{"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":"/task/text-retrieval/papers/2","list_of":"/task/text-retrieval","task":"Text Retrieval","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":7,"rows_per_page":100,"rows":[101,200],"of":671,"counts":{"archive_papers_tagged":671,"with_a_code_link":335,"where_syntology_ran_a_sample":117,"not_listed_spam_title":0,"listed":671,"listed_where_code_ran":117,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":99,"every_run_a_failure_of_syntologys_instrument":18,"listed_with_a_run_with_no_instrument_failure":99,"listed_every_run_a_failure_of_syntologys_instrument":18,"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":"/task/text-retrieval","prev":"/task/text-retrieval","next":"/task/text-retrieval/papers/3","papers":[{"url":"/paper/partial-scene-text-retrieval","slug":"partial-scene-text-retrieval","title":"Partial Scene Text Retrieval","date":"2024-11-15","arxiv_id":"2411.10261","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":15,"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) · 1 unverified","sample_list":"/paper/partial-scene-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.10261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10261"}},"official":{"repos":["lanfeng4659/pstr"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/nearest-neighbor-normalization-improves","slug":"nearest-neighbor-normalization-improves","title":"Nearest Neighbor Normalization Improves Multimodal Retrieval","date":"2024-10-31","arxiv_id":"2410.24114","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-vision-language-pre-training-for","slug":"multilingual-vision-language-pre-training-for","title":"Multilingual Vision-Language Pre-training for the Remote Sensing Domain","date":"2024-10-30","arxiv_id":"2410.23370","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-text-optimizing-rag-with-multimodal","slug":"beyond-text-optimizing-rag-with-multimodal","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","date":"2024-10-29","arxiv_id":"2410.21943","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-text-optimizing-rag-with-multimodal#ran","syntology_url":"https://syntology.ai/paper/2410.21943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21943"}},"official":{"repos":["riedlerm/multimodal_rag_for_industry"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gssf-generalized-structural-sparse-function","slug":"gssf-generalized-structural-sparse-function","title":"GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning","date":"2024-10-20","arxiv_id":"2410.15266","repositories_listed":1,"syntology":null},{"url":"/paper/decomposing-relationship-from-1-to-n-into-n-1","slug":"decomposing-relationship-from-1-to-n-into-n-1","title":"Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval","date":"2024-10-09","arxiv_id":"2410.06618","repositories_listed":1,"syntology":null},{"url":"/paper/from-unimodal-to-multimodal-scaling-up","slug":"from-unimodal-to-multimodal-scaling-up","title":"From Unimodal to Multimodal: Scaling up Projectors to Align Modalities","date":"2024-09-28","arxiv_id":"2409.19425","repositories_listed":1,"syntology":null},{"url":"/paper/reclap-improving-zero-shot-audio","slug":"reclap-improving-zero-shot-audio","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","date":"2024-09-13","arxiv_id":"2409.09213","repositories_listed":1,"syntology":null},{"url":"/paper/modoc-a-modular-interface-for-flexible","slug":"modoc-a-modular-interface-for-flexible","title":"MODOC: A Modular Interface for Flexible Interlinking of Text Retrieval and Text Generation Functions","date":"2024-08-26","arxiv_id":"2408.14623","repositories_listed":1,"syntology":null},{"url":"/paper/mistral-splade-llms-for-for-better-learned","slug":"mistral-splade-llms-for-for-better-learned","title":"Mistral-SPLADE: LLMs for better Learned Sparse Retrieval","date":"2024-08-20","arxiv_id":"2408.11119","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02272","slug":"2408-02272","title":"COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark","date":"2024-08-05","arxiv_id":"2408.02272","repositories_listed":1,"syntology":null},{"url":"/paper/focus-distinguish-and-prompt-unleashing-clip","slug":"focus-distinguish-and-prompt-unleashing-clip","title":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","date":"2024-08-01","arxiv_id":"2408.00441","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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","sample_list":"/paper/focus-distinguish-and-prompt-unleashing-clip#ran","syntology_url":"https://syntology.ai/paper/2408.00441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00441"}},"official":{"repos":["gyann-z/fdp"],"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"]}}},{"url":"/paper/2407-21757","slug":"2407-21757","title":"Learning Video Context as Interleaved Multimodal Sequences","date":"2024-07-31","arxiv_id":"2407.21757","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/2407-21757#ran","syntology_url":"https://syntology.ai/paper/2407.21757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21757"}},"official":{"repos":["showlab/movieseq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gabinsight-exploring-gender-activity-binding","slug":"gabinsight-exploring-gender-activity-binding","title":"GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models","date":"2024-07-30","arxiv_id":"2407.21001","repositories_listed":1,"syntology":null},{"url":"/paper/fico-itr-bridging-fine-grained-and-coarse","slug":"fico-itr-bridging-fine-grained-and-coarse","title":"FiCo-ITR: bridging fine-grained and coarse-grained image-text retrieval for comparative performance analysis","date":"2024-07-29","arxiv_id":"2407.20114","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-cluster-discrimination-for-visual","slug":"multi-label-cluster-discrimination-for-visual","title":"Multi-label Cluster Discrimination for Visual Representation Learning","date":"2024-07-24","arxiv_id":"2407.17331","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 7 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) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}},"official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/object-aware-query-perturbation-for-cross","slug":"object-aware-query-perturbation-for-cross","title":"Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval","date":"2024-07-17","arxiv_id":"2407.12346","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/object-aware-query-perturbation-for-cross#ran","syntology_url":"https://syntology.ai/paper/2407.12346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12346"}},"official":{"repos":["nec-n-sogi/query-perturbation"],"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"]}}},{"url":"/paper/bright-a-realistic-and-challenging-benchmark","slug":"bright-a-realistic-and-challenging-benchmark","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","date":"2024-07-16","arxiv_id":"2407.12883","repositories_listed":1,"syntology":null},{"url":"/paper/video-language-alignment-pre-training-via","slug":"video-language-alignment-pre-training-via","title":"Video-Language Alignment via Spatio-Temporal Graph Transformer","date":"2024-07-16","arxiv_id":"2407.11677","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-text-based-quantitative-and","slug":"towards-a-text-based-quantitative-and","title":"Towards a text-based quantitative and explainable histopathology image analysis","date":"2024-07-10","arxiv_id":"2407.07360","repositories_listed":1,"syntology":null},{"url":"/paper/neurocache-efficient-vector-retrieval-for","slug":"neurocache-efficient-vector-retrieval-for","title":"Neurocache: Efficient Vector Retrieval for Long-range Language Modeling","date":"2024-07-02","arxiv_id":"2407.02486","repositories_listed":1,"syntology":null},{"url":"/paper/cvlue-a-new-benchmark-dataset-for-chinese","slug":"cvlue-a-new-benchmark-dataset-for-chinese","title":"CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation","date":"2024-07-01","arxiv_id":"2407.01081","repositories_listed":1,"syntology":null},{"url":"/paper/signclip-connecting-text-and-sign-language-by","slug":"signclip-connecting-text-and-sign-language-by","title":"SignCLIP: Connecting Text and Sign Language by Contrastive Learning","date":"2024-07-01","arxiv_id":"2407.01264","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-consistency-in-cross-lingual","slug":"improving-the-consistency-in-cross-lingual","title":"Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning","date":"2024-06-26","arxiv_id":"2406.18254","repositories_listed":1,"syntology":null},{"url":"/paper/news-without-borders-domain-adaptation-of","slug":"news-without-borders-domain-adaptation-of","title":"News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation","date":"2024-06-18","arxiv_id":"2406.12634","repositories_listed":1,"syntology":null},{"url":"/paper/symmetric-multi-similarity-loss-for-epic","slug":"symmetric-multi-similarity-loss-for-epic","title":"Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024","date":"2024-06-18","arxiv_id":"2406.12256","repositories_listed":1,"syntology":null},{"url":"/paper/composing-object-relations-and-attributes-for-1","slug":"composing-object-relations-and-attributes-for-1","title":"Composing Object Relations and Attributes for Image-Text Matching","date":"2024-06-17","arxiv_id":"2406.11820","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/composing-object-relations-and-attributes-for-1#ran","syntology_url":"https://syntology.ai/paper/2406.11820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11820"}},"official":{"repos":["vkhoi/cora_cvpr24"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bivlc-extending-vision-language","slug":"bivlc-extending-vision-language","title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","date":"2024-06-14","arxiv_id":"2406.09952","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/bivlc-extending-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.09952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09952"}},"official":{"repos":["imirandam/bivlc"],"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"]}}},{"url":"/paper/towards-vision-language-geo-foundation-model","slug":"towards-vision-language-geo-foundation-model","title":"Towards Vision-Language Geo-Foundation Model: A Survey","date":"2024-06-13","arxiv_id":"2406.09385","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-language-gaps-in-audio-text","slug":"bridging-language-gaps-in-audio-text","title":"Bridging Language Gaps in Audio-Text Retrieval","date":"2024-06-11","arxiv_id":"2406.07012","repositories_listed":1,"syntology":null},{"url":"/paper/which-country-is-this-automatic-country","slug":"which-country-is-this-automatic-country","title":"Which Country Is This? Automatic Country Ranking of Street View Photos","date":"2024-06-11","arxiv_id":"2406.07227","repositories_listed":1,"syntology":null},{"url":"/paper/diving-deep-into-the-motion-representation-of","slug":"diving-deep-into-the-motion-representation-of","title":"Diving Deep into the Motion Representation of Video-Text Models","date":"2024-06-07","arxiv_id":"2406.05075","repositories_listed":1,"syntology":null},{"url":"/paper/a-bi-metric-framework-for-fast-similarity","slug":"a-bi-metric-framework-for-fast-similarity","title":"A Bi-metric Framework for Fast Similarity Search","date":"2024-06-05","arxiv_id":"2406.02891","repositories_listed":1,"syntology":null},{"url":"/paper/transcending-fusion-a-multi-scale-alignment","slug":"transcending-fusion-a-multi-scale-alignment","title":"Transcending Fusion: A Multi-Scale Alignment Method for Remote Sensing Image-Text Retrieval","date":"2024-05-29","arxiv_id":"2405.18959","repositories_listed":1,"syntology":null},{"url":"/paper/ldmol-text-conditioned-molecule-diffusion","slug":"ldmol-text-conditioned-molecule-diffusion","title":"LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space","date":"2024-05-28","arxiv_id":"2405.17829","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":2,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ldmol-text-conditioned-molecule-diffusion#ran","syntology_url":"https://syntology.ai/paper/2405.17829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17829"}},"official":{"repos":["jinhojsk515/ldmol"],"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","unlocated"]}}},{"url":"/paper/cocktail-a-comprehensive-information","slug":"cocktail-a-comprehensive-information","title":"Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration","date":"2024-05-26","arxiv_id":"2405.16546","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-transformers-with-spectrum-1","slug":"accelerating-transformers-with-spectrum-1","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","date":"2024-05-25","arxiv_id":"2405.16148","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/accelerating-transformers-with-spectrum-1#ran","syntology_url":"https://syntology.ai/paper/2405.16148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16148"}},"official":{"repos":["hchautran/PiToMe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prott3-protein-to-text-generation-for-text","slug":"prott3-protein-to-text-generation-for-text","title":"ProtT3: Protein-to-Text Generation for Text-based Protein Understanding","date":"2024-05-21","arxiv_id":"2405.12564","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":13,"phrase":"8 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/prott3-protein-to-text-generation-for-text#ran","syntology_url":"https://syntology.ai/paper/2405.12564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12564"}},"official":{"repos":["acharkq/prott3"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/pir-remote-sensing-image-text-retrieval-with","slug":"pir-remote-sensing-image-text-retrieval-with","title":"PIR: Remote Sensing Image-Text Retrieval with Prior Instruction Representation Learning","date":"2024-05-16","arxiv_id":"2405.10160","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-deep-audio-text-retrieval-through","slug":"revisiting-deep-audio-text-retrieval-through","title":"Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation","date":"2024-05-16","arxiv_id":"2405.10084","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"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","sample_list":"/paper/revisiting-deep-audio-text-retrieval-through#ran","syntology_url":"https://syntology.ai/paper/2405.10084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10084"}},"official":{"repos":["v-manhlt3/m-ltm-audio-text-retrieval"],"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"]}}},{"url":"/paper/explaining-text-similarity-in-transformer","slug":"explaining-text-similarity-in-transformer","title":"Explaining Text Similarity in Transformer Models","date":"2024-05-10","arxiv_id":"2405.06604","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/explaining-text-similarity-in-transformer#ran","syntology_url":"https://syntology.ai/paper/2405.06604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06604"}},"official":{"repos":["alevas/xai_similarity_transformers"],"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"]}}},{"url":"/paper/procis-a-benchmark-for-proactive-retrieval-in","slug":"procis-a-benchmark-for-proactive-retrieval-in","title":"ProCIS: A Benchmark for Proactive Retrieval in Conversations","date":"2024-05-10","arxiv_id":"2405.06460","repositories_listed":1,"syntology":null},{"url":"/paper/refining-joint-text-and-source-code","slug":"refining-joint-text-and-source-code","title":"Refining Joint Text and Source Code Embeddings for Retrieval Task with Parameter-Efficient Fine-Tuning","date":"2024-05-07","arxiv_id":"2405.04126","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-positional-bias-for-query-agnostic","slug":"exploiting-positional-bias-for-query-agnostic","title":"Exploiting Positional Bias for Query-Agnostic Generative Content in Search","date":"2024-05-01","arxiv_id":"2405.00469","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-inverted-indexes-for-approximate","slug":"efficient-inverted-indexes-for-approximate","title":"Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations","date":"2024-04-29","arxiv_id":"2404.18812","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_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) · 1 unverified","sample_list":"/paper/efficient-inverted-indexes-for-approximate#ran","syntology_url":"https://syntology.ai/paper/2404.18812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18812"}},"official":{"repos":["tuskanny/seismic"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/efficient-remote-sensing-with-harmonized","slug":"efficient-remote-sensing-with-harmonized","title":"Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment","date":"2024-04-28","arxiv_id":"2404.18253","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 5 unverified","sample_list":"/paper/efficient-remote-sensing-with-harmonized#ran","syntology_url":"https://syntology.ai/paper/2404.18253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18253"}},"official":{"repos":["seekerhuang/harma"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/shallow-cross-encoders-for-low-latency","slug":"shallow-cross-encoders-for-low-latency","title":"Shallow Cross-Encoders for Low-Latency Retrieval","date":"2024-03-29","arxiv_id":"2403.20222","repositories_listed":1,"syntology":null},{"url":"/paper/arabicaqa-a-comprehensive-dataset-for-arabic","slug":"arabicaqa-a-comprehensive-dataset-for-arabic","title":"ArabicaQA: A Comprehensive Dataset for Arabic Question Answering","date":"2024-03-26","arxiv_id":"2403.17848","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/arabicaqa-a-comprehensive-dataset-for-arabic#ran","syntology_url":"https://syntology.ai/paper/2403.17848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17848"}},"official":{"repos":["datascienceuibk/arabicaqa"],"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"]}}},{"url":"/paper/denoising-table-text-retrieval-for-open","slug":"denoising-table-text-retrieval-for-open","title":"Denoising Table-Text Retrieval for Open-Domain Question Answering","date":"2024-03-26","arxiv_id":"2403.17611","repositories_listed":1,"syntology":null},{"url":"/paper/dreamlip-language-image-pre-training-with","slug":"dreamlip-language-image-pre-training-with","title":"DreamLIP: Language-Image Pre-training with Long Captions","date":"2024-03-25","arxiv_id":"2403.17007","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dreamlip-language-image-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2403.17007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17007"}},"official":{"repos":["zyf0619sjtu/DreamLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/followir-evaluating-and-teaching-information","slug":"followir-evaluating-and-teaching-information","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","date":"2024-03-22","arxiv_id":"2403.15246","repositories_listed":1,"syntology":null},{"url":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}},"official":{"repos":["mlvlab/vid-tldr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-transferability-in-vision-language","slug":"boosting-transferability-in-vision-language","title":"Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory","date":"2024-03-19","arxiv_id":"2403.12445","repositories_listed":1,"syntology":null},{"url":"/paper/eye-gaze-guided-multi-modal-alignment","slug":"eye-gaze-guided-multi-modal-alignment","title":"Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning","date":"2024-03-19","arxiv_id":"2403.12416","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"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","sample_list":"/paper/eye-gaze-guided-multi-modal-alignment#ran","syntology_url":"https://syntology.ai/paper/2403.12416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12416"}},"official":{"repos":["momarky/egma"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/cross-modal-and-uni-modal-soft-label","slug":"cross-modal-and-uni-modal-soft-label","title":"Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval","date":"2024-03-08","arxiv_id":"2403.05261","repositories_listed":1,"syntology":null},{"url":"/paper/panda-70m-captioning-70m-videos-with-multiple","slug":"panda-70m-captioning-70m-videos-with-multiple","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","date":"2024-02-29","arxiv_id":"2402.19479","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-learned-sparse-retrieval-with","slug":"multimodal-learned-sparse-retrieval-with","title":"Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control","date":"2024-02-27","arxiv_id":"2402.17535","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/multimodal-learned-sparse-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2402.17535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17535"}},"official":{"repos":["thongnt99/lsr-multimodal"],"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"]}}},{"url":"/paper/longagent-scaling-language-models-to-128k","slug":"longagent-scaling-language-models-to-128k","title":"LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration","date":"2024-02-18","arxiv_id":"2402.11550","repositories_listed":1,"syntology":null},{"url":"/paper/distillation-enhanced-generative-retrieval","slug":"distillation-enhanced-generative-retrieval","title":"Distillation Enhanced Generative Retrieval","date":"2024-02-16","arxiv_id":"2402.10769","repositories_listed":1,"syntology":null},{"url":"/paper/m2-raap-a-multi-modal-recipe-for-advancing","slug":"m2-raap-a-multi-modal-recipe-for-advancing","title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","date":"2024-01-31","arxiv_id":"2401.17797","repositories_listed":1,"syntology":null},{"url":"/paper/embracing-language-inclusivity-and-diversity","slug":"embracing-language-inclusivity-and-diversity","title":"Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning","date":"2024-01-30","arxiv_id":"2401.17186","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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","sample_list":"/paper/embracing-language-inclusivity-and-diversity#ran","syntology_url":"https://syntology.ai/paper/2401.17186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17186"}},"official":{"repos":["yangbang18/clfm"],"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"]}}},{"url":"/paper/towards-3d-molecule-text-interpretation-in","slug":"towards-3d-molecule-text-interpretation-in","title":"Towards 3D Molecule-Text Interpretation in Language Models","date":"2024-01-25","arxiv_id":"2401.13923","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-3d-molecule-text-interpretation-in#ran","syntology_url":"https://syntology.ai/paper/2401.13923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13923"}},"official":{"repos":["lsh0520/3d-molm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-image-text-matching-with-adaptive","slug":"enhancing-image-text-matching-with-adaptive","title":"Enhancing Image-Text Matching with Adaptive Feature Aggregation","date":"2024-01-18","arxiv_id":"2401.09725","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-the-impact-of-false-negatives-in","slug":"mitigating-the-impact-of-false-negatives-in","title":"Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization","date":"2023-12-30","arxiv_id":"2401.00165","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 4 unverified","sample_list":"/paper/mitigating-the-impact-of-false-negatives-in#ran","syntology_url":"https://syntology.ai/paper/2401.00165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00165"}},"official":{"repos":["wangskygit/passage-sieve"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pros-prompting-to-simulate-generalized","slug":"pros-prompting-to-simulate-generalized","title":"ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval","date":"2023-12-19","arxiv_id":"2312.12478","repositories_listed":1,"syntology":null},{"url":"/paper/predictive-chemistry-augmented-with-text","slug":"predictive-chemistry-augmented-with-text","title":"Predictive Chemistry Augmented with Text Retrieval","date":"2023-12-08","arxiv_id":"2312.04881","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/predictive-chemistry-augmented-with-text#ran","syntology_url":"https://syntology.ai/paper/2312.04881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04881"}},"official":{"repos":["thomas0809/textreact"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/pefa-parameter-free-adapters-for-large-scale","slug":"pefa-parameter-free-adapters-for-large-scale","title":"PEFA: Parameter-Free Adapters for Large-scale Embedding-based Retrieval Models","date":"2023-12-05","arxiv_id":"2312.02429","repositories_listed":1,"syntology":null},{"url":"/paper/mllms-augmented-visual-language","slug":"mllms-augmented-visual-language","title":"MLLMs-Augmented Visual-Language Representation Learning","date":"2023-11-30","arxiv_id":"2311.18765","repositories_listed":1,"syntology":null},{"url":"/paper/synthesize-diagnose-and-optimize-towards-fine","slug":"synthesize-diagnose-and-optimize-towards-fine","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","date":"2023-11-30","arxiv_id":"2312.00081","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"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) · 7 unverified","sample_list":"/paper/synthesize-diagnose-and-optimize-towards-fine#ran","syntology_url":"https://syntology.ai/paper/2312.00081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00081"}},"official":{"repos":["wjpoom/spec"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/ai-generated-images-introduce-invisible","slug":"ai-generated-images-introduce-invisible","title":"Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images","date":"2023-11-23","arxiv_id":"2311.14084","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-text-retrieval-with","slug":"towards-robust-text-retrieval-with","title":"Towards Robust Text Retrieval with Progressive Learning","date":"2023-11-20","arxiv_id":"2311.11691","repositories_listed":1,"syntology":null},{"url":"/paper/text-retrieval-with-multi-stage-re-ranking","slug":"text-retrieval-with-multi-stage-re-ranking","title":"Text Retrieval with Multi-Stage Re-Ranking Models","date":"2023-11-14","arxiv_id":"2311.07994","repositories_listed":1,"syntology":null},{"url":"/paper/glen-generative-retrieval-via-lexical-index","slug":"glen-generative-retrieval-via-lexical-index","title":"GLEN: Generative Retrieval via Lexical Index Learning","date":"2023-11-06","arxiv_id":"2311.03057","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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) · 2 unverified","sample_list":"/paper/glen-generative-retrieval-via-lexical-index#ran","syntology_url":"https://syntology.ai/paper/2311.03057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03057"}},"official":{"repos":["skleee/GLEN"],"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":["found_in_text","official"]}}},{"url":"/paper/harvest-video-foundation-models-via-efficient","slug":"harvest-video-foundation-models-via-efficient","title":"Harvest Video Foundation Models via Efficient Post-Pretraining","date":"2023-10-30","arxiv_id":"2310.19554","repositories_listed":1,"syntology":null},{"url":"/paper/a-prior-instruction-representation-framework","slug":"a-prior-instruction-representation-framework","title":"A Prior Instruction Representation Framework for Remote Sensing Image-text Retrieval","date":"2023-10-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unlock-multi-modal-capability-of-dense","slug":"unlock-multi-modal-capability-of-dense","title":"MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin","date":"2023-10-21","arxiv_id":"2310.14037","repositories_listed":1,"syntology":{"n":18,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":0,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unlock-multi-modal-capability-of-dense#ran","syntology_url":"https://syntology.ai/paper/2310.14037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14037"}},"official":{"repos":["openmatch/marvel"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/molca-molecular-graph-language-modeling-with","slug":"molca-molecular-graph-language-modeling-with","title":"MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter","date":"2023-10-19","arxiv_id":"2310.12798","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":16,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/molca-molecular-graph-language-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2310.12798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12798"}},"official":{"repos":["acharkq/molca"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/extending-multi-modal-contrastive","slug":"extending-multi-modal-contrastive","title":"Extending Multi-modal Contrastive Representations","date":"2023-10-13","arxiv_id":"2310.08884","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/extending-multi-modal-contrastive#ran","syntology_url":"https://syntology.ai/paper/2310.08884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08884"}},"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"]}}},{"url":"/paper/on-using-gui-interaction-data-to-improve-text","slug":"on-using-gui-interaction-data-to-improve-text","title":"On Using GUI Interaction Data to Improve Text Retrieval-based Bug Localization","date":"2023-10-12","arxiv_id":"2310.08083","repositories_listed":1,"syntology":null},{"url":"/paper/from-scarcity-to-efficiency-improving-clip","slug":"from-scarcity-to-efficiency-improving-clip","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","date":"2023-10-11","arxiv_id":"2310.07699","repositories_listed":1,"syntology":null},{"url":"/paper/building-an-open-vocabulary-video-clip-model","slug":"building-an-open-vocabulary-video-clip-model","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","date":"2023-10-08","arxiv_id":"2310.05010","repositories_listed":1,"syntology":null},{"url":"/paper/prototype-based-aleatoric-uncertainty-1","slug":"prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","arxiv_id":"2309.17093","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":10,"n_instrument":7,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":7,"n_pointer_only":8,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/prototype-based-aleatoric-uncertainty-1#ran","syntology_url":"https://syntology.ai/paper/2309.17093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17093"}},"official":{"repos":["leolee99/pau"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/implicit-differentiable-outlier-detection","slug":"implicit-differentiable-outlier-detection","title":"Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-09-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-open-domain-table-question","slug":"enhancing-open-domain-table-question","title":"Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval","date":"2023-09-19","arxiv_id":"2309.10506","repositories_listed":1,"syntology":null},{"url":"/paper/unified-coarse-to-fine-alignment-for-video","slug":"unified-coarse-to-fine-alignment-for-video","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","date":"2023-09-18","arxiv_id":"2309.10091","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":4,"phrase":"11 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unified-coarse-to-fine-alignment-for-video#ran","syntology_url":"https://syntology.ai/paper/2309.10091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10091"}},"official":{"repos":["ziyang412/ucofia"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/multiway-adapater-adapting-large-scale-multi","slug":"multiway-adapater-adapting-large-scale-multi","title":"MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval","date":"2023-09-04","arxiv_id":"2309.01516","repositories_listed":1,"syntology":null},{"url":"/paper/linktransformer-a-unified-package-for-record","slug":"linktransformer-a-unified-package-for-record","title":"LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models","date":"2023-09-02","arxiv_id":"2309.00789","repositories_listed":1,"syntology":null},{"url":"/paper/unipt-universal-parallel-tuning-for-transfer","slug":"unipt-universal-parallel-tuning-for-transfer","title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","date":"2023-08-28","arxiv_id":"2308.14316","repositories_listed":1,"syntology":null},{"url":"/paper/towards-fast-and-accurate-image-text","slug":"towards-fast-and-accurate-image-text","title":"Towards Fast and Accurate Image-Text Retrieval with Self-Supervised Fine-Grained Alignment","date":"2023-08-27","arxiv_id":"2308.14009","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-transfer-learning-for-1","slug":"parameter-efficient-transfer-learning-for-1","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","date":"2023-08-24","arxiv_id":"2308.12509","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/parameter-efficient-transfer-learning-for-1#ran","syntology_url":"https://syntology.ai/paper/2308.12509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12509"}},"official":{"repos":["ZhanYang-nwpu/PE-RSITR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/multi-event-video-text-retrieval","slug":"multi-event-video-text-retrieval","title":"Multi-event Video-Text Retrieval","date":"2023-08-22","arxiv_id":"2308.11551","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":18,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-event-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2308.11551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11551"}},"official":{"repos":["gengyuanmax/mevtr"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/alip-adaptive-language-image-pre-training","slug":"alip-adaptive-language-image-pre-training","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","date":"2023-08-16","arxiv_id":"2308.08428","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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","sample_list":"/paper/alip-adaptive-language-image-pre-training#ran","syntology_url":"https://syntology.ai/paper/2308.08428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08428"}},"official":{"repos":["deepglint/alip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/helping-hands-an-object-aware-ego-centric","slug":"helping-hands-an-object-aware-ego-centric","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","date":"2023-08-15","arxiv_id":"2308.07918","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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","sample_list":"/paper/helping-hands-an-object-aware-ego-centric#ran","syntology_url":"https://syntology.ai/paper/2308.07918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07918"}},"official":{"repos":["chuhanxx/helping_hand_for_egocentric_videos"],"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"]}}},{"url":"/paper/advclip-downstream-agnostic-adversarial","slug":"advclip-downstream-agnostic-adversarial","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","date":"2023-08-14","arxiv_id":"2308.07026","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":5,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/advclip-downstream-agnostic-adversarial#ran","syntology_url":"https://syntology.ai/paper/2308.07026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07026"}},"official":{"repos":["cgcl-codes/advclip"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-all-seeing-project-towards-panoptic","slug":"the-all-seeing-project-towards-panoptic","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","date":"2023-08-03","arxiv_id":"2308.01907","repositories_listed":1,"syntology":null},{"url":"/paper/set-level-guidance-attack-boosting","slug":"set-level-guidance-attack-boosting","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","date":"2023-07-26","arxiv_id":"2307.14061","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":1,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"9 ran (of which 1 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) · 3 unverified","sample_list":"/paper/set-level-guidance-attack-boosting#ran","syntology_url":"https://syntology.ai/paper/2307.14061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14061"}},"official":{"repos":["Zoky-2020/Set-level_Guidance_Attack"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/prior-prototype-representation-joint-learning","slug":"prior-prototype-representation-joint-learning","title":"PRIOR: Prototype Representation Joint Learning from Medical Images and Reports","date":"2023-07-24","arxiv_id":"2307.12577","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/prior-prototype-representation-joint-learning#ran","syntology_url":"https://syntology.ai/paper/2307.12577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12577"}},"official":{"repos":["qtacierp/prior"],"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"]}}},{"url":"/paper/mclip-multilingual-clip-via-cross-lingual","slug":"mclip-multilingual-clip-via-cross-lingual","title":"mCLIP: Multilingual CLIP via Cross-lingual Transfer","date":"2023-07-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stop-pre-training-adapt-visual-language","slug":"stop-pre-training-adapt-visual-language","title":"Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages","date":"2023-06-29","arxiv_id":"2306.16774","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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) · 0 unverified","sample_list":"/paper/stop-pre-training-adapt-visual-language#ran","syntology_url":"https://syntology.ai/paper/2306.16774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16774"}},"official":{"repos":["yasminekaroui/clicotea"],"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"]}}},{"url":"/paper/msvd-indonesian-a-benchmark-for-multimodal","slug":"msvd-indonesian-a-benchmark-for-multimodal","title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","date":"2023-06-20","arxiv_id":"2306.11341","repositories_listed":1,"syntology":null}],"record_sha256":"b4af03f1aee6f572b6e9c80669791cd51526f2f0835ddbd0de6e7af3c5b9b340","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}