{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SCPEKNYM2KZORBN34L53N2ZXQI","short_pith_number":"pith:SCPEKNYM","schema_version":"1.0","canonical_sha256":"909e45370cd2b2e885bbe2fbb6eb37822f43e880719316701e5f173d1c7874b8","source":{"kind":"arxiv","id":"2402.03766","version":1},"attestation_state":"computed","paper":{"title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Chunhua Shen, Fei Wei, Limeng Qiao, Shuang Xu, Xiangxiang Chu, Xiaofei Sun, Xinyang Lin, Xinyu Zhang, Yang Yang, Yiming Hu","submitted_at":"2024-02-06T07:16:36Z","abstract_excerpt":"We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance. Specifically, MobileVLM V2 1.7B achieves better or on-par performance on standard VLM benchmarks compared with much larger VLMs at the 3B scale. Notably, our 3B model outperforms a large variety of VLMs at the 7B+ scale. Our models will be released at https://github.com/Meituan-AutoML/M"},"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":"2402.03766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T07:16:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84b9c58045de68a8b2907ac0d45e29242e04429d9fa6940472a6ac564a360e02","abstract_canon_sha256":"7eb8e16f991b71830f382d088f0cf1c5c5829439efb21b87c2952af69febfcb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T15:20:59.326796Z","signature_b64":"BRBgDR1TojGpgLy1UI2OwaCZRFgZXm9tOujzbNVQ1XCMVyPVJSaR0YheA0Q15mp59FRR35O6821UjclnattvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"909e45370cd2b2e885bbe2fbb6eb37822f43e880719316701e5f173d1c7874b8","last_reissued_at":"2026-05-18T15:20:59.324347Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T15:20:59.324347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Chunhua Shen, Fei Wei, Limeng Qiao, Shuang Xu, Xiangxiang Chu, Xiaofei Sun, Xinyang Lin, Xinyu Zhang, Yang Yang, Yiming Hu","submitted_at":"2024-02-06T07:16:36Z","abstract_excerpt":"We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance. Specifically, MobileVLM V2 1.7B achieves better or on-par performance on standard VLM benchmarks compared with much larger VLMs at the 3B scale. Notably, our 3B model outperforms a large variety of VLMs at the 7B+ scale. Our models will be released at https://github.com/Meituan-AutoML/M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03766","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":""},"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":"2402.03766","created_at":"2026-05-18T15:20:59.324493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03766v1","created_at":"2026-05-18T15:20:59.324493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03766","created_at":"2026-05-18T15:20:59.324493+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCPEKNYM2KZO","created_at":"2026-05-18T15:20:59.324493+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCPEKNYM2KZORBN3","created_at":"2026-05-18T15:20:59.324493+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCPEKNYM","created_at":"2026-05-18T15:20:59.324493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":17,"sample":[{"citing_arxiv_id":"2509.21912","citing_title":"Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2409.12514","citing_title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2505.05472","citing_title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04476","citing_title":"Vision-aligned Latent Reasoning for Multi-modal Large Language Model","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2404.14396","citing_title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2410.13848","citing_title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2603.02123","citing_title":"Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02689","citing_title":"Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10641","citing_title":"LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2501.17811","citing_title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09442","citing_title":"UIPress: Bringing Optical Token Compression to UI-to-Code Generation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08050","citing_title":"ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04579","citing_title":"Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13565","citing_title":"UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14629","citing_title":"Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI","json":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI.json","graph_json":"https://pith.science/api/pith-number/SCPEKNYM2KZORBN34L53N2ZXQI/graph.json","events_json":"https://pith.science/api/pith-number/SCPEKNYM2KZORBN34L53N2ZXQI/events.json","paper":"https://pith.science/paper/SCPEKNYM"},"agent_actions":{"view_html":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI","download_json":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI.json","view_paper":"https://pith.science/paper/SCPEKNYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03766&json=true","fetch_graph":"https://pith.science/api/pith-number/SCPEKNYM2KZORBN34L53N2ZXQI/graph.json","fetch_events":"https://pith.science/api/pith-number/SCPEKNYM2KZORBN34L53N2ZXQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/action/storage_attestation","attest_author":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/action/author_attestation","sign_citation":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/action/citation_signature","submit_replication":"https://pith.science/pith/SCPEKNYM2KZORBN34L53N2ZXQI/action/replication_record"}},"created_at":"2026-05-18T15:20:59.324493+00:00","updated_at":"2026-05-18T15:20:59.324493+00:00"}