{"arxiv_id":"2310.19785","paper":"/paper/what-s-up-with-vision-language-models","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amitakamath/whatsup_vlms","path":"model_zoo/blip_utils/blip.py","file_url":"https://github.com/amitakamath/whatsup_vlms/blob/HEAD/model_zoo/blip_utils/blip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f837c334ddfa8af4","mcp_get_code":{"code_sha256":"f837c334ddfa8af4"}},{"arxiv_id":"2305.16304","paper":"/paper/candidate-set-re-ranking-for-composed-image","title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Cuberick-Orion/Bi-Blip4CIR","path":"src/blip_modules/blip.py","file_url":"https://github.com/Cuberick-Orion/Bi-Blip4CIR/blob/HEAD/src/blip_modules/blip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f837c334ddfa8af4","mcp_get_code":{"code_sha256":"f837c334ddfa8af4"}},{"arxiv_id":"2304.05977","paper":"/paper/imagereward-learning-and-evaluating-human-1","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","date":"2023-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/ImageReward","path":"ImageReward/models/BLIP/blip.py","file_url":"https://github.com/THUDM/ImageReward/blob/HEAD/ImageReward/models/BLIP/blip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f837c334ddfa8af4","mcp_get_code":{"code_sha256":"f837c334ddfa8af4"}},{"arxiv_id":"2301.10222","paper":"/paper/rangevit-towards-vision-transformers-for-3d","title":"RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving","date":"2023-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valeoai/rangevit","path":"models/rangevit.py","file_url":"https://github.com/valeoai/rangevit/blob/HEAD/models/rangevit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2be1b57c31497f10","mcp_get_code":{"code_sha256":"2be1b57c31497f10"}},{"arxiv_id":"2210.01936","paper":"/paper/when-and-why-vision-language-models-behave","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","date":"2022-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mertyg/vision-language-models-are-bows","path":"model_zoo/blip_utils/blip.py","file_url":"https://github.com/mertyg/vision-language-models-are-bows/blob/HEAD/model_zoo/blip_utils/blip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f837c334ddfa8af4","mcp_get_code":{"code_sha256":"f837c334ddfa8af4"}}]}