{"_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_18a0310b0b26b4d250fa60a7a0d26f121beedf65cd9f8990eeef9c9ac8f315ec","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_18a0310b0b26b4d250fa60a7a0d26f121beedf65cd9f8990eeef9c9ac8f315ec","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e408c5fb6eea3f5b4cdca72da5190f48b3211fb3baed8808d38052e1ed9c432f","published":"Mon, 01 Jun 2026 00:00:00 -0400","receipt_hash":"e408c5fb6eea3f5b4cdca72da5190f48b3211fb3baed8808d38052e1ed9c432f","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":"e408c5fb6eea3f5b4cdca72da5190f48b3211fb3baed8808d38052e1ed9c432f","observed_at":"2026-06-01T04:43:13.859018Z","parent_run_hash":"8993bbc535dae8c9669e099af3624cb39166b8d9bbfd66f26ae5c338cbb21be2","published":"Mon, 01 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:2605.30561v1 Announce Type: cross \nAbstract: Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding. However, 3D understanding still largely relies on expert vision models with complex task-specific designs. The key argument this work wants to make is that VLMs are native 3D learners. Our in-depth large scale study shows that 1) focal length unification, 2) text-based pixel reference and 3) data mixture and scaling, are all you need for effective 3D learning. Model architecture changes, large models, heavy data augmentations, and complex losses including the regression formulation, many of which form the foundation of expert vision models, are actually not necessary conditions. As a result, we propose VLM3, a scalable method with the simplest design that enables standard VLMs to master diverse 3D tasks. VLM3 not only advances the VLM depth estimation accuracy by a large ","title":"VLM3: Vision Language Models Are Native 3D Learners","url":"https://arxiv.org/abs/2605.30561","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.30561v1 Announce Type: cross \nAbstract: Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting. They have shown promising performance in semantic understanding. However, 3D understanding still largely relies on expert vision models with complex task-specific designs. The key argument this work wants to make is that VLMs are native 3D learners. Our in-depth large scale study shows that 1) focal length unification, 2) text-based pixel reference and 3) data mixture and scaling, are all you need for effective 3D learning. Model architecture changes, large models, heavy data augmentations, and complex losses including the regression formulation, many of which form the foundation of expert vision models, are actually not necessary conditions. As a result, we propose VLM3, a scalable method with the simplest design that enables standard VLMs to master diverse 3D tasks. VLM3 not only advances the VLM depth estimation accuracy by a large ","title":"VLM3: Vision Language Models Are Native 3D Learners","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-01T04:43:13Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.30561"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:a1ce63e6bddd6db1eb182e2555d47e4078d4aff2b0ca511829211a6ef83f8f13831f4de5b6d86ff978d424ae5eda7d679890a2796d592db5d8fc23d1120d9c04","signer":"crovia.substrate","subject":{"observed_at":"2026-06-01T04:43:13Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.30561"},"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":"449c92ed5075a57a56f2af39e8e57e71e1a5ff2f9b7e3699fe59d9e383dcef0a","leaf_index":163836,"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":"abe70628450c325f9c0a2d5280b58f93a7aa4b9b99527010d097089b88abb5c3","side":"right"},{"sibling":"fc644bf17eceefa0466ec7372a2e556a2d7635428507e42f2d727f36918f022e","side":"right"},{"sibling":"c6e40d2a4499561493872b1568e5285da43a7ff7ced092b5a87a4659d0a086d1","side":"left"},{"sibling":"3768a10bc566886e5d4e900a7bdb7aa03041e2fdbf823ddcd6029c3d1aa2752a","side":"left"},{"sibling":"4d05c1d10ce177e734550afbe0158142b54cf93075855777c739ec460dad2756","side":"left"},{"sibling":"a8f314233e57d9b2e1f73a238db7bf336c4b3b1673499ca02aeae9337c8cb49b","side":"left"},{"sibling":"6f506d4e4c7fb170ea5ab20efffbcbb69464bf6db4cde5e90925fede53e31584","side":"left"},{"sibling":"764e4312cdb701ef8613acdc2311e1724d6a379f21c70c30ed832e7ede3d2d33","side":"left"},{"sibling":"5a0517e6c348bc5a70f1aef04c1415d23980c712e375838fff54dfa281f98760","side":"left"},{"sibling":"d6986f4b6a5bd07cba1de43f660d527af780ad1465d0f4af5f137bd514e95f7e","side":"left"},{"sibling":"aff54f89d4445cf32bb05b2ece532d190200cb92524489ddfa648b5cc36e21a4","side":"left"},{"sibling":"f028fad1771bff7dceff3a83baf90249f4eb410ebedfe92dda1bb2b89d7093c8","side":"left"},{"sibling":"59c6490072e8a1d357ece10bb08d7f449a3acbae58e130e3e7469cbea0314c65","side":"left"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"c9ac00eed8c475f1e525869bb329af03d052181b19ff8234edefe12f6ecec154","side":"right"},{"sibling":"ce41d9b82f34b16efd653dfb3552acc4e2512939e47903e5fc979fbed00c5764","side":"right"},{"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":164217,"merkle_root":"a1098816aea1b60b8fe37b62410469bc5024a2c335bbec4f6ef2add7875dbdf2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260601T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-01T05:37:41Z","sig_algorithm":"ed25519","signature":"d7f91db1d54b9495c499440c2828f4bd53360555391ce6e25adea5183bc1fa0f697d80708a099d0b0429e6f8cb6c71e7fccf82acb3c84481149974fb26074708","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_18a0310b0b26b4d250fa60a7a0d26f121beedf65cd9f8990eeef9c9ac8f315ec"}}