{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generalized-predictive-model-for-autonomous","title":"GenAD: Generalized Predictive Model for Autonomous Driving","arxiv_id":"2403.09630","date":"2024-03-14","proceeding":"CVPR 2024 1","authors":["Jiazhi Yang","Shenyuan Gao","Yihang Qiu","Li Chen","Tianyu Li","Bo Dai","Kashyap Chitta","Penghao Wu","Jia Zeng","Ping Luo","Jun Zhang","Andreas Geiger","Yu Qiao","Hongyang Li"],"abstract":"In this paper, we introduce the first large-scale video prediction model in the autonomous driving discipline. To eliminate the restriction of high-cost data collection and empower the generalization ability of our model, we acquire massive data from the web and pair it with diverse and high-quality text descriptions. The resultant dataset accumulates over 2000 hours of driving videos, spanning areas all over the world with diverse weather conditions and traffic scenarios. Inheriting the merits from recent latent diffusion models, our model, dubbed GenAD, handles the challenging dynamics in driving scenes with novel temporal reasoning blocks. We showcase that it can generalize to various unseen driving datasets in a zero-shot manner, surpassing general or driving-specific video prediction counterparts. Furthermore, GenAD can be adapted into an action-conditioned prediction model or a motion planner, holding great potential for real-world driving applications.","url_abs":"https://arxiv.org/abs/2403.09630v2","url_pdf":"https://arxiv.org/pdf/2403.09630v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"generalized-predictive-model-for-autonomous","repo_url":"https://github.com/opendrivelab/driveagi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"generalized-predictive-model-for-autonomous","repo_url":"https://github.com/opendrivelab/uniad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generalized-predictive-model-for-autonomous","repo_url":"https://github.com/valeoai/VideoActionModel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"video-prediction","task_name":"Video Prediction"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.09630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09630"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendrivelab/uniad","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendrivelab/driveagi","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/valeoai/VideoActionModel","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":6,"ran":6,"repositories":1},"listed":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"687ca21a8d19317f","entry":"count_done_frames","repo":"opendrivelab/driveagi","repo_kind":"official","path":"opendv/utils/frame_extraction.py","file_url":"https://github.com/opendrivelab/driveagi/blob/HEAD/opendv/utils/frame_extraction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"687ca21a8d19317f"}},{"code_sha256_prefix":"01c31d25dffa247a","entry":"get_mini_opendv","repo":"opendrivelab/driveagi","repo_kind":"official","path":"opendv/utils/download.py","file_url":"https://github.com/opendrivelab/driveagi/blob/HEAD/opendv/utils/download.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01c31d25dffa247a"}},{"code_sha256_prefix":"ca3ca4be35ed28cc","entry":"get_video_with_meta","repo":"opendrivelab/driveagi","repo_kind":"official","path":"opendv/utils/download.py","file_url":"https://github.com/opendrivelab/driveagi/blob/HEAD/opendv/utils/download.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ca3ca4be35ed28cc"}},{"code_sha256_prefix":"cadbe4cde8ce2b48","entry":"map_category_to_caption","repo":"opendrivelab/driveagi","repo_kind":"official","path":"opendv/utils/cmd2caption.py","file_url":"https://github.com/opendrivelab/driveagi/blob/HEAD/opendv/utils/cmd2caption.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cadbe4cde8ce2b48"}},{"code_sha256_prefix":"dc1a05c6429223c5","entry":"special_video_setting_log","repo":"opendrivelab/driveagi","repo_kind":"official","path":"opendv/utils/frame_extraction.py","file_url":"https://github.com/opendrivelab/driveagi/blob/HEAD/opendv/utils/frame_extraction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc1a05c6429223c5"}},{"code_sha256_prefix":"bd3e121688d8441b","entry":"youtuber_formatize","repo":"opendrivelab/driveagi","repo_kind":"official","path":"opendv/utils/download.py","file_url":"https://github.com/opendrivelab/driveagi/blob/HEAD/opendv/utils/download.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd3e121688d8441b"}},{"code_sha256_prefix":"2eb7a18c3d3c6298","entry":"mix_datasets","repo":"valeoai/VideoActionModel","repo_kind":"listed","path":"vam/datalib/data_mixing.py","file_url":"https://github.com/valeoai/VideoActionModel/blob/HEAD/vam/datalib/data_mixing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2eb7a18c3d3c6298"}},{"code_sha256_prefix":"7916970abec39bd5","entry":"setup_logger","repo":"valeoai/VideoActionModel","repo_kind":"listed","path":"vam/datalib/create_opendv_tokens.py","file_url":"https://github.com/valeoai/VideoActionModel/blob/HEAD/vam/datalib/create_opendv_tokens.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7916970abec39bd5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}