{"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/playslot-learning-inverse-latent-dynamics-for","title":"PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning","arxiv_id":"2502.07600","date":"2025-02-11","proceeding":null,"authors":["Angel Villar-Corrales","Sven Behnke"],"abstract":"Predicting future scene representations is a crucial task for enabling robots to understand and interact with the environment. However, most existing methods rely on videos and simulations with precise action annotations, limiting their ability to leverage the large amount of available unlabeled video data. To address this challenge, we propose PlaySlot, an object-centric video prediction model that infers object representations and latent actions from unlabeled video sequences. It then uses these representations to forecast future object states and video frames. PlaySlot allows the generation of multiple possible futures conditioned on latent actions, which can be inferred from video dynamics, provided by a user, or generated by a learned action policy, thus enabling versatile and interpretable world modeling. Our results show that PlaySlot outperforms both stochastic and object-centric baselines for video prediction across different environments. Furthermore, we show that our inferred latent actions can be used to learn robot behaviors sample-efficiently from unlabeled video demonstrations. Videos and code are available on https://play-slot.github.io/PlaySlot/.","url_abs":"https://arxiv.org/abs/2502.07600v2","url_pdf":"https://arxiv.org/pdf/2502.07600v2.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":"playslot-learning-inverse-latent-dynamics-for","repo_url":"https://github.com/angelvillar96/PlaySlot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.07600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07600"}},"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/angelvillar96/PlaySlot","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"listed":{"samples":7,"ran":2,"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":"5ca24b920606f0a2","entry":"EmaCodebookMeter","repo":"angelvillar96/PlaySlot","repo_kind":"listed","path":"src/models/Predictors/LatentAction.py","file_url":"https://github.com/angelvillar96/PlaySlot/blob/HEAD/src/models/Predictors/LatentAction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ca24b920606f0a2"}},{"code_sha256_prefix":"ba9a1df12fde93dc","entry":"L2_efficient","repo":"angelvillar96/PlaySlot","repo_kind":"listed","path":"src/models/Predictors/LatentAction.py","file_url":"https://github.com/angelvillar96/PlaySlot/blob/HEAD/src/models/Predictors/LatentAction.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba9a1df12fde93dc"}},{"code_sha256_prefix":"adbfde23ea97543a","entry":"BaseSlotLatentAction","repo":"angelvillar96/PlaySlot","repo_kind":"listed","path":"src/models/Predictors/LatentAction.py","file_url":"https://github.com/angelvillar96/PlaySlot/blob/HEAD/src/models/Predictors/LatentAction.py","link_basis":"first_harvest_node","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":"adbfde23ea97543a"}},{"code_sha256_prefix":"0e0822d3270030b0","entry":"EmaVectorQuantizer","repo":"angelvillar96/PlaySlot","repo_kind":"listed","path":"src/models/Predictors/LatentAction.py","file_url":"https://github.com/angelvillar96/PlaySlot/blob/HEAD/src/models/Predictors/LatentAction.py","link_basis":"first_harvest_node","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":"0e0822d3270030b0"}},{"code_sha256_prefix":"7fecc1a82e25d865","entry":"VQSimpleMLPSlotLatentAction","repo":"angelvillar96/PlaySlot","repo_kind":"listed","path":"src/models/Predictors/LatentAction.py","file_url":"https://github.com/angelvillar96/PlaySlot/blob/HEAD/src/models/Predictors/LatentAction.py","link_basis":"first_harvest_node","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":"7fecc1a82e25d865"}},{"code_sha256_prefix":"32667968d7719805","entry":"VectorQuantizer","repo":"angelvillar96/PlaySlot","repo_kind":"listed","path":"src/models/Predictors/LatentAction.py","file_url":"https://github.com/angelvillar96/PlaySlot/blob/HEAD/src/models/Predictors/LatentAction.py","link_basis":"first_harvest_node","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":"32667968d7719805"}},{"code_sha256_prefix":"3304f3b6edd62667","entry":"print_","repo":"angelvillar96/PlaySlot","repo_kind":"listed","path":"src/models/Predictors/LatentAction.py","file_url":"https://github.com/angelvillar96/PlaySlot/blob/HEAD/src/models/Predictors/LatentAction.py","link_basis":"first_harvest_node","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":"3304f3b6edd62667"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}