{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/clip/papers/ran/4","list_of":"/method/clip","method":"CLIP","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":4,"pages_in_order":7,"rows_per_page":100,"rows":[301,400],"of":649,"counts":{"archive_papers_tagged":3094,"with_a_code_link":1617,"where_syntology_ran_a_sample":649,"not_listed_spam_title":0,"listed":3094,"listed_where_code_ran":649,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":554,"every_run_a_failure_of_syntologys_instrument":95,"listed_with_a_run_with_no_instrument_failure":554,"listed_every_run_a_failure_of_syntologys_instrument":95,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/clip/papers/ran/1","prev":"/method/clip/papers/ran/3","next":"/method/clip/papers/ran/5","papers":[{"paper":"/paper/langsplat-3d-language-gaussian-splatting","slug":"langsplat-3d-language-gaussian-splatting","title":"LangSplat: 3D Language Gaussian Splatting","date":"2023-12-26","arxiv_id":"2312.16084","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["minghanqin/LangSplat"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/spectral-prompt-tuning-unveiling-unseen","slug":"spectral-prompt-tuning-unveiling-unseen","title":"Spectral Prompt Tuning:Unveiling Unseen Classes for Zero-Shot Semantic Segmentation","date":"2023-12-20","arxiv_id":"2312.12754","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["clearxu/spt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-dinoiser-teaching-clip-a-few-dino-tricks","slug":"clip-dinoiser-teaching-clip-a-few-dino-tricks","title":"CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation","date":"2023-12-19","arxiv_id":"2312.12359","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wysoczanska/clip_dinoiser"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/shot2story20k-a-new-benchmark-for","slug":"shot2story20k-a-new-benchmark-for","title":"Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","date":"2023-12-16","arxiv_id":"2312.10300","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bytedance/Shot2Story"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/collaborating-foundation-models-for-domain","slug":"collaborating-foundation-models-for-domain","title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","date":"2023-12-15","arxiv_id":"2312.09788","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yasserben/clouds"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/osprey-pixel-understanding-with-visual","slug":"osprey-pixel-understanding-with-visual","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","date":"2023-12-15","arxiv_id":"2312.10032","n_code_links":2,"syntology":{"ran":10,"of":14,"n_ran_checked":8,"n_instrument":2,"unverified":4,"pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["circleradon/osprey"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/a-picture-is-worth-more-than-77-text-tokens","slug":"a-picture-is-worth-more-than-77-text-tokens","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","date":"2023-12-14","arxiv_id":"2312.08578","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":8,"n_instrument":0,"unverified":4,"pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["facebookresearch/dci"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/tokenize-anything-via-prompting","slug":"tokenize-anything-via-prompting","title":"Tokenize Anything via Prompting","date":"2023-12-14","arxiv_id":"2312.09128","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["baaivision/tokenize-anything"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ez-clip-efficient-zeroshot-video-action","slug":"ez-clip-efficient-zeroshot-video-action","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","date":"2023-12-13","arxiv_id":"2312.08010","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":4,"n_instrument":5,"unverified":4,"pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shahzadnit/ez-clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-well-does-gpt-4v-ision-adapt-to","slug":"how-well-does-gpt-4v-ision-adapt-to","title":"How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation","date":"2023-12-12","arxiv_id":"2312.07424","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jameszhou-gl/gpt-4v-distribution-shift"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/smartedit-exploring-complex-instruction-based","slug":"smartedit-exploring-complex-instruction-based","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","date":"2023-12-11","arxiv_id":"2312.06739","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"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","official":{"repos":["TencentARC/SmartEdit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/am-radio-agglomerative-model-reduce-all","slug":"am-radio-agglomerative-model-reduce-all","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","date":"2023-12-10","arxiv_id":"2312.06709","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nvlabs/radio"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/swiftbrush-one-step-text-to-image-diffusion","slug":"swiftbrush-one-step-text-to-image-diffusion","title":"SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation","date":"2023-12-08","arxiv_id":"2312.05239","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"phrase":"5 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["vinairesearch/swiftbrush"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-are-good-prompt","slug":"large-language-models-are-good-prompt","title":"Large Language Models are Good Prompt Learners for Low-Shot Image Classification","date":"2023-12-07","arxiv_id":"2312.04076","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhaohengz/llamp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/open-vocabulary-segmentation-with-semantic","slug":"open-vocabulary-segmentation-with-semantic","title":"Open-Vocabulary Segmentation with Semantic-Assisted Calibration","date":"2023-12-07","arxiv_id":"2312.04089","n_code_links":2,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["workforai/scan","yongliu20/SCAN"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/scaling-laws-of-synthetic-images-for-model","slug":"scaling-laws-of-synthetic-images-for-model","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","date":"2023-12-07","arxiv_id":"2312.04567","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/syn-rep-learn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/foundation-model-assisted-weakly-supervised","slug":"foundation-model-assisted-weakly-supervised","title":"Foundation Model Assisted Weakly Supervised Semantic Segmentation","date":"2023-12-06","arxiv_id":"2312.03585","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["HAL-42/FMA-WSSS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/lite-mind-towards-efficient-and-versatile","slug":"lite-mind-towards-efficient-and-versatile","title":"Lite-Mind: Towards Efficient and Robust Brain Representation Network","date":"2023-12-06","arxiv_id":"2312.03781","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gongzix/lite-mind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/alpha-clip-a-clip-model-focusing-on-wherever","slug":"alpha-clip-a-clip-model-focusing-on-wherever","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","date":"2023-12-06","arxiv_id":"2312.03818","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sunzey/alphaclip"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/describing-differences-in-image-sets-with","slug":"describing-differences-in-image-sets-with","title":"Describing Differences in Image Sets with Natural Language","date":"2023-12-05","arxiv_id":"2312.02974","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["understanding-visual-datasets/visdiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sclip-rethinking-self-attention-for-dense","slug":"sclip-rethinking-self-attention-for-dense","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","date":"2023-12-04","arxiv_id":"2312.01597","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wangf3014/sclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/language-only-efficient-training-of-zero-shot","slug":"language-only-efficient-training-of-zero-shot","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","date":"2023-12-04","arxiv_id":"2312.01998","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":3,"n_instrument":0,"unverified":5,"pointer_only":8,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["navervision/lincir"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/openvoice-versatile-instant-voice-cloning","slug":"openvoice-versatile-instant-voice-cloning","title":"OpenVoice: Versatile Instant Voice Cloning","date":"2023-12-03","arxiv_id":"2312.01479","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":12,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/deepcache-accelerating-diffusion-models-for","slug":"deepcache-accelerating-diffusion-models-for","title":"DeepCache: Accelerating Diffusion Models for Free","date":"2023-12-01","arxiv_id":"2312.00858","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["horseee/deepcache"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/rethinking-fid-towards-a-better-evaluation","slug":"rethinking-fid-towards-a-better-evaluation","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","date":"2023-11-30","arxiv_id":"2401.09603","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/clap-contrastive-learning-with-augmented","slug":"clap-contrastive-learning-with-augmented","title":"CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts","date":"2023-11-28","arxiv_id":"2311.16445","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["YichaoCai1/CLAP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/zero-shot-referring-expression-comprehension","slug":"zero-shot-referring-expression-comprehension","title":"Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions","date":"2023-11-28","arxiv_id":"2311.17048","n_code_links":1,"syntology":{"ran":14,"of":20,"n_ran_checked":10,"n_instrument":4,"unverified":6,"pointer_only":10,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 3 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["show-han/zeroshot_rec"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/mobileclip-fast-image-text-models-through","slug":"mobileclip-fast-image-text-models-through","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","date":"2023-11-28","arxiv_id":"2311.17049","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["apple/ml-mobileclip","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/beyond-sole-strength-customized-ensembles-for","slug":"beyond-sole-strength-customized-ensembles-for","title":"Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models","date":"2023-11-28","arxiv_id":"2311.17091","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhihelu/ensemble_vlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/test-time-adaptation-of-discriminative-models","slug":"test-time-adaptation-of-discriminative-models","title":"Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback","date":"2023-11-27","arxiv_id":"2311.16102","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/removing-nsfw-concepts-from-vision-and","slug":"removing-nsfw-concepts-from-vision-and","title":"Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models","date":"2023-11-27","arxiv_id":"2311.16254","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":3,"n_instrument":1,"unverified":3,"pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["aimagelab/safe-clip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/id-like-prompt-learning-for-few-shot-out-of","slug":"id-like-prompt-learning-for-few-shot-out-of","title":"ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection","date":"2023-11-26","arxiv_id":"2311.15243","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ycfate/id-like"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-the-vulnerability-of-clip-to","slug":"understanding-the-vulnerability-of-clip-to","title":"Understanding the Vulnerability of CLIP to Image Compression","date":"2023-11-23","arxiv_id":"2311.14029","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["CangxiongChen/understanding_CLIP_vulnerability"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hardware-resilience-properties-of-text-guided-1","slug":"hardware-resilience-properties-of-text-guided-1","title":"Hardware Resilience Properties of Text-Guided Image Classifiers","date":"2023-11-23","arxiv_id":"2311.14062","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["talalwasim/textguidedresilience"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hgclip-exploring-vision-language-models-with-1","slug":"hgclip-exploring-vision-language-models-with-1","title":"HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding","date":"2023-11-23","arxiv_id":"2311.14064","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":0,"n_instrument":3,"unverified":3,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["richard-peng-xia/HGCLIP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/badclip-dual-embedding-guided-backdoor-attack","slug":"badclip-dual-embedding-guided-backdoor-attack","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","date":"2023-11-20","arxiv_id":"2311.12075","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/adversarial-prompt-tuning-for-vision-language","slug":"adversarial-prompt-tuning-for-vision-language","title":"Adversarial Prompt Tuning for Vision-Language Models","date":"2023-11-19","arxiv_id":"2311.11261","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jiamingzhang94/adversarial-prompt-tuning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/event-causality-is-key-to-computational-story","slug":"event-causality-is-key-to-computational-story","title":"Event Causality Is Key to Computational Story Understanding","date":"2023-11-16","arxiv_id":"2311.09648","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["insundaycathy/event-causality-extraction"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/wildlifedatasets-an-open-source-toolkit-for","slug":"wildlifedatasets-an-open-source-toolkit-for","title":"WildlifeDatasets: An open-source toolkit for animal re-identification","date":"2023-11-15","arxiv_id":"2311.09118","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wildlifedatasets/wildlife-datasets","wildlifedatasets/wildlife-tools"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/convnet-vs-transformer-supervised-vs-clip","slug":"convnet-vs-transformer-supervised-vs-clip","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","date":"2023-11-15","arxiv_id":"2311.09215","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kirill-vish/beyond-inet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/pretrain-like-you-inference-masked-tuning","slug":"pretrain-like-you-inference-masked-tuning","title":"Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval","date":"2023-11-13","arxiv_id":"2311.07622","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Chen-Junyang-cn/PLI"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/follow-up-differential-descriptions-language","slug":"follow-up-differential-descriptions-language","title":"Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification","date":"2023-11-10","arxiv_id":"2311.07593","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["batsresearch/fudd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gipcol-graph-injected-soft-prompting-for","slug":"gipcol-graph-injected-soft-prompting-for","title":"GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning","date":"2023-11-09","arxiv_id":"2311.05729","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":7,"n_instrument":0,"unverified":5,"pointer_only":12,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hlr/gipcol"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/weakly-supervised-cross-model-learning-in","slug":"weakly-supervised-cross-model-learning-in","title":"Weakly supervised cross-modal learning in high-content screening","date":"2023-11-08","arxiv_id":"2311.04678","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gwatkinson/jump_download"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-clip-help-sound-source-localization","slug":"can-clip-help-sound-source-localization","title":"Can CLIP Help Sound Source Localization?","date":"2023-11-07","arxiv_id":"2311.04066","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["swimmiing/ACL-SSL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/recognize-any-regions","slug":"recognize-any-regions","title":"Recognize Any Regions","date":"2023-11-02","arxiv_id":"2311.01373","n_code_links":1,"syntology":{"ran":5,"of":11,"n_ran_checked":2,"n_instrument":3,"unverified":6,"pointer_only":11,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","official":{"repos":["surrey-uplab/recognize-any-regions"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/language-guided-visual-question-answering","slug":"language-guided-visual-question-answering","title":"Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts","date":"2023-10-31","arxiv_id":"2310.20159","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["declare-lab/lg-vqa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/videocrafter1-open-diffusion-models-for-high","slug":"videocrafter1-open-diffusion-models-for-high","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","date":"2023-10-30","arxiv_id":"2310.19512","n_code_links":3,"syntology":{"ran":10,"of":12,"n_ran_checked":9,"n_instrument":1,"unverified":2,"pointer_only":7,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ailab-cvc/videocrafter"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/anomalyclip-object-agnostic-prompt-learning","slug":"anomalyclip-object-agnostic-prompt-learning","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","date":"2023-10-29","arxiv_id":"2310.18961","n_code_links":3,"syntology":{"ran":19,"of":32,"n_ran_checked":14,"n_instrument":5,"unverified":13,"pointer_only":15,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","official":{"repos":["zqhang/anomalyclip"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/lp-ovod-open-vocabulary-object-detection-by","slug":"lp-ovod-open-vocabulary-object-detection-by","title":"LP-OVOD: Open-Vocabulary Object Detection by Linear Probing","date":"2023-10-26","arxiv_id":"2310.17109","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vinairesearch/lp-ovod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/emoclip-a-vision-language-method-for-zero","slug":"emoclip-a-vision-language-method-for-zero","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","date":"2023-10-25","arxiv_id":"2310.16640","n_code_links":1,"syntology":{"ran":4,"of":10,"n_ran_checked":4,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["nickyfot/emoclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/tic-clip-continual-training-of-clip-models","slug":"tic-clip-continual-training-of-clip-models","title":"TiC-CLIP: Continual Training of CLIP Models","date":"2023-10-24","arxiv_id":"2310.16226","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":9,"phrase":"5 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; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["apple/ml-tic-clip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-bla-benchmark-investigating-basic","slug":"the-bla-benchmark-investigating-basic","title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models","date":"2023-10-23","arxiv_id":"2310.15061","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":6,"n_instrument":5,"unverified":1,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shin-ee-chen/bla"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/inject-semantic-concepts-into-image-tagging","slug":"inject-semantic-concepts-into-image-tagging","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","date":"2023-10-23","arxiv_id":"2310.15200","n_code_links":2,"syntology":{"ran":7,"of":8,"n_ran_checked":5,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"7 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xinyu1205/recognize-anything"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/vision-language-models-are-zero-shot-reward","slug":"vision-language-models-are-zero-shot-reward","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","date":"2023-10-19","arxiv_id":"2310.12921","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alignmentresearch/vlmrm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/does-clip-s-generalization-performance-mainly","slug":"does-clip-s-generalization-performance-mainly","title":"Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?","date":"2023-10-14","arxiv_id":"2310.09562","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"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) · 2 unverified","official":{"repos":["brendel-group/clip-ood"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/extending-multi-modal-contrastive","slug":"extending-multi-modal-contrastive","title":"Extending Multi-modal Contrastive Representations","date":"2023-10-13","arxiv_id":"2310.08884","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mcr-peft/ex-mcr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-by-language-for-training-free","slug":"vision-by-language-for-training-free","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","date":"2023-10-13","arxiv_id":"2310.09291","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["explainableml/vision_by_language"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/distilling-from-vision-language-models-for","slug":"distilling-from-vision-language-models-for","title":"Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification","date":"2023-10-12","arxiv_id":"2310.08255","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":11,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["val-iisc/VL2V-ADiP"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mapping-memes-to-words-for-multimodal-hateful","slug":"mapping-memes-to-words-for-multimodal-hateful","title":"Mapping Memes to Words for Multimodal Hateful Meme Classification","date":"2023-10-12","arxiv_id":"2310.08368","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["miccunifi/issues"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/cross-modal-cognitive-consensus-guided-audio","slug":"cross-modal-cognitive-consensus-guided-audio","title":"Cross-modal Cognitive Consensus guided Audio-Visual Segmentation","date":"2023-10-10","arxiv_id":"2310.06259","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":9,"n_instrument":1,"unverified":2,"pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhaofengshi/avs-c3n"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/interpreting-clip-s-image-representation-via","slug":"interpreting-clip-s-image-representation-via","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","date":"2023-10-09","arxiv_id":"2310.05916","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yossigandelsman/clip_text_span"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gmmformer-gaussian-mixture-model-based","slug":"gmmformer-gaussian-mixture-model-based","title":"GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval","date":"2023-10-08","arxiv_id":"2310.05195","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huangmozhi9527/GMMFormer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/kandinsky-an-improved-text-to-image-synthesis","slug":"kandinsky-an-improved-text-to-image-synthesis","title":"Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion","date":"2023-10-05","arxiv_id":"2310.03502","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":7,"n_instrument":5,"unverified":6,"pointer_only":10,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ai-forever/Kandinsky-2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/better-safe-than-sorry-pre-training-clip","slug":"better-safe-than-sorry-pre-training-clip","title":"Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks","date":"2023-10-05","arxiv_id":"2310.05862","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":4,"n_instrument":1,"unverified":5,"pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["bigml-cs-ucla/safeclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/delving-into-clip-latent-space-for-video","slug":"delving-into-clip-latent-space-for-video","title":"Delving into CLIP latent space for Video Anomaly Recognition","date":"2023-10-04","arxiv_id":"2310.02835","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["luca-zanella-dvl/AnomalyCLIP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/sieve-multimodal-dataset-pruning-using-image","slug":"sieve-multimodal-dataset-pruning-using-image","title":"Sieve: Multimodal Dataset Pruning Using Image Captioning Models","date":"2023-10-03","arxiv_id":"2310.02110","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/sieve"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/controlling-vision-language-models-for","slug":"controlling-vision-language-models-for","title":"Controlling Vision-Language Models for Multi-Task Image Restoration","date":"2023-10-02","arxiv_id":"2310.01018","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":5,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["algolzw/daclip-uir"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/clipself-vision-transformer-distills-itself","slug":"clipself-vision-transformer-distills-itself","title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","date":"2023-10-02","arxiv_id":"2310.01403","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wusize/clipself"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-mask-aware-clip-representations-for","slug":"learning-mask-aware-clip-representations-for","title":"Learning Mask-aware CLIP Representations for Zero-Shot Segmentation","date":"2023-09-30","arxiv_id":"2310.00240","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"5 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jiaosiyu1999/maft"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/automatikz-text-guided-synthesis-of","slug":"automatikz-text-guided-synthesis-of","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","date":"2023-09-30","arxiv_id":"2310.00367","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["potamides/automatikz"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/domain-controlled-prompt-learning","slug":"domain-controlled-prompt-learning","title":"Domain-Controlled Prompt Learning","date":"2023-09-30","arxiv_id":"2310.07730","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["caoql98/dcpl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/practical-membership-inference-attacks-1","slug":"practical-membership-inference-attacks-1","title":"Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study","date":"2023-09-29","arxiv_id":"2310.00108","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":11,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ruoxi-jia-group/clip-mia"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":1,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/context-i2w-mapping-images-to-context","slug":"context-i2w-mapping-images-to-context","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","date":"2023-09-28","arxiv_id":"2309.16137","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pter61/context-i2w"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/demystifying-clip-data","slug":"demystifying-clip-data","title":"Demystifying CLIP Data","date":"2023-09-28","arxiv_id":"2309.16671","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["facebookresearch/metaclip"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/one-for-all-video-conversation-is-feasible","slug":"one-for-all-video-conversation-is-feasible","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","date":"2023-09-27","arxiv_id":"2309.15785","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["farewellthree/BT-Adapter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/geoclip-clip-inspired-alignment-between","slug":"geoclip-clip-inspired-alignment-between","title":"GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization","date":"2023-09-27","arxiv_id":"2309.16020","n_code_links":3,"syntology":{"ran":5,"of":13,"n_ran_checked":5,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["VicenteVivan/geo-clip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-diy-clip-dense-inference-yields-open","slug":"clip-diy-clip-dense-inference-yields-open","title":"CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free","date":"2023-09-25","arxiv_id":"2309.14289","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wysoczanska/clip-diy"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rewrite-caption-semantics-bridging-semantic-1","slug":"rewrite-caption-semantics-bridging-semantic-1","title":"Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation","date":"2023-09-24","arxiv_id":"2309.13505","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xing0047/rewrite"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/tinyclip-clip-distillation-via-affinity","slug":"tinyclip-clip-distillation-via-affinity","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","date":"2023-09-21","arxiv_id":"2309.12314","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["microsoft/Cream"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-sentence-speaks-a-thousand-images-domain","slug":"a-sentence-speaks-a-thousand-images-domain","title":"A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance","date":"2023-09-21","arxiv_id":"2309.12530","n_code_links":1,"syntology":{"ran":14,"of":16,"n_ran_checked":14,"n_instrument":0,"unverified":2,"pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["oodbag/rise"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-grained-temporal-prototype-learning-for","slug":"multi-grained-temporal-prototype-learning-for","title":"Multi-grained Temporal Prototype Learning for Few-shot Video Object Segmentation","date":"2023-09-20","arxiv_id":"2309.11160","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":5,"n_instrument":3,"unverified":2,"pointer_only":10,"phrase":"8 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nankepan/VIPMT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dreamllm-synergistic-multimodal-comprehension","slug":"dreamllm-synergistic-multimodal-comprehension","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","date":"2023-09-20","arxiv_id":"2309.11499","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["RunpeiDong/DreamLLM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/unsupervised-open-vocabulary-object","slug":"unsupervised-open-vocabulary-object","title":"Unsupervised Open-Vocabulary Object Localization in Videos","date":"2023-09-18","arxiv_id":"2309.09858","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":12,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["amazon-science/object-centric-vol"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/parameter-efficient-long-tailed-recognition","slug":"parameter-efficient-long-tailed-recognition","title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","date":"2023-09-18","arxiv_id":"2309.10019","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":1,"n_instrument":4,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["shijxcs/lift"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/livelyspeaker-towards-semantic-aware-co","slug":"livelyspeaker-towards-semantic-aware-co","title":"LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation","date":"2023-09-17","arxiv_id":"2309.09294","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zyhbili/livelyspeaker"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/disentangling-spatial-and-temporal-learning","slug":"disentangling-spatial-and-temporal-learning","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","date":"2023-09-14","arxiv_id":"2309.07911","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alibaba-mmai-research/dist"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/language-models-as-black-box-optimizers-for","slug":"language-models-as-black-box-optimizers-for","title":"Language Models as Black-Box Optimizers for Vision-Language Models","date":"2023-09-12","arxiv_id":"2309.05950","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":7,"n_instrument":1,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["shihongl1998/llm-as-a-blackbox-optimizer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/2309-06256","slug":"2309-06256","title":"Mitigating the Alignment Tax of RLHF","date":"2023-09-12","arxiv_id":"2309.06256","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["avalonstrel/mitigating-the-alignment-tax-of-rlhf"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi3drefer-grounding-text-description-to","slug":"multi3drefer-grounding-text-description-to","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","date":"2023-09-11","arxiv_id":"2309.05251","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["3dlg-hcvc/M3DRef-CLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffusion-model-is-secretly-a-training-free","slug":"diffusion-model-is-secretly-a-training-free","title":"Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter","date":"2023-09-06","arxiv_id":"2309.02773","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["VCG-team/DiffSegmenter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unified-pre-training-with-pseudo-texts-for-1","slug":"unified-pre-training-with-pseudo-texts-for-1","title":"Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification","date":"2023-09-04","arxiv_id":"2309.01420","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":1,"n_instrument":3,"unverified":4,"pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zhiyinshao-h/unipt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/nllb-clip-train-performant-multilingual-image","slug":"nllb-clip-train-performant-multilingual-image","title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","date":"2023-09-04","arxiv_id":"2309.01859","n_code_links":4,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/image-hijacking-adversarial-images-can","slug":"image-hijacking-adversarial-images-can","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","date":"2023-09-01","arxiv_id":"2309.00236","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["euanong/image-hijacks"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/anovl-adapting-vision-language-models-for","slug":"anovl-adapting-vision-language-models-for","title":"Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization","date":"2023-08-30","arxiv_id":"2308.15939","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":5,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hq-deng/AnoVL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/read-only-prompt-optimization-for-vision","slug":"read-only-prompt-optimization-for-vision","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","date":"2023-08-29","arxiv_id":"2308.14960","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["mlvlab/rpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/clipn-for-zero-shot-ood-detection-teaching","slug":"clipn-for-zero-shot-ood-detection-teaching","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","date":"2023-08-23","arxiv_id":"2308.12213","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":8,"n_instrument":2,"unverified":6,"pointer_only":2,"phrase":"10 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["xmed-lab/clipn"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":1,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/villa-fine-grained-vision-language","slug":"villa-fine-grained-vision-language","title":"ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data","date":"2023-08-22","arxiv_id":"2308.11194","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["stanfordmimi/villa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/composed-image-retrieval-using-contrastive","slug":"composed-image-retrieval-using-contrastive","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","date":"2023-08-22","arxiv_id":"2308.11485","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ABaldrati/CLIP4Cir"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vadclip-adapting-vision-language-models-for","slug":"vadclip-adapting-vision-language-models-for","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","date":"2023-08-22","arxiv_id":"2308.11681","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nwpu-zxr/vadclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"a0fef63b3d79c15f11240589831749cc27859f42e2ffb92faa39b42fd4e31f8e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}