{"paper":{"title":"LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies","arxiv_id":"2606.15768","primary_cat":"cs.RO","submitted_at":"2026-06-14T12:06:58+00:00","version_compiled":"v2"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v2","sentences":[{"i":0,"p":0.82,"id":"s0","own":false,"role":"background","text":"Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change the scene.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.17,"method":0.0,"result":0.0,"background":0.82,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.67,"id":"s1","own":false,"role":"background","text":"World-Action Models (WAMs) address this limitation by conditioning policies on predicted futures, yet existing approaches typically rely on computationally expensive video generation with substantial pixel-level redundancy.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.18,"role_probabilities":{"gap":0.3,"method":0.0,"result":0.0,"background":0.67,"limitation":0.03,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":1.0,"id":"s2","own":true,"role":"contribution","text":"We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.89,"main_claim_p":0.39,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":3,"p":0.74,"id":"s3","own":true,"role":"method","text":"At the core of LaWAM is a latent-action-conditioned Latent World Model (LaWM).","hedge":{"p":1.0,"label":"asserted"},"own_p":0.6,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.74,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.26,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"We obtain LaWM by training a latent action model in the latent space of a pretrained vision foundation model and repurposing its forward decoder to predict future observation features for scene evolution.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":5,"p":0.96,"id":"s5","own":true,"role":"method","text":"LaWAM then conditions action generation on these predicted latent visual subgoals to enable dynamics-aware robot control.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.79,"main_claim_p":0.15,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.96,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.04,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.45,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"LaWAM runs in 187 ms per action-chunk prediction and achieves up to 24x lower wall-clock latency than pixel-space WAMs.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.16,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.97,"text":"LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference.","location":"abstract s6","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":6358,"cost_usd_reported":0.0},"compiled_at":"2026-10-27","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.08,"human_participants":0.06,"controlled_comparison":0.57,"randomized_assignment":0.01,"states_quantitative_result":0.99,"compares_with_prior_results":0.94,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.96,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.96,"simulation_or_computation":0.04}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.97,"text":"We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v2"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":8,"sentences_in_abstract":8},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}