{"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/video-occupancy-models","title":"Video Occupancy Models","arxiv_id":"2407.09533","date":"2024-06-25","proceeding":null,"authors":["Manan Tomar","Philippe Hansen-Estruch","Philip Bachman","Alex Lamb","John Langford","Matthew E. Taylor","Sergey Levine"],"abstract":"We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about individual pixels. Unlike prior latent-space world models, VOCs directly predict the discounted distribution of future states in a single step, thus avoiding the need for multistep roll-outs. We show that both properties are beneficial when building predictive models of video for use in downstream control. Code is available at \\href{https://github.com/manantomar/video-occupancy-models}{\\texttt{github.com/manantomar/video-occupancy-models}}.","url_abs":"https://arxiv.org/abs/2407.09533v1","url_pdf":"https://arxiv.org/pdf/2407.09533v1.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":"video-occupancy-models","repo_url":"https://github.com/manantomar/video-occupancy-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.09533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09533"}},"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/manantomar/video-occupancy-models","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_draft_wrong":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"02651e015d7df7d8","entry":"get_parameter_names","repo":"manantomar/video-occupancy-models","repo_kind":"official","path":"utils/network_utils.py","file_url":"https://github.com/manantomar/video-occupancy-models/blob/HEAD/utils/network_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02651e015d7df7d8"}},{"code_sha256_prefix":"52a34e88baa61a95","entry":"get_unique_int","repo":"manantomar/video-occupancy-models","repo_kind":"official","path":"utils/dmc.py","file_url":"https://github.com/manantomar/video-occupancy-models/blob/HEAD/utils/dmc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52a34e88baa61a95"}},{"code_sha256_prefix":"c3d4a06b8d3ec9c6","entry":"k3s1p0","repo":"manantomar/video-occupancy-models","repo_kind":"official","path":"utils/drqv2.py","file_url":"https://github.com/manantomar/video-occupancy-models/blob/HEAD/utils/drqv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3d4a06b8d3ec9c6"}},{"code_sha256_prefix":"66c36536e7655816","entry":"k4s2p0","repo":"manantomar/video-occupancy-models","repo_kind":"official","path":"utils/drqv2.py","file_url":"https://github.com/manantomar/video-occupancy-models/blob/HEAD/utils/drqv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66c36536e7655816"}},{"code_sha256_prefix":"eca6cdf05972a95e","entry":"l2norm","repo":"manantomar/video-occupancy-models","repo_kind":"official","path":"dino/norm_ema_quantizer.py","file_url":"https://github.com/manantomar/video-occupancy-models/blob/HEAD/dino/norm_ema_quantizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eca6cdf05972a95e"}},{"code_sha256_prefix":"ada1d74afbd92171","entry":"sample_vectors","repo":"manantomar/video-occupancy-models","repo_kind":"official","path":"dino/norm_ema_quantizer.py","file_url":"https://github.com/manantomar/video-occupancy-models/blob/HEAD/dino/norm_ema_quantizer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ada1d74afbd92171"}},{"code_sha256_prefix":"4e63eaa872a45c44","entry":"kmeans","repo":"manantomar/video-occupancy-models","repo_kind":"official","path":"dino/norm_ema_quantizer.py","file_url":"https://github.com/manantomar/video-occupancy-models/blob/HEAD/dino/norm_ema_quantizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4e63eaa872a45c44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}