{"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/cross-modal-alignment","name":"cross-modal alignment","slug":"cross-modal-alignment","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":342,"papers_with_code":151,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/gaze-cifar-10","name":"Gaze-CIFAR-10","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":342,"of_with_code":151,"tagged_in_all":342,"counts":{"archive_papers_tagged":342,"with_a_code_link":151,"where_syntology_ran_a_sample":47,"not_listed_spam_title":0,"listed":342,"listed_where_code_ran":47,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":38,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":38,"listed_every_run_a_failure_of_syntologys_instrument":9,"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"},"items":[{"url":"/paper/layoutlmv3-pre-training-for-document-ai-with","slug":"layoutlmv3-pre-training-for-document-ai-with","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","date":"2022-04-18","arxiv_id":"2204.08387","repositories_listed":4,"syntology":null},{"url":"/paper/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","repositories_listed":3,"syntology":null},{"url":"/paper/skywork-r1v3-technical-report","slug":"skywork-r1v3-technical-report","title":"Skywork-R1V3 Technical Report","date":"2025-07-08","arxiv_id":"2507.06167","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":12,"phrase":"11 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; 9 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/skywork-r1v3-technical-report#ran","syntology_url":"https://syntology.ai/paper/2507.06167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06167"}},"official":{"repos":["SkyworkAI/Skywork-R1V"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/desta2-5-audio-toward-general-purpose-large","slug":"desta2-5-audio-toward-general-purpose-large","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","date":"2025-07-03","arxiv_id":"2507.02768","repositories_listed":2,"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/desta2-5-audio-toward-general-purpose-large#ran","syntology_url":"https://syntology.ai/paper/2507.02768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.02768"}},"official":{"repos":["kehanlu/desta2.5-audio"],"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/multi-granularity-cross-modal-alignment-for","slug":"multi-granularity-cross-modal-alignment-for","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","date":"2022-10-12","arxiv_id":"2210.06044","repositories_listed":2,"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/multi-granularity-cross-modal-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2210.06044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06044"}},"official":{"repos":["fuying-wang/mgca"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/bridge-tower-building-bridges-between","slug":"bridge-tower-building-bridges-between","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","date":"2022-06-17","arxiv_id":"2206.08657","repositories_listed":2,"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/bridge-tower-building-bridges-between#ran","syntology_url":"https://syntology.ai/paper/2206.08657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08657"}},"official":{"repos":["microsoft/BridgeTower"],"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/rsrefseg-2-decoupling-referring-remote","slug":"rsrefseg-2-decoupling-referring-remote","title":"RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation Models","date":"2025-07-08","arxiv_id":"2507.06231","repositories_listed":1,"syntology":null},{"url":"/paper/flash-vstream-efficient-real-time","slug":"flash-vstream-efficient-real-time","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","date":"2025-06-30","arxiv_id":"2506.23825","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 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; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/flash-vstream-efficient-real-time#ran","syntology_url":"https://syntology.ai/paper/2506.23825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.23825"}},"official":{"repos":["IVGSZ/Flash-VStream"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperpath-knowledge-guided-hyperbolic","slug":"hyperpath-knowledge-guided-hyperbolic","title":"HyperPath: Knowledge-Guided Hyperbolic Semantic Hierarchy Modeling for WSI Analysis","date":"2025-06-19","arxiv_id":"2506.16398","repositories_listed":1,"syntology":null},{"url":"/paper/omnidrca-parallel-speech-text-foundation","slug":"omnidrca-parallel-speech-text-foundation","title":"OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment","date":"2025-06-11","arxiv_id":"2506.09349","repositories_listed":1,"syntology":null},{"url":"/paper/reid5o-achieving-omni-multi-modal-person-re","slug":"reid5o-achieving-omni-multi-modal-person-re","title":"ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model","date":"2025-06-11","arxiv_id":"2506.09385","repositories_listed":1,"syntology":null},{"url":"/paper/modality-curation-building-universal","slug":"modality-curation-building-universal","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","date":"2025-05-26","arxiv_id":"2505.19650","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/modality-curation-building-universal#ran","syntology_url":"https://syntology.ai/paper/2505.19650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19650"}},"official":{"repos":["friedrichor/UNITE"],"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/icpl-reid-identity-conditional-prompt","slug":"icpl-reid-identity-conditional-prompt","title":"ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identification","date":"2025-05-23","arxiv_id":"2505.17821","repositories_listed":1,"syntology":null},{"url":"/paper/u-sam-an-audio-language-model-for-unified","slug":"u-sam-an-audio-language-model-for-unified","title":"U-SAM: An audio language Model for Unified Speech, Audio, and Music Understanding","date":"2025-05-20","arxiv_id":"2505.13880","repositories_listed":1,"syntology":null},{"url":"/paper/mathcoder-vl-bridging-vision-and-code-for","slug":"mathcoder-vl-bridging-vision-and-code-for","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning","date":"2025-05-15","arxiv_id":"2505.10557","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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","sample_list":"/paper/mathcoder-vl-bridging-vision-and-code-for#ran","syntology_url":"https://syntology.ai/paper/2505.10557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10557"}},"official":{"repos":["mathllm/mathcoder"],"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"]}}},{"url":"/paper/msci-addressing-clip-s-inherent-limitations","slug":"msci-addressing-clip-s-inherent-limitations","title":"MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning","date":"2025-05-15","arxiv_id":"2505.10289","repositories_listed":1,"syntology":{"n":28,"n_ran":23,"n_constructed":13,"n_ran_checked":19,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":28,"phrase":"23 ran (of which 13 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/msci-addressing-clip-s-inherent-limitations#ran","syntology_url":"https://syntology.ai/paper/2505.10289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10289"}},"official":{"repos":["ltpwy/msci"],"state":"official (archive's flag): 22 ran","n_ran":22,"n_constructed":13,"n_ran_no_instrument_failure":19,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/anatomical-attention-alignment-representation","slug":"anatomical-attention-alignment-representation","title":"Anatomical Attention Alignment representation for Radiology Report Generation","date":"2025-05-12","arxiv_id":"2505.07689","repositories_listed":1,"syntology":null},{"url":"/paper/hcma-hierarchical-cross-model-alignment-for","slug":"hcma-hierarchical-cross-model-alignment-for","title":"HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation","date":"2025-05-10","arxiv_id":"2505.06512","repositories_listed":1,"syntology":null},{"url":"/paper/task-adapter-task-specific-adaptation-with","slug":"task-adapter-task-specific-adaptation-with","title":"Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition","date":"2025-05-09","arxiv_id":"2505.06002","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-embeddings-for-frozen-vision","slug":"probabilistic-embeddings-for-frozen-vision","title":"Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models","date":"2025-05-08","arxiv_id":"2505.05163","repositories_listed":1,"syntology":null},{"url":"/paper/cav-mae-sync-improving-contrastive-audio","slug":"cav-mae-sync-improving-contrastive-audio","title":"CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment","date":"2025-05-02","arxiv_id":"2505.01237","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cav-mae-sync-improving-contrastive-audio#ran","syntology_url":"https://syntology.ai/paper/2505.01237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.01237"}},"official":{"repos":["edsonroteia/cav-mae-sync"],"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/micarvlmoe-a-modern-gated-cross-aligned","slug":"micarvlmoe-a-modern-gated-cross-aligned","title":"MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation","date":"2025-04-29","arxiv_id":"2504.20343","repositories_listed":1,"syntology":null},{"url":"/paper/cross-attention-for-state-based-model-rwkv-7","slug":"cross-attention-for-state-based-model-rwkv-7","title":"Cross-attention for State-based model RWKV-7","date":"2025-04-19","arxiv_id":"2504.14260","repositories_listed":1,"syntology":null},{"url":"/paper/3d-coca-contrastive-learners-are-3d","slug":"3d-coca-contrastive-learners-are-3d","title":"3D CoCa: Contrastive Learners are 3D Captioners","date":"2025-04-13","arxiv_id":"2504.09518","repositories_listed":1,"syntology":null},{"url":"/paper/gaze-guided-learning-avoiding-shortcut-bias","slug":"gaze-guided-learning-avoiding-shortcut-bias","title":"Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification","date":"2025-04-08","arxiv_id":"2504.05583","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-fusion-and-vision-language-models","slug":"multimodal-fusion-and-vision-language-models","title":"Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision","date":"2025-04-03","arxiv_id":"2504.02477","repositories_listed":1,"syntology":null},{"url":"/paper/cost-contrastive-one-stage-transformer-for","slug":"cost-contrastive-one-stage-transformer-for","title":"COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking","date":"2025-04-02","arxiv_id":"2504.01321","repositories_listed":1,"syntology":null},{"url":"/paper/bipvl-seg-bidirectional-progressive-vision","slug":"bipvl-seg-bidirectional-progressive-vision","title":"BiPVL-Seg: Bidirectional Progressive Vision-Language Fusion with Global-Local Alignment for Medical Image Segmentation","date":"2025-03-30","arxiv_id":"2503.23534","repositories_listed":1,"syntology":null},{"url":"/paper/lposs-label-propagation-over-patches-and","slug":"lposs-label-propagation-over-patches-and","title":"LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation","date":"2025-03-25","arxiv_id":"2503.19777","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/lposs-label-propagation-over-patches-and#ran","syntology_url":"https://syntology.ai/paper/2503.19777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19777"}},"official":{"repos":["vladan-stojnic/lposs"],"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/comp-continual-multimodal-pre-training-for","slug":"comp-continual-multimodal-pre-training-for","title":"CoMP: Continual Multimodal Pre-training for Vision Foundation Models","date":"2025-03-24","arxiv_id":"2503.18931","repositories_listed":1,"syntology":null},{"url":"/paper/enhanced-ood-detection-through-cross-modal","slug":"enhanced-ood-detection-through-cross-modal","title":"Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations","date":"2025-03-24","arxiv_id":"2503.18817","repositories_listed":1,"syntology":null},{"url":"/paper/language-based-image-colorization-a-benchmark","slug":"language-based-image-colorization-a-benchmark","title":"Language-based Image Colorization: A Benchmark and Beyond","date":"2025-03-19","arxiv_id":"2503.14974","repositories_listed":1,"syntology":null},{"url":"/paper/gem-empowering-mllm-for-grounded-ecg","slug":"gem-empowering-mllm-for-grounded-ecg","title":"GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images","date":"2025-03-08","arxiv_id":"2503.06073","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/gem-empowering-mllm-for-grounded-ecg#ran","syntology_url":"https://syntology.ai/paper/2503.06073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06073"}},"official":{"repos":["lanxiang1017/gem"],"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/rcrank-multimodal-ranking-of-root-causes-of","slug":"rcrank-multimodal-ranking-of-root-causes-of","title":"RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems","date":"2025-03-06","arxiv_id":"2503.04252","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-causal-relation-alignment-for-1","slug":"cross-modal-causal-relation-alignment-for-1","title":"Cross-modal Causal Relation Alignment for Video Question Grounding","date":"2025-03-05","arxiv_id":"2503.07635","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":12,"n_ran_checked":13,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":16,"phrase":"13 ran (of which 12 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cross-modal-causal-relation-alignment-for-1#ran","syntology_url":"https://syntology.ai/paper/2503.07635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07635"}},"official":{"repos":["wissingchen/cra-gqa"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":12,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/swimvg-step-wise-multimodal-fusion-and","slug":"swimvg-step-wise-multimodal-fusion-and","title":"SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding","date":"2025-02-24","arxiv_id":"2502.16786","repositories_listed":1,"syntology":null},{"url":"/paper/mv-clam-multi-view-molecular-interpretation","slug":"mv-clam-multi-view-molecular-interpretation","title":"MV-CLAM: Multi-View Molecular Interpretation with Cross-Modal Projection via Language Model","date":"2025-02-23","arxiv_id":"2503.04780","repositories_listed":1,"syntology":null},{"url":"/paper/crossover-3d-scene-cross-modal-alignment","slug":"crossover-3d-scene-cross-modal-alignment","title":"CrossOver: 3D Scene Cross-Modal Alignment","date":"2025-02-20","arxiv_id":"2502.15011","repositories_listed":1,"syntology":null},{"url":"/paper/phantom-subject-consistent-video-generation","slug":"phantom-subject-consistent-video-generation","title":"Phantom: Subject-consistent video generation via cross-modal alignment","date":"2025-02-16","arxiv_id":"2502.11079","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/phantom-subject-consistent-video-generation#ran","syntology_url":"https://syntology.ai/paper/2502.11079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11079"}},"official":null}},{"url":"/paper/ask-in-any-modality-a-comprehensive-survey-on","slug":"ask-in-any-modality-a-comprehensive-survey-on","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","date":"2025-02-12","arxiv_id":"2502.08826","repositories_listed":1,"syntology":null},{"url":"/paper/mme5-improving-multimodal-multilingual","slug":"mme5-improving-multimodal-multilingual","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","date":"2025-02-12","arxiv_id":"2502.08468","repositories_listed":1,"syntology":null},{"url":"/paper/ola-pushing-the-frontiers-of-omni-modal","slug":"ola-pushing-the-frontiers-of-omni-modal","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","date":"2025-02-06","arxiv_id":"2502.04328","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 4 unverified","sample_list":"/paper/ola-pushing-the-frontiers-of-omni-modal#ran","syntology_url":"https://syntology.ai/paper/2502.04328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04328"}},"official":{"repos":["ola-omni/ola"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/clip-behaves-like-a-bag-of-words-model-cross","slug":"clip-behaves-like-a-bag-of-words-model-cross","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","date":"2025-02-05","arxiv_id":"2502.03566","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-behaves-like-a-bag-of-words-model-cross#ran","syntology_url":"https://syntology.ai/paper/2502.03566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03566"}},"official":{"repos":["kdariina/clip-not-bow-unimodally"],"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"]}}},{"url":"/paper/whispa-semantically-and-psychologically","slug":"whispa-semantically-and-psychologically","title":"WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning","date":"2025-01-15","arxiv_id":"2501.16344","repositories_listed":1,"syntology":null},{"url":"/paper/align-kd-distilling-cross-modal-alignment-1","slug":"align-kd-distilling-cross-modal-alignment-1","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-bridge-leveraging-diffusion-model","slug":"diffusion-bridge-leveraging-diffusion-model","title":"Diffusion Bridge: Leveraging Diffusion Model to Reduce the Modality Gap Between Text and Vision for Zero-Shot Image Captioning","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/free-lunch-enhancements-for-multi-modal-crowd","slug":"free-lunch-enhancements-for-multi-modal-crowd","title":"Free Lunch Enhancements for Multi-modal Crowd Counting","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-visual-representation-for-text","slug":"enhancing-visual-representation-for-text","title":"Enhancing Visual Representation for Text-based Person Searching","date":"2024-12-30","arxiv_id":"2412.20646","repositories_listed":1,"syntology":null},{"url":"/paper/asap-advancing-semantic-alignment-promotes","slug":"asap-advancing-semantic-alignment-promotes","title":"ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding","date":"2024-12-17","arxiv_id":"2412.12718","repositories_listed":1,"syntology":null},{"url":"/paper/geal-generalizable-3d-affordance-learning","slug":"geal-generalizable-3d-affordance-learning","title":"GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency","date":"2024-12-12","arxiv_id":"2412.09511","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-music-generation-with-explicit","slug":"multimodal-music-generation-with-explicit","title":"Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation","date":"2024-12-12","arxiv_id":"2412.09428","repositories_listed":1,"syntology":null},{"url":"/paper/align-kd-distilling-cross-modal-alignment","slug":"align-kd-distilling-cross-modal-alignment","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model","date":"2024-12-02","arxiv_id":"2412.01282","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/align-kd-distilling-cross-modal-alignment#ran","syntology_url":"https://syntology.ai/paper/2412.01282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01282"}},"official":{"repos":["fqhank/align-kd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/simcmf-a-simple-cross-modal-fine-tuning","slug":"simcmf-a-simple-cross-modal-fine-tuning","title":"SimCMF: A Simple Cross-modal Fine-tuning Strategy from Vision Foundation Models to Any Imaging Modality","date":"2024-11-27","arxiv_id":"2411.18669","repositories_listed":1,"syntology":null},{"url":"/paper/towards-cross-modal-text-molecule-retrieval","slug":"towards-cross-modal-text-molecule-retrieval","title":"Towards Cross-Modal Text-Molecule Retrieval with Better Modality Alignment","date":"2024-10-31","arxiv_id":"2410.23715","repositories_listed":1,"syntology":null},{"url":"/paper/alignvsr-audio-visual-cross-modal-alignment","slug":"alignvsr-audio-visual-cross-modal-alignment","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition","date":"2024-10-21","arxiv_id":"2410.16438","repositories_listed":1,"syntology":null},{"url":"/paper/less-label-efficient-and-single-stage","slug":"less-label-efficient-and-single-stage","title":"LESS: Label-Efficient and Single-Stage Referring 3D Segmentation","date":"2024-10-17","arxiv_id":"2410.13294","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-semantic-variation-in-text-to","slug":"evaluating-semantic-variation-in-text-to","title":"Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective","date":"2024-10-14","arxiv_id":"2410.10291","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/evaluating-semantic-variation-in-text-to#ran","syntology_url":"https://syntology.ai/paper/2410.10291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10291"}},"official":{"repos":["zhuxiangru/semvarbench"],"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"]}}},{"url":"/paper/deciphering-cross-modal-alignment-in-large","slug":"deciphering-cross-modal-alignment-in-large","title":"Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate","date":"2024-10-09","arxiv_id":"2410.07167","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":2,"n_instrument":10,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"12 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; 10 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deciphering-cross-modal-alignment-in-large#ran","syntology_url":"https://syntology.ai/paper/2410.07167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07167"}},"official":{"repos":["shikiw/modality-integration-rate"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/c-melt-contrastive-enhanced-masked-auto","slug":"c-melt-contrastive-enhanced-masked-auto","title":"Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners","date":"2024-10-03","arxiv_id":"2410.02131","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/c-melt-contrastive-enhanced-masked-auto#ran","syntology_url":"https://syntology.ai/paper/2410.02131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02131"}},"official":{"repos":["manhph2211/d-beta"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/melody-is-all-you-need-for-music-generation","slug":"melody-is-all-you-need-for-music-generation","title":"Melody-Guided Music Generation","date":"2024-09-30","arxiv_id":"2409.20196","repositories_listed":1,"syntology":null},{"url":"/paper/mapper-multimodal-prior-guided-parameter","slug":"mapper-multimodal-prior-guided-parameter","title":"MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension","date":"2024-09-20","arxiv_id":"2409.13609","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"8 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mapper-multimodal-prior-guided-parameter#ran","syntology_url":"https://syntology.ai/paper/2409.13609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13609"}},"official":{"repos":["liuting20/mapper"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cast-cross-modal-alignment-similarity-test","slug":"cast-cross-modal-alignment-similarity-test","title":"CAST: Cross-modal Alignment Similarity Test for Vision Language Models","date":"2024-09-17","arxiv_id":"2409.11007","repositories_listed":1,"syntology":null},{"url":"/paper/kale-an-artwork-image-captioning-system","slug":"kale-an-artwork-image-captioning-system","title":"KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph","date":"2024-09-17","arxiv_id":"2409.10921","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-uncertainty-evidential-deep-learning","slug":"beyond-uncertainty-evidential-deep-learning","title":"Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding","date":"2024-08-29","arxiv_id":"2408.16272","repositories_listed":1,"syntology":null},{"url":"/paper/law-of-vision-representation-in-mllms","slug":"law-of-vision-representation-in-mllms","title":"Law of Vision Representation in MLLMs","date":"2024-08-29","arxiv_id":"2408.16357","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-facial-expression-recognition-of","slug":"a-survey-on-facial-expression-recognition-of","title":"A Survey on Facial Expression Recognition of Static and Dynamic Emotions","date":"2024-08-28","arxiv_id":"2408.15777","repositories_listed":1,"syntology":null},{"url":"/paper/focus-on-focus-focus-oriented-representation","slug":"focus-on-focus-focus-oriented-representation","title":"Focus on Focus: Focus-oriented Representation Learning and Multi-view Cross-modal Alignment for Glioma Grading","date":"2024-08-16","arxiv_id":"2408.08527","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-multi-grained-alignment-for","slug":"advancing-multi-grained-alignment-for","title":"Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training","date":"2024-08-15","arxiv_id":"2408.07919","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/advancing-multi-grained-alignment-for#ran","syntology_url":"https://syntology.ai/paper/2408.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07919"}},"official":{"repos":["ming-er/mga-clap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-00969","slug":"2408-00969","title":"Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach","date":"2024-08-02","arxiv_id":"2408.00969","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2408-00969#ran","syntology_url":"https://syntology.ai/paper/2408.00969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00969"}},"official":{"repos":["wqw123wqw/pftrack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dac-2d-3d-retrieval-with-noisy-labels-via","slug":"dac-2d-3d-retrieval-with-noisy-labels-via","title":"DAC: 2D-3D Retrieval with Noisy Labels via Divide-and-Conquer Alignment and Correction","date":"2024-07-25","arxiv_id":"2407.17779","repositories_listed":1,"syntology":null},{"url":"/paper/craft-cross-modal-aligned-features-improve","slug":"craft-cross-modal-aligned-features-improve","title":"Craft: Cross-modal Aligned Features Improve Robustness of Prompt Tuning","date":"2024-07-22","arxiv_id":"2407.15894","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-sight-and-sound-advanced-sound","slug":"aligning-sight-and-sound-advanced-sound","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment","date":"2024-07-18","arxiv_id":"2407.13676","repositories_listed":1,"syntology":null},{"url":"/paper/distractors-immune-representation-learning","slug":"distractors-immune-representation-learning","title":"Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning","date":"2024-07-16","arxiv_id":"2407.11683","repositories_listed":1,"syntology":null},{"url":"/paper/towards-bridging-the-cross-modal-semantic-gap","slug":"towards-bridging-the-cross-modal-semantic-gap","title":"Towards Bridging the Cross-modal Semantic Gap for Multi-modal Recommendation","date":"2024-07-07","arxiv_id":"2407.05420","repositories_listed":1,"syntology":null},{"url":"/paper/mitigate-the-gap-investigating-approaches-for","slug":"mitigate-the-gap-investigating-approaches-for","title":"Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP","date":"2024-06-25","arxiv_id":"2406.17639","repositories_listed":1,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":9,"n_instrument":7,"n_unverified":6,"n_honours":0,"n_violates":3,"n_no_contract":6,"n_pointer_only":22,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 3 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mitigate-the-gap-investigating-approaches-for#ran","syntology_url":"https://syntology.ai/paper/2406.17639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17639"}},"official":{"repos":["sarahesl/alignclip"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/presto-progressive-pretraining-enhances","slug":"presto-progressive-pretraining-enhances","title":"PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes","date":"2024-06-19","arxiv_id":"2406.13193","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/presto-progressive-pretraining-enhances#ran","syntology_url":"https://syntology.ai/paper/2406.13193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13193"}},"official":{"repos":["idea-xl/presto"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-multimedia-recommendation-via","slug":"boosting-multimedia-recommendation-via","title":"It is Never Too Late to Mend: Separate Learning for Multimedia Recommendation","date":"2024-06-12","arxiv_id":"2406.08270","repositories_listed":1,"syntology":null},{"url":"/paper/flash-vstream-memory-based-real-time","slug":"flash-vstream-memory-based-real-time","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","date":"2024-06-12","arxiv_id":"2406.08085","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-polymer-properties-based-on","slug":"predicting-polymer-properties-based-on","title":"MMPolymer: A Multimodal Multitask Pretraining Framework for Polymer Property Prediction","date":"2024-06-07","arxiv_id":"2406.04727","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"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","sample_list":"/paper/predicting-polymer-properties-based-on#ran","syntology_url":"https://syntology.ai/paper/2406.04727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04727"}},"official":{"repos":["fanmengwang/mmpolymer"],"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"]}}},{"url":"/paper/collaborative-novel-object-discovery-and-box","slug":"collaborative-novel-object-discovery-and-box","title":"Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection","date":"2024-06-02","arxiv_id":"2406.00830","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":4,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/collaborative-novel-object-discovery-and-box#ran","syntology_url":"https://syntology.ai/paper/2406.00830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00830"}},"official":{"repos":["yangcaoai/CoDA_NeurIPS2023"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/deco-decoupling-token-compression-from","slug":"deco-decoupling-token-compression-from","title":"DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models","date":"2024-05-31","arxiv_id":"2405.20985","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 1 unverified","sample_list":"/paper/deco-decoupling-token-compression-from#ran","syntology_url":"https://syntology.ai/paper/2405.20985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20985"}},"official":{"repos":["yaolinli/deco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/seeing-the-image-prioritizing-visual","slug":"seeing-the-image-prioritizing-visual","title":"Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment","date":"2024-05-28","arxiv_id":"2405.17871","repositories_listed":1,"syntology":null},{"url":"/paper/structural-entities-extraction-and-patient","slug":"structural-entities-extraction-and-patient","title":"Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation","date":"2024-05-23","arxiv_id":"2405.14905","repositories_listed":1,"syntology":null},{"url":"/paper/factual-serialization-enhancement-a-key","slug":"factual-serialization-enhancement-a-key","title":"Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation","date":"2024-05-15","arxiv_id":"2405.09586","repositories_listed":1,"syntology":null},{"url":"/paper/listen-then-see-video-alignment-with-speaker","slug":"listen-then-see-video-alignment-with-speaker","title":"Listen Then See: Video Alignment with Speaker Attention","date":"2024-04-21","arxiv_id":"2404.13530","repositories_listed":1,"syntology":null},{"url":"/paper/hivg-hierarchical-multimodal-fine-grained","slug":"hivg-hierarchical-multimodal-fine-grained","title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","date":"2024-04-20","arxiv_id":"2404.13400","repositories_listed":1,"syntology":null},{"url":"/paper/mma-dfer-multimodal-adaptation-of-unimodal","slug":"mma-dfer-multimodal-adaptation-of-unimodal","title":"MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild","date":"2024-04-13","arxiv_id":"2404.09010","repositories_listed":1,"syntology":null},{"url":"/paper/secg-semantic-enhanced-3d-visual-grounding","slug":"secg-semantic-enhanced-3d-visual-grounding","title":"SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention","date":"2024-03-13","arxiv_id":"2403.08182","repositories_listed":1,"syntology":null},{"url":"/paper/a-cross-modal-approach-to-silent-speech-with","slug":"a-cross-modal-approach-to-silent-speech-with","title":"A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition","date":"2024-03-02","arxiv_id":"2403.05583","repositories_listed":1,"syntology":null},{"url":"/paper/mentor-multi-level-self-supervised-learning","slug":"mentor-multi-level-self-supervised-learning","title":"MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation","date":"2024-02-29","arxiv_id":"2402.19407","repositories_listed":1,"syntology":null},{"url":"/paper/the-devil-is-in-the-details-boosting-guided","slug":"the-devil-is-in-the-details-boosting-guided","title":"The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation","date":"2024-01-16","arxiv_id":"2401.08123","repositories_listed":1,"syntology":null},{"url":"/paper/auffusion-leveraging-the-power-of-diffusion","slug":"auffusion-leveraging-the-power-of-diffusion","title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation","date":"2024-01-02","arxiv_id":"2401.01044","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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","sample_list":"/paper/auffusion-leveraging-the-power-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2401.01044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01044"}},"official":{"repos":["happylittlecat2333/Auffusion"],"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"]}}},{"url":"/paper/linguistic-aware-patch-slimming-framework-for","slug":"linguistic-aware-patch-slimming-framework-for","title":"Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/conditional-variational-autoencoder-for-sign","slug":"conditional-variational-autoencoder-for-sign","title":"Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment","date":"2023-12-25","arxiv_id":"2312.15645","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/conditional-variational-autoencoder-for-sign#ran","syntology_url":"https://syntology.ai/paper/2312.15645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15645"}},"official":{"repos":["rzhao-zhsq/cv-slt"],"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/brainvis-exploring-the-bridge-between-brain","slug":"brainvis-exploring-the-bridge-between-brain","title":"BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction","date":"2023-12-22","arxiv_id":"2312.14871","repositories_listed":1,"syntology":null},{"url":"/paper/mask-grounding-for-referring-image","slug":"mask-grounding-for-referring-image","title":"Mask Grounding for Referring Image Segmentation","date":"2023-12-19","arxiv_id":"2312.12198","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":13,"phrase":"10 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; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mask-grounding-for-referring-image#ran","syntology_url":"https://syntology.ai/paper/2312.12198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12198"}},"official":{"repos":["yxchng/mask-grounding"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-balanced-alignment-modal-enhanced","slug":"towards-balanced-alignment-modal-enhanced","title":"Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval","date":"2023-12-19","arxiv_id":"2312.12155","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-balanced-alignment-modal-enhanced#ran","syntology_url":"https://syntology.ai/paper/2312.12155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12155"}},"official":{"repos":["lntzm/mesm"],"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/m2conceptbase-a-fine-grained-aligned-multi","slug":"m2conceptbase-a-fine-grained-aligned-multi","title":"M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base","date":"2023-12-16","arxiv_id":"2312.10417","repositories_listed":1,"syntology":null},{"url":"/paper/vlap-efficient-video-language-alignment-via","slug":"vlap-efficient-video-language-alignment-via","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","date":"2023-12-13","arxiv_id":"2312.08367","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/vlap-efficient-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2312.08367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08367"}},"official":{"repos":["xijun-cs/vila"],"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"]}}}],"syntology_records":32,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":47,"papers_where_code_ran_first_page":"/task/cross-modal-alignment/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/cross-modal-alignment/papers/2","json":"/task/cross-modal-alignment/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/cross-modal-alignment/papers/3","json":"/task/cross-modal-alignment/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/cross-modal-alignment/papers/4","json":"/task/cross-modal-alignment/papers/4.json","rows":42},{"order":"ran","page":1,"of":1,"url":"/task/cross-modal-alignment/papers/ran/1","json":"/task/cross-modal-alignment/papers/ran/1.json","rows":47}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"16430f9e1ad256c121202ad1fa3be54291d37f3f5e42c1c877f06b6dd14f69d2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}