{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HSI22V325PJGXVNDHOUBHICDAF","short_pith_number":"pith:HSI22V32","schema_version":"1.0","canonical_sha256":"3c91ad577aebd26bd5a33ba813a0430151c59239b038019001ec5eb4c9872b1f","source":{"kind":"arxiv","id":"2412.16158","version":2},"attestation_state":"computed","paper":{"title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxin Tao, Chenyu Zhang, Gao Huang, Jiawen Liu, Jifeng Dai, Lewei Lu, Shiqian Su, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zhe Chen","submitted_at":"2024-12-20T18:59:59Z","abstract_excerpt":"The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the challenge of inferior performance. Most existing monolithic VLMs require tuning pre-trained LLMs to acquire vision abilities, which may degrade their language capabilities. To address this dilemma, this paper presents a novel high-performance monolithic VLM named HoVLE. We note that LLMs have been shown capable of interpreting images, when image embeddings a"},"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":"2412.16158","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"83f300339f24c975e74e2a722cb68fc5f669e5d2fdb2e2d0b0f2988238c7c31b","abstract_canon_sha256":"9e76357a37841322b716276737ba39fb37983ae8981b1d919715d9791188a765"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:30.646545Z","signature_b64":"WZdvxprNlgV5nFnh6CtHi85cV4N99FaZRO0zwyX1aQNC6MU0IfBoHpcaYo2Zvg1ItBmZHslVWTzqLserCvRmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c91ad577aebd26bd5a33ba813a0430151c59239b038019001ec5eb4c9872b1f","last_reissued_at":"2026-07-05T10:11:30.646027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:30.646027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxin Tao, Chenyu Zhang, Gao Huang, Jiawen Liu, Jifeng Dai, Lewei Lu, Shiqian Su, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zhe Chen","submitted_at":"2024-12-20T18:59:59Z","abstract_excerpt":"The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the challenge of inferior performance. Most existing monolithic VLMs require tuning pre-trained LLMs to acquire vision abilities, which may degrade their language capabilities. To address this dilemma, this paper presents a novel high-performance monolithic VLM named HoVLE. We note that LLMs have been shown capable of interpreting images, when image embeddings a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16158","kind":"arxiv","version":2},"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/2412.16158/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":"2412.16158","created_at":"2026-07-05T10:11:30.646090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16158v2","created_at":"2026-07-05T10:11:30.646090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16158","created_at":"2026-07-05T10:11:30.646090+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSI22V325PJG","created_at":"2026-07-05T10:11:30.646090+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSI22V325PJGXVND","created_at":"2026-07-05T10:11:30.646090+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSI22V32","created_at":"2026-07-05T10:11:30.646090+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/HSI22V325PJGXVNDHOUBHICDAF","json":"https://pith.science/pith/HSI22V325PJGXVNDHOUBHICDAF.json","graph_json":"https://pith.science/api/pith-number/HSI22V325PJGXVNDHOUBHICDAF/graph.json","events_json":"https://pith.science/api/pith-number/HSI22V325PJGXVNDHOUBHICDAF/events.json","paper":"https://pith.science/paper/HSI22V32"},"agent_actions":{"view_html":"https://pith.science/pith/HSI22V325PJGXVNDHOUBHICDAF","download_json":"https://pith.science/pith/HSI22V325PJGXVNDHOUBHICDAF.json","view_paper":"https://pith.science/paper/HSI22V32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16158&json=true","fetch_graph":"https://pith.science/api/pith-number/HSI22V325PJGXVNDHOUBHICDAF/graph.json","fetch_events":"https://pith.science/api/pith-number/HSI22V325PJGXVNDHOUBHICDAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSI22V325PJGXVNDHOUBHICDAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSI22V325PJGXVNDHOUBHICDAF/action/storage_attestation","attest_author":"https://pith.science/pith/HSI22V325PJGXVNDHOUBHICDAF/action/author_attestation","sign_citation":"https://pith.science/pith/HSI22V325PJGXVNDHOUBHICDAF/action/citation_signature","submit_replication":"https://pith.science/pith/HSI22V325PJGXVNDHOUBHICDAF/action/replication_record"}},"created_at":"2026-07-05T10:11:30.646090+00:00","updated_at":"2026-07-05T10:11:30.646090+00:00"}