{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_9957adc04622424c121d7da491e83261456f4a6c11b84b6a06c4db18ee722f6a","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_9957adc04622424c121d7da491e83261456f4a6c11b84b6a06c4db18ee722f6a","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"f7f933b6834ebb0150a689e12cf0161c9eecc505b429dfb55b2c02091a91d736","published":"Mon, 08 Jun 2026 00:00:00 -0400","receipt_hash":"f7f933b6834ebb0150a689e12cf0161c9eecc505b429dfb55b2c02091a91d736","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"f7f933b6834ebb0150a689e12cf0161c9eecc505b429dfb55b2c02091a91d736","observed_at":"2026-06-08T04:44:02.392073Z","parent_run_hash":"4b9e67a023632e16a32d228bb97fee209911f388e0a8dbf20b5a4ec02729c20f","published":"Mon, 08 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2605.20950v2 Announce Type: replace-cross \nAbstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existing vision token reduction methods alleviate this burden, but they unintentionally preserve the isolated visual subject strictly aligned with the user's query, which fails to substantially explore salient subjects and their contextual relationships. In this paper, we propose SPpruner, a subject-centric progressive reduction paradigm that emulates the \\textit{Focus-then-Context} mechanism of the human visual perception system. Specifically, we first construct a focus identification module to explicitly model the interplay between visual saliency and semantic relevance. Herein, it can excavate the comprehensive visual subject spectrum to ensure a high-fidelity representation of visual input. Subsequently, a context-aware structural scanning module is developed to aggregate contextua","title":"Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models","url":"https://arxiv.org/abs/2605.20950","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.20950v2 Announce Type: replace-cross \nAbstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existing vision token reduction methods alleviate this burden, but they unintentionally preserve the isolated visual subject strictly aligned with the user's query, which fails to substantially explore salient subjects and their contextual relationships. In this paper, we propose SPpruner, a subject-centric progressive reduction paradigm that emulates the \\textit{Focus-then-Context} mechanism of the human visual perception system. Specifically, we first construct a focus identification module to explicitly model the interplay between visual saliency and semantic relevance. Herein, it can excavate the comprehensive visual subject spectrum to ensure a high-fidelity representation of visual input. Subsequently, a context-aware structural scanning module is developed to aggregate contextua","title":"Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-08T04:44:02Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.20950"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:c255e85f6821afd0093f356a5108dfd2fb3e80b9affbed1bfe6989997ac0166b09c4bb4514e8818dac12852d1808ae4426bed3ea03b61d7ff7701c2d64ebea02","signer":"crovia.substrate","subject":{"observed_at":"2026-06-08T04:44:02Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.20950"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"67a86ca5aeb372383ff95b9496ba30327f36c96e56a41d4166810345f4260617","leaf_index":223903,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"f3383cca3c171749e0f44d3ab83ab3081c9d42f9f480b45023588b0ef8d58b06","side":"left"},{"sibling":"50c242befe31abc45c487eafbee18b137d513c59d7e64fe82d4a660fd05574e0","side":"left"},{"sibling":"60f2f60bd092d2487e2b485e8cb278900d5cad18c8a05aa422b1bf9d8e511090","side":"left"},{"sibling":"e96ffdac5749e6dc3bc6621af6893e03cf670bcc32b3395bcd076c135731ff2d","side":"left"},{"sibling":"786971193f2b7ff3689f59823d26ec748efbc0d4b77edebd05fe29029d41d59f","side":"left"},{"sibling":"7a3fd3b100f030f34dd146a0f7e7ff612e24a350629d2c6d2ccd949dabb576c8","side":"right"},{"sibling":"d9e96a026bf19228243264aa70a028a48f8a58ae04caab8ebd434847bf9e27ac","side":"right"},{"sibling":"e9e4595b6d3a8db8d409d92f766595bee2c79e9389fc033969243fd816d368c5","side":"left"},{"sibling":"fad4d9627e4b025e7840b4e896082fb8291cbf1a4c05653b3a789c8a4205d4b5","side":"right"},{"sibling":"e8dcea313a54920d83e4f72d5a4223f986c719f264241d171c4712efaaf1fc54","side":"left"},{"sibling":"5480e1ea31f4744f9bd7c4261771fe51f2cdb01e705cc17320bfc202d935ca12","side":"right"},{"sibling":"24fdc29d461691aedb6fa920758206b5bb43851f477ef7a04c34aaed84b8971b","side":"left"},{"sibling":"036922da4e1e2c46d948f070454bfad299b7406fb00735ea9d8bd1e687f5f445","side":"right"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"87c6b850dfec08ac35a693d9db3a3315250a68adb1cfab9b1015f212b63b15bd","side":"right"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":224761,"merkle_root":"e9f7b49b652e869ab97ffba9c5a31356b2d0e3dc5d00bb28944adf737c46b1e7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260609T103805Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-09T14:15:34Z","sig_algorithm":"ed25519","signature":"8ad8076fb12c8e486ae1d1559a9a7ba8e2ee996a9ad3d8ba7bcdbdbd88ab3a15bcb429707aca6d3e9d8b97e2ba755b3dcc77b1abb6601ccb829842719a6fb30d","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_9957adc04622424c121d7da491e83261456f4a6c11b84b6a06c4db18ee722f6a"}}