{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VORDOVWBIY3AEO2ZWP7O7RKBG7","short_pith_number":"pith:VORDOVWB","schema_version":"1.0","canonical_sha256":"aba23756c14636023b59b3feefc54137fea56a9b2717fccba5b739b6c8828c4b","source":{"kind":"arxiv","id":"2606.06078","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Distillation for Visual Autoregressive Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amirhossein Habibian, Aritra Bhowmik, Elia Peruzzo, Guillaume Sautiere, Yuki M Asano","submitted_at":"2026-06-04T12:15:31Z","abstract_excerpt":"Autoregressive (AR) image generation models are highly expressive but computationally intensive, motivating effective model compression. Knowledge distillation (KD) is a natural approach for model compression and has been widely studied in language modeling, yet its behavior in visual AR generation remains underexplored. In this work, we present the first systematic study of distillation strategies for AR image models. Our analysis shows that while standard distillation can yield meaningful gains, recent methods developed for language do not directly transfer to images: long decoding horizons "},"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":"2606.06078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T12:15:31Z","cross_cats_sorted":[],"title_canon_sha256":"630f50589babf60391a7f466b0443b2f157f195dc249d9ac1f000d68323b1ce9","abstract_canon_sha256":"ef67bf91e9d272f775e90ea6ff588ffc3d222af39070b4ab3b9e074407991748"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:32.342764Z","signature_b64":"/J2seH+0qAB7Yq0vuAlZW6d1wm0qCK72QYh8iMuvmdjFBpO4gfcvpwELC/Kx7M34L7PzHbtNJdDyZfclTj3cCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aba23756c14636023b59b3feefc54137fea56a9b2717fccba5b739b6c8828c4b","last_reissued_at":"2026-06-05T01:15:32.342292Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:32.342292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation for Visual Autoregressive Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amirhossein Habibian, Aritra Bhowmik, Elia Peruzzo, Guillaume Sautiere, Yuki M Asano","submitted_at":"2026-06-04T12:15:31Z","abstract_excerpt":"Autoregressive (AR) image generation models are highly expressive but computationally intensive, motivating effective model compression. Knowledge distillation (KD) is a natural approach for model compression and has been widely studied in language modeling, yet its behavior in visual AR generation remains underexplored. In this work, we present the first systematic study of distillation strategies for AR image models. Our analysis shows that while standard distillation can yield meaningful gains, recent methods developed for language do not directly transfer to images: long decoding horizons "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06078","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/2606.06078/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":"2606.06078","created_at":"2026-06-05T01:15:32.342375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06078v1","created_at":"2026-06-05T01:15:32.342375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06078","created_at":"2026-06-05T01:15:32.342375+00:00"},{"alias_kind":"pith_short_12","alias_value":"VORDOVWBIY3A","created_at":"2026-06-05T01:15:32.342375+00:00"},{"alias_kind":"pith_short_16","alias_value":"VORDOVWBIY3AEO2Z","created_at":"2026-06-05T01:15:32.342375+00:00"},{"alias_kind":"pith_short_8","alias_value":"VORDOVWB","created_at":"2026-06-05T01:15:32.342375+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/VORDOVWBIY3AEO2ZWP7O7RKBG7","json":"https://pith.science/pith/VORDOVWBIY3AEO2ZWP7O7RKBG7.json","graph_json":"https://pith.science/api/pith-number/VORDOVWBIY3AEO2ZWP7O7RKBG7/graph.json","events_json":"https://pith.science/api/pith-number/VORDOVWBIY3AEO2ZWP7O7RKBG7/events.json","paper":"https://pith.science/paper/VORDOVWB"},"agent_actions":{"view_html":"https://pith.science/pith/VORDOVWBIY3AEO2ZWP7O7RKBG7","download_json":"https://pith.science/pith/VORDOVWBIY3AEO2ZWP7O7RKBG7.json","view_paper":"https://pith.science/paper/VORDOVWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06078&json=true","fetch_graph":"https://pith.science/api/pith-number/VORDOVWBIY3AEO2ZWP7O7RKBG7/graph.json","fetch_events":"https://pith.science/api/pith-number/VORDOVWBIY3AEO2ZWP7O7RKBG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VORDOVWBIY3AEO2ZWP7O7RKBG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VORDOVWBIY3AEO2ZWP7O7RKBG7/action/storage_attestation","attest_author":"https://pith.science/pith/VORDOVWBIY3AEO2ZWP7O7RKBG7/action/author_attestation","sign_citation":"https://pith.science/pith/VORDOVWBIY3AEO2ZWP7O7RKBG7/action/citation_signature","submit_replication":"https://pith.science/pith/VORDOVWBIY3AEO2ZWP7O7RKBG7/action/replication_record"}},"created_at":"2026-06-05T01:15:32.342375+00:00","updated_at":"2026-06-05T01:15:32.342375+00:00"}