{"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/gesture-generation","name":"Gesture Generation","slug":"gesture-generation","description_markdown":"Generation of gestures, as a sequence of 3d poses","categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":107,"papers_with_code":46,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":7,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/gesture-generation-on-beat2","slug":"gesture-generation-on-beat2","dataset":"BEAT2","dataset_url":"/dataset/beat2","rows_in_archive":14,"metrics":["FGD"],"first_row_in_archive_order":{"model":"Intentional Gesture","paper_title":"Intentional Gesture: Deliver Your Intentions with Gestures for Speech","paper_url":"/paper/intentional-gesture-deliver-your-intentions","paper_date":"2025-05-21","arxiv_id":"2505.15197","code_links":[{"title":"andypinxinliu/Intentional-Gesture","url":"https://github.com/andypinxinliu/Intentional-Gesture"}],"syntology":null}},{"leaderboard":"/sota/gesture-generation-on-ted-gesture-dataset","slug":"gesture-generation-on-ted-gesture-dataset","dataset":"TED Gesture Dataset","dataset_url":"/dataset/ted-gesture-dataset","rows_in_archive":6,"metrics":["FGD"],"first_row_in_archive_order":{"model":"AQ-GT","paper_title":"AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis","paper_url":"/paper/aq-gt-a-temporally-aligned-and-quantized-gru","paper_date":"2023-05-02","arxiv_id":"2305.01241","code_links":[{"title":"hvoss-techfak/AQGT","url":"https://github.com/hvoss-techfak/AQGT"}],"syntology":null}},{"leaderboard":"/sota/gesture-generation-on-beat","slug":"gesture-generation-on-beat","dataset":"BEAT","dataset_url":"/dataset/beat","rows_in_archive":5,"metrics":["FID"],"first_row_in_archive_order":{"model":"CaMN","paper_title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","paper_url":"/paper/beat-a-large-scale-semantic-and-emotional","paper_date":"2022-03-10","arxiv_id":"2203.05297","code_links":[{"title":"PantoMatrix/PantoMatrix","url":"https://github.com/PantoMatrix/PantoMatrix"}],"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/beat-a-large-scale-semantic-and-emotional#ran","syntology_url":"https://syntology.ai/paper/2203.05297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05297"}},"official":{"repos":["PantoMatrix/PantoMatrix"],"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"]}}}},{"leaderboard":"/sota/gesture-generation-on-dvs128-gesture","slug":"gesture-generation-on-dvs128-gesture","dataset":"DVS128 Gesture","dataset_url":"/dataset/dvs128-gesture-dataset","rows_in_archive":1,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"ECSNet","paper_title":"Ecsnet: Spatio-temporal feature learning for event camera","paper_url":"/paper/ecsnet-spatio-temporal-feature-learning-for","paper_date":"2022-08-29","arxiv_id":null,"code_links":[{"title":"happychenpipi/ECSNet","url":"https://github.com/happychenpipi/ECSNet"}],"syntology":null}}],"datasets":[{"url":"/dataset/dvs128-gesture-dataset","name":"DVS128 Gesture","full_name":"","num_papers_in_archive":103},{"url":"/dataset/beat","name":"BEAT","full_name":"Body-Expression-Audio-Text","num_papers_in_archive":56},{"url":"/dataset/beat2","name":"BEAT2","full_name":"BEAT-SMPLX-FLAME","num_papers_in_archive":23},{"url":"/dataset/ted-gesture-dataset","name":"TED Gesture Dataset","full_name":"","num_papers_in_archive":12},{"url":"/dataset/talking-with-hands-16-2m","name":"Talking With Hands 16.2M","full_name":"Talking With Hands 16.2M","num_papers_in_archive":5},{"url":"/dataset/bige","name":"BiGe","full_name":"Bielefeld Gesture Corpus","num_papers_in_archive":2},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/3d-shape-generation","name":"3D Shape Generation"}],"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":2,"rows_per_page":100,"shown":100,"of":107,"of_with_code":46,"tagged_in_all":107,"counts":{"archive_papers_tagged":107,"with_a_code_link":46,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":107,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/robosuite-a-modular-simulation-framework-and","slug":"robosuite-a-modular-simulation-framework-and","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","date":"2020-09-25","arxiv_id":"2009.12293","repositories_listed":7,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robosuite-a-modular-simulation-framework-and#ran","syntology_url":"https://syntology.ai/paper/2009.12293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12293"}},"official":null}},{"url":"/paper/generating-holistic-3d-human-motion-from","slug":"generating-holistic-3d-human-motion-from","title":"Generating Holistic 3D Human Motion from Speech","date":"2022-12-08","arxiv_id":"2212.04420","repositories_listed":3,"syntology":null},{"url":"/paper/the-genea-challenge-2022-a-large-evaluation","slug":"the-genea-challenge-2022-a-large-evaluation","title":"The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation","date":"2022-08-22","arxiv_id":"2208.10441","repositories_listed":3,"syntology":null},{"url":"/paper/the-genea-challenge-2023-a-large-scale","slug":"the-genea-challenge-2023-a-large-scale","title":"The GENEA Challenge 2023: A large scale evaluation of gesture generation models in monadic and dyadic settings","date":"2023-08-24","arxiv_id":"2308.12646","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-genea-challenge-2023-a-large-scale#ran","syntology_url":"https://syntology.ai/paper/2308.12646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12646"}},"official":{"repos":["teonikolov/genea_visualizer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/speech-gesture-generation-from-the-trimodal","slug":"speech-gesture-generation-from-the-trimodal","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","date":"2020-09-04","arxiv_id":"2009.02119","repositories_listed":2,"syntology":null},{"url":"/paper/learning-individual-styles-of-conversational-1","slug":"learning-individual-styles-of-conversational-1","title":"Learning Individual Styles of Conversational Gesture","date":"2019-06-10","arxiv_id":"1906.04160","repositories_listed":2,"syntology":null},{"url":"/paper/deepgesture-a-conversational-gesture","slug":"deepgesture-a-conversational-gesture","title":"DeepGesture: A conversational gesture synthesis system based on emotions and semantics","date":"2025-07-03","arxiv_id":"2507.03147","repositories_listed":1,"syntology":null},{"url":"/paper/intentional-gesture-deliver-your-intentions","slug":"intentional-gesture-deliver-your-intentions","title":"Intentional Gesture: Deliver Your Intentions with Gestures for Speech","date":"2025-05-21","arxiv_id":"2505.15197","repositories_listed":1,"syntology":null},{"url":"/paper/varges-improving-variation-in-co-speech-3d","slug":"varges-improving-variation-in-co-speech-3d","title":"VarGes: Improving Variation in Co-Speech 3D Gesture Generation via StyleCLIPS","date":"2025-02-15","arxiv_id":"2502.10729","repositories_listed":1,"syntology":null},{"url":"/paper/gesturelsm-latent-shortcut-based-co-speech","slug":"gesturelsm-latent-shortcut-based-co-speech","title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","date":"2025-01-31","arxiv_id":"2501.18898","repositories_listed":1,"syntology":null},{"url":"/paper/retrieving-semantics-from-the-deep-an-rag","slug":"retrieving-semantics-from-the-deep-an-rag","title":"Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis","date":"2024-12-09","arxiv_id":"2412.06786","repositories_listed":1,"syntology":null},{"url":"/paper/enabling-synergistic-full-body-control-in-1","slug":"enabling-synergistic-full-body-control-in-1","title":"Enabling Synergistic Full-Body Control in Prompt-Based Co-Speech Motion Generation","date":"2024-10-01","arxiv_id":"2410.00464","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21136","slug":"2407-21136","title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls","date":"2024-07-30","arxiv_id":"2407.21136","repositories_listed":1,"syntology":null},{"url":"/paper/amuse-emotional-speech-driven-3d-body","slug":"amuse-emotional-speech-driven-3d-body","title":"AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion","date":"2024-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/convofusion-multi-modal-conversational","slug":"convofusion-multi-modal-conversational","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","date":"2024-03-26","arxiv_id":"2403.17936","repositories_listed":1,"syntology":null},{"url":"/paper/mambatalk-efficient-holistic-gesture","slug":"mambatalk-efficient-holistic-gesture","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","date":"2024-03-14","arxiv_id":"2403.09471","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/mambatalk-efficient-holistic-gesture#ran","syntology_url":"https://syntology.ai/paper/2403.09471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09471"}},"official":{"repos":["kkakkkka/MambaTalk"],"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/emage-towards-unified-holistic-co-speech","slug":"emage-towards-unified-holistic-co-speech","title":"EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling","date":"2023-12-31","arxiv_id":"2401.00374","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/emage-towards-unified-holistic-co-speech#ran","syntology_url":"https://syntology.ai/paper/2401.00374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00374"}},"official":{"repos":["PantoMatrix/PantoMatrix"],"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/emotional-speech-driven-3d-body-animation-via","slug":"emotional-speech-driven-3d-body-animation-via","title":"Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion","date":"2023-12-07","arxiv_id":"2312.04466","repositories_listed":1,"syntology":null},{"url":"/paper/livelyspeaker-towards-semantic-aware-co","slug":"livelyspeaker-towards-semantic-aware-co","title":"LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation","date":"2023-09-17","arxiv_id":"2309.09294","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/livelyspeaker-towards-semantic-aware-co#ran","syntology_url":"https://syntology.ai/paper/2309.09294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09294"}},"official":{"repos":["zyhbili/livelyspeaker"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unifiedgesture-a-unified-gesture-synthesis","slug":"unifiedgesture-a-unified-gesture-synthesis","title":"UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons","date":"2023-09-13","arxiv_id":"2309.07051","repositories_listed":1,"syntology":null},{"url":"/paper/synthogestures-a-novel-framework-for","slug":"synthogestures-a-novel-framework-for","title":"SynthoGestures: A Novel Framework for Synthetic Dynamic Hand Gesture Generation for Driving Scenarios","date":"2023-09-08","arxiv_id":"2309.04421","repositories_listed":1,"syntology":null},{"url":"/paper/c2g2-controllable-co-speech-gesture","slug":"c2g2-controllable-co-speech-gesture","title":"C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model","date":"2023-08-29","arxiv_id":"2308.15016","repositories_listed":1,"syntology":null},{"url":"/paper/emotiongesture-audio-driven-diverse-emotional","slug":"emotiongesture-audio-driven-diverse-emotional","title":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","date":"2023-05-30","arxiv_id":"2305.18891","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":3,"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/emotiongesture-audio-driven-diverse-emotional#ran","syntology_url":"https://syntology.ai/paper/2305.18891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18891"}},"official":{"repos":["xingqunqi-lab/emotiongestures"],"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/qpgesture-quantization-based-and-phase-guided-1","slug":"qpgesture-quantization-based-and-phase-guided-1","title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","date":"2023-05-18","arxiv_id":"2305.11094","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/qpgesture-quantization-based-and-phase-guided-1#ran","syntology_url":"https://syntology.ai/paper/2305.11094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11094"}},"official":{"repos":["youngseng/qpgesture"],"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/aq-gt-a-temporally-aligned-and-quantized-gru","slug":"aq-gt-a-temporally-aligned-and-quantized-gru","title":"AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture Synthesis","date":"2023-05-02","arxiv_id":"2305.01241","repositories_listed":1,"syntology":null},{"url":"/paper/gesturediffuclip-gesture-diffusion-model-with","slug":"gesturediffuclip-gesture-diffusion-model-with","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","date":"2023-03-26","arxiv_id":"2303.14613","repositories_listed":1,"syntology":null},{"url":"/paper/taming-diffusion-models-for-audio-driven-co","slug":"taming-diffusion-models-for-audio-driven-co","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","date":"2023-03-16","arxiv_id":"2303.09119","repositories_listed":1,"syntology":null},{"url":"/paper/listen-denoise-action-audio-driven-motion","slug":"listen-denoise-action-audio-driven-motion","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","date":"2022-11-17","arxiv_id":"2211.09707","repositories_listed":1,"syntology":null},{"url":"/paper/rhythmic-gesticulator-rhythm-aware-co-speech","slug":"rhythmic-gesticulator-rhythm-aware-co-speech","title":"Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings","date":"2022-10-04","arxiv_id":"2210.01448","repositories_listed":1,"syntology":null},{"url":"/paper/zeroeggs-zero-shot-example-based-gesture","slug":"zeroeggs-zero-shot-example-based-gesture","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","date":"2022-09-15","arxiv_id":"2209.07556","repositories_listed":1,"syntology":null},{"url":"/paper/ecsnet-spatio-temporal-feature-learning-for","slug":"ecsnet-spatio-temporal-feature-learning-for","title":"Ecsnet: Spatio-temporal feature learning for event camera","date":"2022-08-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-reprgesture-entry-to-the-genea-challenge","slug":"the-reprgesture-entry-to-the-genea-challenge","title":"The ReprGesture entry to the GENEA Challenge 2022","date":"2022-08-25","arxiv_id":"2208.12133","repositories_listed":1,"syntology":null},{"url":"/paper/learning-hierarchical-cross-modal-association","slug":"learning-hierarchical-cross-modal-association","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","date":"2022-03-24","arxiv_id":"2203.13161","repositories_listed":1,"syntology":null},{"url":"/paper/beat-a-large-scale-semantic-and-emotional","slug":"beat-a-large-scale-semantic-and-emotional","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","date":"2022-03-10","arxiv_id":"2203.05297","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/beat-a-large-scale-semantic-and-emotional#ran","syntology_url":"https://syntology.ai/paper/2203.05297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05297"}},"official":{"repos":["PantoMatrix/PantoMatrix"],"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/seeg-semantic-energized-co-speech-gesture","slug":"seeg-semantic-energized-co-speech-gesture","title":"SEEG: Semantic Energized Co-Speech Gesture Generation","date":"2022-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gesture2vec-clustering-gestures-using","slug":"gesture2vec-clustering-gestures-using","title":"Gesture2Vec: Clustering Gestures using Representation Learning Methods for Co-speech Gesture Generation","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/speech-drives-templates-co-speech-gesture","slug":"speech-drives-templates-co-speech-gesture","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","date":"2021-08-18","arxiv_id":"2108.08020","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/speech-drives-templates-co-speech-gesture#ran","syntology_url":"https://syntology.ai/paper/2108.08020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08020"}},"official":{"repos":["shenhanqian/speechdrivestemplates"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/speech2affectivegestures-synthesizing-co","slug":"speech2affectivegestures-synthesizing-co","title":"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning","date":"2021-07-31","arxiv_id":"2108.00262","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-human-like-gesture-synthesis","slug":"probabilistic-human-like-gesture-synthesis","title":"Probabilistic Human-like Gesture Synthesis from Speech using GRU-based WGAN","date":"2021-07-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-integrating-gesture","slug":"a-framework-for-integrating-gesture","title":"A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents","date":"2021-02-24","arxiv_id":"2102.12302","repositories_listed":1,"syntology":null},{"url":"/paper/deepnag-deep-non-adversarial-gesture","slug":"deepnag-deep-non-adversarial-gesture","title":"DeepNAG: Deep Non-Adversarial Gesture Generation","date":"2020-11-18","arxiv_id":"2011.09149","repositories_listed":1,"syntology":null},{"url":"/paper/no-gestures-left-behind-learning","slug":"no-gestures-left-behind-learning","title":"No Gestures Left Behind: Learning Relationships between Spoken Language and Freeform Gestures","date":"2020-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/style-transfer-for-co-speech-gesture","slug":"style-transfer-for-co-speech-gesture","title":"Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach","date":"2020-07-24","arxiv_id":"2007.12553","repositories_listed":1,"syntology":null},{"url":"/paper/moving-fast-and-slow-analysis-of","slug":"moving-fast-and-slow-analysis-of","title":"Moving fast and slow: Analysis of representations and post-processing in speech-driven automatic gesture generation","date":"2020-07-16","arxiv_id":"2007.09170","repositories_listed":1,"syntology":null},{"url":"/paper/style-controllable-speech-driven-gesture","slug":"style-controllable-speech-driven-gesture","title":"Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows","date":"2020-05-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gesticulator-a-framework-for-semantically","slug":"gesticulator-a-framework-for-semantically","title":"Gesticulator: A framework for semantically-aware speech-driven gesture generation","date":"2020-01-25","arxiv_id":"2001.09326","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/gesticulator-a-framework-for-semantically#ran","syntology_url":"https://syntology.ai/paper/2001.09326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.09326"}},"official":{"repos":["Svito-zar/gesticulator"],"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":null,"slug":"m3g-multi-granular-gesture-generator-for","title":"M3G: Multi-Granular Gesture Generator for Audio-Driven Full-Body Human Motion Synthesis","date":"2025-05-13","arxiv_id":"2505.08293","repositories_listed":0,"syntology":null},{"url":null,"slug":"inter-diffusion-generation-model-of-speakers","title":"Inter-Diffusion Generation Model of Speakers and Listeners for Effective Communication","date":"2025-05-08","arxiv_id":"2505.04996","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-3-gesture-towards-coherent-concurrent-co","title":"Co$^{3}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion","date":"2025-05-03","arxiv_id":"2505.01746","repositories_listed":0,"syntology":null},{"url":"/paper/echomask-speech-queried-attention-based-mask","slug":"echomask-speech-queried-attention-based-mask","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","date":"2025-04-12","arxiv_id":"2504.09209","repositories_listed":0,"syntology":null},{"url":null,"slug":"easygennet-an-efficient-framework-for-audio","title":"EasyGenNet: An Efficient Framework for Audio-Driven Gesture Video Generation Based on Diffusion Model","date":"2025-04-11","arxiv_id":"2504.08344","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-driven-gesture-generation-via-deviation","title":"Audio-driven Gesture Generation via Deviation Feature in the Latent Space","date":"2025-03-27","arxiv_id":"2503.21616","repositories_listed":0,"syntology":null},{"url":null,"slug":"sarges-semantically-aligned-reliable-gesture","title":"SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain","date":"2025-03-26","arxiv_id":"2503.20202","repositories_listed":0,"syntology":null},{"url":null,"slug":"didiffges-decoupled-semi-implicit-diffusion","title":"DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech","date":"2025-03-21","arxiv_id":"2503.17059","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-virtual-human","title":"Large Language Models for Virtual Human Gesture Selection","date":"2025-03-18","arxiv_id":"2503.14408","repositories_listed":0,"syntology":null},{"url":null,"slug":"mag-multi-modal-aligned-autoregressive-co","title":"MAG: Multi-Modal Aligned Autoregressive Co-Speech Gesture Generation without Vector Quantization","date":"2025-03-18","arxiv_id":"2503.14040","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-generation-of-co-speech-gestures","title":"Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion","date":"2025-03-13","arxiv_id":"2503.10488","repositories_listed":0,"syntology":null},{"url":null,"slug":"hop-heterogeneous-topology-based-multimodal","title":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation","date":"2025-03-03","arxiv_id":"2503.01175","repositories_listed":0,"syntology":null},{"url":"/paper/contextual-gesture-co-speech-gesture-video","slug":"contextual-gesture-co-speech-gesture-video","title":"Contextual Gesture: Co-Speech Gesture Video Generation through Context-aware Gesture Representation","date":"2025-02-11","arxiv_id":"2502.07239","repositories_listed":0,"syntology":null},{"url":null,"slug":"emo2-end-effector-guided-audio-driven-avatar","title":"EMO2: End-Effector Guided Audio-Driven Avatar Video Generation","date":"2025-01-18","arxiv_id":"2501.10687","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-speech-gesture-video-generation-with","title":"Co-Speech Gesture Video Generation with Implicit Motion-Audio Entanglement","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/semtalk-holistic-co-speech-motion-generation","slug":"semtalk-holistic-co-speech-motion-generation","title":"SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis","date":"2024-12-21","arxiv_id":"2412.16563","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-language-of-motion-unifying-verbal-and","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","date":"2024-12-13","arxiv_id":"2412.10523","repositories_listed":0,"syntology":null},{"url":null,"slug":"dim-gestor-co-speech-gesture-generation-with","title":"DiM-Gestor: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2","date":"2024-11-23","arxiv_id":"2411.16729","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-gan-for-enhancing-diffusion","title":"Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audios","date":"2024-10-27","arxiv_id":"2410.20359","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-body-language-models","title":"Large Body Language Models","date":"2024-10-21","arxiv_id":"2410.16533","repositories_listed":0,"syntology":null},{"url":null,"slug":"emphasizing-semantic-consistency-of-salient","title":"Emphasizing Semantic Consistency of Salient Posture for Speech-Driven Gesture Generation","date":"2024-10-17","arxiv_id":"2410.13786","repositories_listed":0,"syntology":null},{"url":null,"slug":"expgest-expressive-speaker-generation-using","title":"ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance","date":"2024-10-12","arxiv_id":"2410.09396","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-genea-leaderboard-an-extended","title":"Towards a GENEA Leaderboard -- an Extended, Living Benchmark for Evaluating and Advancing Conversational Motion Synthesis","date":"2024-10-08","arxiv_id":"2410.06327","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-gesticulator-leveraging-large-language","title":"LLM Gesticulator: Leveraging Large Language Models for Scalable and Controllable Co-Speech Gesture Synthesis","date":"2024-10-06","arxiv_id":"2410.10851","repositories_listed":0,"syntology":null},{"url":null,"slug":"mm-conv-a-multi-modal-conversational-dataset","title":"MM-Conv: A Multi-modal Conversational Dataset for Virtual Humans","date":"2024-09-30","arxiv_id":"2410.00253","repositories_listed":0,"syntology":null},{"url":null,"slug":"2d-or-not-2d-how-does-the-dimensionality-of","title":"2D or not 2D: How Does the Dimensionality of Gesture Representation Affect 3D Co-Speech Gesture Generation?","date":"2024-09-16","arxiv_id":"2409.10357","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-spatial-awareness-in-data","title":"Incorporating Spatial Awareness in Data-Driven Gesture Generation for Virtual Agents","date":"2024-08-07","arxiv_id":"2408.04127","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-03312","title":"MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation","date":"2024-08-06","arxiv_id":"2408.03312","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00370","title":"DiM-Gesture: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 framework","date":"2024-08-01","arxiv_id":"2408.00370","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-the-impact-of-2d-gesture","title":"Investigating the impact of 2D gesture representation on co-speech gesture generation","date":"2024-06-21","arxiv_id":"2406.15111","repositories_listed":0,"syntology":null},{"url":null,"slug":"cocogesture-toward-coherent-co-speech-3d","title":"CoCoGesture: Toward Coherent Co-speech 3D Gesture Generation in the Wild","date":"2024-05-27","arxiv_id":"2405.16874","repositories_listed":0,"syntology":null},{"url":null,"slug":"llanimation-llama-driven-gesture-animation","title":"LLAniMAtion: LLAMA Driven Gesture Animation","date":"2024-05-13","arxiv_id":"2405.08042","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-to-non-barrier-communication-gloss","title":"Bridge to Non-Barrier Communication: Gloss-Prompted Fine-grained Cued Speech Gesture Generation with Diffusion Model","date":"2024-04-30","arxiv_id":"2404.19277","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-driven-personalized-gesture-synthetics","title":"Speech-driven Personalized Gesture Synthetics: Harnessing Automatic Fuzzy Feature Inference","date":"2024-03-16","arxiv_id":"2403.10805","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffsheg-a-diffusion-based-approach-for-real","title":"DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation","date":"2024-01-09","arxiv_id":"2401.04747","repositories_listed":0,"syntology":null},{"url":null,"slug":"freetalker-controllable-speech-and-text","title":"Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness","date":"2024-01-07","arxiv_id":"2401.03476","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-generation-multi-modal-gesture","title":"Chain of Generation: Multi-Modal Gesture Synthesis via Cascaded Conditional Control","date":"2023-12-26","arxiv_id":"2312.15900","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-emotion-transition-learning","title":"Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation","date":"2023-11-29","arxiv_id":"2311.17532","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-in-textual-analysis-for","title":"Large language models in textual analysis for gesture selection","date":"2023-10-04","arxiv_id":"2310.13705","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-gesture-gan-gesture-generation-for","title":"Speech-Gesture GAN: Gesture Generation for Robots and Embodied Agents","date":"2023-09-17","arxiv_id":"2309.09346","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-based-co-speech-gesture-generation","title":"Diffusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation","date":"2023-09-11","arxiv_id":"2309.05455","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-is-all-in-one-speech-driven-gesture","title":"Audio is all in one: speech-driven gesture synthetics using WavLM pre-trained model","date":"2023-08-11","arxiv_id":"2308.05995","repositories_listed":0,"syntology":null},{"url":null,"slug":"emog-synthesizing-emotive-co-speech-3d","title":"EMoG: Synthesizing Emotive Co-speech 3D Gesture with Diffusion Model","date":"2023-06-20","arxiv_id":"2306.11496","repositories_listed":0,"syntology":null},{"url":null,"slug":"mpe4g-multimodal-pretrained-encoder-for-co","title":"MPE4G: Multimodal Pretrained Encoder for Co-Speech Gesture Generation","date":"2023-05-25","arxiv_id":"2305.15740","repositories_listed":0,"syntology":null},{"url":null,"slug":"gesgpt-speech-gesture-synthesis-with-text","title":"GesGPT: Speech Gesture Synthesis With Text Parsing from ChatGPT","date":"2023-03-23","arxiv_id":"2303.13013","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-gesture-generation-in-a-large","title":"Evaluating gesture generation in a large-scale open challenge: The GENEA Challenge 2022","date":"2023-03-15","arxiv_id":"2303.08737","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio2gestures-generating-diverse-gestures-1","title":"Audio2Gestures: Generating Diverse Gestures from Audio","date":"2023-01-17","arxiv_id":"2301.06690","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-review-of-data-driven-co","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","date":"2023-01-13","arxiv_id":"2301.05339","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-for-personalized-co-speech","title":"Continual Learning for Personalized Co-speech Gesture Generation","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-style-transfer-for-gesture","title":"Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding","date":"2022-08-03","arxiv_id":"2208.01917","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-adaptation-for-personalized-co","title":"Low-Resource Adaptation for Personalized Co-Speech Gesture Generation","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/audio2gestures-generating-diverse-gestures","slug":"audio2gestures-generating-diverse-gestures","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","date":"2021-08-15","arxiv_id":"2108.06720","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-analysis-of-the-predictability-of","title":"Multimodal analysis of the predictability of hand-gesture properties","date":"2021-08-12","arxiv_id":"2108.05762","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech2properties2gestures-gesture-property","title":"Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech","date":"2021-06-28","arxiv_id":"2106.14736","repositories_listed":0,"syntology":null}],"syntology_records":10,"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":10,"papers_where_code_ran_first_page":"/task/gesture-generation/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":2,"url":"/task/gesture-generation/papers/2","json":"/task/gesture-generation/papers/2.json","rows":7},{"order":"ran","page":1,"of":1,"url":"/task/gesture-generation/papers/ran/1","json":"/task/gesture-generation/papers/ran/1.json","rows":10}],"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":"bd3d47f1026057b1d056ae42f23a7b891d24a7dec72187f58e1c510c7971dea1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}