{"paper":{"title":"Training-Free Interaction-Aligned Visual Token Pruning for Efficient Embodied Manipulation","arxiv_id":"2603.22991","primary_cat":"cs.CV","submitted_at":"2026-03-24T09:33:05+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":1.0,"id":"s0","own":false,"role":"background","text":"Efficient visual representation is a central image-processing challenge in embodied manipulation, where policies repeatedly process dense visual-token sequences during closed-loop control.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":1.0,"id":"s1","own":false,"role":"background","text":"Existing methods rank or prune tokens using semantic relevance, VLM attention, cross-frame redundancy, or motion in the action space.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.03,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.86,"id":"s2","own":false,"role":"gap","text":"These signals may discard task-relevant regions when instruction-related appearance and observed image motion are not yet spatially aligned.","hedge":{"p":1.0,"label":"hedged_possibility"},"own_p":0.08,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.86,"method":0.0,"result":0.0,"background":0.13,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.87,"id":"s3","own":true,"role":"contribution","text":"We introduce Interaction-Aligned Pruning (IAprune), a training-free method that treats per-frame budget setting and within-budget token selection as two linked decisions.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.0,"method":0.13,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.87,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"Semantic--motion spatial agreement guides the choice between Conservative and Aggressive coverage, and the resulting region size is mapped to a calibrated dynamic budget.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.86,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.07,"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":1.0,"id":"s5","own":true,"role":"method","text":"Continuous semantic and motion responses rank the existing tokens, while geometric residual correction redirects fixed selection slots toward under-represented boundaries without increasing the sequence length.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"Across four embodied manipulation policies, three simulation benchmarks, and a real-robot platform, IAprune provides a favorable accuracy--efficiency trade-off, matching the unpruned policy on LIBERO with a \\(1.54\\times\\) speedup and reaching \\(1.48\\times\\) acceleration on a real robot.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.73,"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":0.82,"id":"s7","own":true,"role":"result","text":"Phase-wise analysis shows that retention gains are largest under tight budgets early in an episode, while fixed-budget analysis confirms that geometry replaces low-priority tokens with boundary and contact-region evidence rather than retaining more tokens.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.12,"quantitative":true,"quantitative_p":0.71,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.82,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.18}},{"i":8,"p":0.57,"id":"s8","own":false,"role":"future_work","text":"Our project website is: \\href{https://chengjt1999.github.io/VLA-IAP.github.io/}{IAprune.com}.","hedge":{"p":0.53,"label":"unclear"},"own_p":0.2,"main_claim_p":0.01,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.03,"result":0.01,"background":0.1,"limitation":0.01,"future_work":0.57,"contribution":0.28,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"Across four embodied manipulation policies, three simulation benchmarks, and a real-robot platform, IAprune provides a favorable accuracy--efficiency trade-off, matching the unpruned policy on LIBERO with a \\(1.54\\times\\) speedup and reaching \\(1.48\\times\\) acceleration on a real robot.","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":7041,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.06,"states_limitation":0.18,"human_participants":0.04,"controlled_comparison":0.93,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.91,"mentions_code_or_data_availability":0.27},"evidential_basis":{"p":0.88,"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":0.88,"simulation_or_computation":0.12}},"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":1.0,"text":"We introduce Interaction-Aligned Pruning (IAprune), a training-free method that treats per-frame budget setting and within-budget token selection as two linked decisions.","location":"abstract s3"}},"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":9,"sentences_in_abstract":9},"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"}}}