{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RY5QKCNSBOQJCSBSIZHJBOQQZ4","short_pith_number":"pith:RY5QKCNS","schema_version":"1.0","canonical_sha256":"8e3b0509b20ba0914832464e90ba10cf145ca3d6f5e4b59d9acc2aa4703dc86b","source":{"kind":"arxiv","id":"2606.05981","version":1},"attestation_state":"computed","paper":{"title":"Video-Rate Streaming Stylization on a Vision-Aware MLLM-Conditioned Edit Diffusion: Asymmetric Batched Inference on a Distilled UNet + MLLM Text Encoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Yoshiyuki Ootani","submitted_at":"2026-06-04T10:24:06Z","abstract_excerpt":"Aggressive distillation of the diffusion U-Net inverts the per-frame bottleneck of real-time text-to-image pipelines: once the denoiser is a 4-step or 1-step distilled student, the text encoder becomes the critical path. This inversion is most acute in vision-aware edit diffusion, where the encoder is a multimodal large language model (MLLM). We study the case of a 0.39B distilled edit U-Net paired with a 2.13B MLLM text encoder (Qwen3-VL) and present a streaming pipeline targeted at this regime built around three engineering mechanisms: asymmetric side-stream / main-stream CUDA pipelining wit"},"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":"2606.05981","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T10:24:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"42b01130f26e79358914f1bb3abcd0404a7ba8f4a1b6e1c7925f350c82a8580e","abstract_canon_sha256":"5f5f13aeee914a3a658470e81283c22b486e3b551c8370a3ddf429808fb7cb49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:29.454677Z","signature_b64":"tPdFuZkODUtyAJC0ckekFegzaI7if1vD4iaFESsfH6M3C4hvgPRdLZMrcYNfikJyfLYKrcjDQgNE6NZZDAF5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e3b0509b20ba0914832464e90ba10cf145ca3d6f5e4b59d9acc2aa4703dc86b","last_reissued_at":"2026-06-05T01:15:29.454184Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:29.454184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-Rate Streaming Stylization on a Vision-Aware MLLM-Conditioned Edit Diffusion: Asymmetric Batched Inference on a Distilled UNet + MLLM Text Encoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Yoshiyuki Ootani","submitted_at":"2026-06-04T10:24:06Z","abstract_excerpt":"Aggressive distillation of the diffusion U-Net inverts the per-frame bottleneck of real-time text-to-image pipelines: once the denoiser is a 4-step or 1-step distilled student, the text encoder becomes the critical path. This inversion is most acute in vision-aware edit diffusion, where the encoder is a multimodal large language model (MLLM). We study the case of a 0.39B distilled edit U-Net paired with a 2.13B MLLM text encoder (Qwen3-VL) and present a streaming pipeline targeted at this regime built around three engineering mechanisms: asymmetric side-stream / main-stream CUDA pipelining wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05981","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/2606.05981/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":"2606.05981","created_at":"2026-06-05T01:15:29.454256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05981v1","created_at":"2026-06-05T01:15:29.454256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05981","created_at":"2026-06-05T01:15:29.454256+00:00"},{"alias_kind":"pith_short_12","alias_value":"RY5QKCNSBOQJ","created_at":"2026-06-05T01:15:29.454256+00:00"},{"alias_kind":"pith_short_16","alias_value":"RY5QKCNSBOQJCSBS","created_at":"2026-06-05T01:15:29.454256+00:00"},{"alias_kind":"pith_short_8","alias_value":"RY5QKCNS","created_at":"2026-06-05T01:15:29.454256+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/RY5QKCNSBOQJCSBSIZHJBOQQZ4","json":"https://pith.science/pith/RY5QKCNSBOQJCSBSIZHJBOQQZ4.json","graph_json":"https://pith.science/api/pith-number/RY5QKCNSBOQJCSBSIZHJBOQQZ4/graph.json","events_json":"https://pith.science/api/pith-number/RY5QKCNSBOQJCSBSIZHJBOQQZ4/events.json","paper":"https://pith.science/paper/RY5QKCNS"},"agent_actions":{"view_html":"https://pith.science/pith/RY5QKCNSBOQJCSBSIZHJBOQQZ4","download_json":"https://pith.science/pith/RY5QKCNSBOQJCSBSIZHJBOQQZ4.json","view_paper":"https://pith.science/paper/RY5QKCNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05981&json=true","fetch_graph":"https://pith.science/api/pith-number/RY5QKCNSBOQJCSBSIZHJBOQQZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/RY5QKCNSBOQJCSBSIZHJBOQQZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RY5QKCNSBOQJCSBSIZHJBOQQZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RY5QKCNSBOQJCSBSIZHJBOQQZ4/action/storage_attestation","attest_author":"https://pith.science/pith/RY5QKCNSBOQJCSBSIZHJBOQQZ4/action/author_attestation","sign_citation":"https://pith.science/pith/RY5QKCNSBOQJCSBSIZHJBOQQZ4/action/citation_signature","submit_replication":"https://pith.science/pith/RY5QKCNSBOQJCSBSIZHJBOQQZ4/action/replication_record"}},"created_at":"2026-06-05T01:15:29.454256+00:00","updated_at":"2026-06-05T01:15:29.454256+00:00"}