{"paper":{"title":"AnySlot: Goal-Conditioned Vision-Language-Action Policies for Zero-Shot Slot-Level Placement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AnySlot generates an explicit visual scene marker from language to let goal-conditioned VLA policies handle precise zero-shot slot placement.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ci-Jyun Liang, Jorge Mendez-Mendz, Qinbo Zhang, Qi Su, Rongtao Xu, Sifan Zhou, Zhaofeng Hu","submitted_at":"2026-04-12T03:09:44Z","abstract_excerpt":"Vision-Language-Action (VLA) policies have emerged as a versatile paradigm for generalist robotic manipulation. However, precise object placement under compositional language remains challenging for end-to-end VLA policies. Slot-level placement requires reliable slot grounding and centimeter-level geometric precision. To this end, we propose AnySlot, a framework that reduces compositional complexity by introducing an explicit spatial visual goal between language grounding and control. AnySlot converts language into a visual goal by rendering a spatial marker at the intended slot, then executes"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"AnySlot significantly outperforms flat VLA baselines and previous modular grounding methods in zero-shot slot-level placement.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That generating a reliable scene marker from language instructions is always possible and that the goal-conditioned policy can consistently achieve the required sub-centimeter spatial accuracy without additional fine-tuning or domain-specific data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AnySlot decouples language grounding from low-level control by inserting an explicit visual goal image, yielding better zero-shot performance on precise slot placement tasks than flat VLA policies.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AnySlot generates an explicit visual scene marker from language to let goal-conditioned VLA policies handle precise zero-shot slot placement.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7b2b38b702b6d476e029a33606fc3f8af3ad940e87e0cc0eafb0a05e71722c6c"},"source":{"id":"2604.10432","kind":"arxiv","version":3},"verdict":{"id":"dfca2dba-48cd-4dbf-8ad6-9cd9d84a40f0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:38:01.997535Z","strongest_claim":"AnySlot significantly outperforms flat VLA baselines and previous modular grounding methods in zero-shot slot-level placement.","one_line_summary":"AnySlot decouples language grounding from low-level control by inserting an explicit visual goal image, yielding better zero-shot performance on precise slot placement tasks than flat VLA policies.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That generating a reliable scene marker from language instructions is always possible and that the goal-conditioned policy can consistently achieve the required sub-centimeter spatial accuracy without additional fine-tuning or domain-specific data.","pith_extraction_headline":"AnySlot generates an explicit visual scene marker from language to let goal-conditioned VLA policies handle precise zero-shot slot placement."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10432/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}