{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AQ3QQLCP5SJDYFCC7UE67SDRX3","short_pith_number":"pith:AQ3QQLCP","schema_version":"1.0","canonical_sha256":"0437082c4fec923c1442fd09efc871bec48c8b73e6ac324db6525fa0bff4d309","source":{"kind":"arxiv","id":"2606.05254","version":1},"attestation_state":"computed","paper":{"title":"Flash-WAM: Modality-Aware Distillation for World Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Arash Akbari, Arman Akbari, Ci Zhang, Geng Yuan, Lin Zhao, Weiwei Chen, Xuan Zhang, Yanzhi Wang, Yixiao Chen","submitted_at":"2026-06-03T15:29:57Z","abstract_excerpt":"World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens of denoising steps, a cost that precludes real-time control. Step distillation has emerged as the natural remedy, but off-the-shelf methods break down in the joint video-action setting because video and action streams use different SNR-shifted noise schedules and reach training with substantially different marginal noise distributions, an asymmetry that single-modality distillation methods cannot accommodate. We intro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.05254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T15:29:57Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"1e07c6a8bf38dcdaf63880c87abfc2514f5b2cae985bdf8043775ec0cf748f7d","abstract_canon_sha256":"f0c3bc8c5bcae5c899c15eb8cd0b199b082bed55ad5d1f20e574d33565d77865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:50.660357Z","signature_b64":"3Ot+Tch96rsWBz2ZCkf/fvUnTllYtTQhSCQKyh4yxqwq/boksvBitCUcm5eaCZYfAPoU3AXdwtKUjM3s41pwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0437082c4fec923c1442fd09efc871bec48c8b73e6ac324db6525fa0bff4d309","last_reissued_at":"2026-06-05T00:13:50.659797Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:50.659797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flash-WAM: Modality-Aware Distillation for World Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Arash Akbari, Arman Akbari, Ci Zhang, Geng Yuan, Lin Zhao, Weiwei Chen, Xuan Zhang, Yanzhi Wang, Yixiao Chen","submitted_at":"2026-06-03T15:29:57Z","abstract_excerpt":"World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens of denoising steps, a cost that precludes real-time control. Step distillation has emerged as the natural remedy, but off-the-shelf methods break down in the joint video-action setting because video and action streams use different SNR-shifted noise schedules and reach training with substantially different marginal noise distributions, an asymmetry that single-modality distillation methods cannot accommodate. We intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05254","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.05254/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.05254","created_at":"2026-06-05T00:13:50.659892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05254v1","created_at":"2026-06-05T00:13:50.659892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05254","created_at":"2026-06-05T00:13:50.659892+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQ3QQLCP5SJD","created_at":"2026-06-05T00:13:50.659892+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQ3QQLCP5SJDYFCC","created_at":"2026-06-05T00:13:50.659892+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQ3QQLCP","created_at":"2026-06-05T00:13:50.659892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3","json":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3.json","graph_json":"https://pith.science/api/pith-number/AQ3QQLCP5SJDYFCC7UE67SDRX3/graph.json","events_json":"https://pith.science/api/pith-number/AQ3QQLCP5SJDYFCC7UE67SDRX3/events.json","paper":"https://pith.science/paper/AQ3QQLCP"},"agent_actions":{"view_html":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3","download_json":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3.json","view_paper":"https://pith.science/paper/AQ3QQLCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05254&json=true","fetch_graph":"https://pith.science/api/pith-number/AQ3QQLCP5SJDYFCC7UE67SDRX3/graph.json","fetch_events":"https://pith.science/api/pith-number/AQ3QQLCP5SJDYFCC7UE67SDRX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3/action/storage_attestation","attest_author":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3/action/author_attestation","sign_citation":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3/action/citation_signature","submit_replication":"https://pith.science/pith/AQ3QQLCP5SJDYFCC7UE67SDRX3/action/replication_record"}},"created_at":"2026-06-05T00:13:50.659892+00:00","updated_at":"2026-06-05T00:13:50.659892+00:00"}