{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XXMJ2NHHAXOHWMNFGFBXUC4CXI","short_pith_number":"pith:XXMJ2NHH","schema_version":"1.0","canonical_sha256":"bdd89d34e705dc7b31a531437a0b82ba1979ecf24ec99ee74181c8f9372b81a1","source":{"kind":"arxiv","id":"2501.04001","version":3},"attestation_state":"computed","paper":{"title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haobo Yuan, Jiashi Feng, Lu Qi, Ming-Hsuan Yang, Shilin Xu, Shunping Ji, Tao Zhang, Xiangtai Li, Yueyi Sun, Yunhai Tong, Zilong Huang","submitted_at":"2025-01-07T18:58:54Z","abstract_excerpt":"This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal one-shot instruction tuning. Sa2VA combines SAM-2, a foundation video segmentation model, with MLLM, the advanced vision-language model, and unifies text, image, and video into a shared LLM token space. Using the LLM, Sa2VA generates instruction to"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2501.04001","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T18:58:54Z","cross_cats_sorted":[],"title_canon_sha256":"182fbd81701d2e83bb759bbc154509c069a63c6d97465120834f6e8e7d179ffb","abstract_canon_sha256":"af1b72fcb24f808b68a624b1c50a2756d0e0ee2cfca9157d605e2e71789746e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.000652Z","signature_b64":"iNC8AvmmvhT4VsBahBDAPDHVjw8yB3GQZYeLULtDlZePTUySLtRYat3Gl6t6X1V+pV99rH/BtK9SQuPxMo2nBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdd89d34e705dc7b31a531437a0b82ba1979ecf24ec99ee74181c8f9372b81a1","last_reissued_at":"2026-05-17T23:38:48.000065Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.000065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haobo Yuan, Jiashi Feng, Lu Qi, Ming-Hsuan Yang, Shilin Xu, Shunping Ji, Tao Zhang, Xiangtai Li, Yueyi Sun, Yunhai Tong, Zilong Huang","submitted_at":"2025-01-07T18:58:54Z","abstract_excerpt":"This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal one-shot instruction tuning. Sa2VA combines SAM-2, a foundation video segmentation model, with MLLM, the advanced vision-language model, and unifies text, image, and video into a shared LLM token space. Using the LLM, Sa2VA generates instruction to"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Sa2VA is the first comprehensive, unified model for dense grounded understanding of both images and videos that supports referring segmentation and conversation with minimal one-shot instruction tuning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the LLM-generated instruction tokens can reliably guide SAM-2 to produce precise masks across complex video scenes without task-specific architectural changes or heavy fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e2e0c6f450bbd5a684e1cce0175ca33a6167b5f731f0c3ab33d5f25dd01d6f71"},"source":{"id":"2501.04001","kind":"arxiv","version":3},"verdict":{"id":"96ea7224-7912-48dc-ba16-361d3a3b6fc6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T11:35:57.949381Z","strongest_claim":"Sa2VA is the first comprehensive, unified model for dense grounded understanding of both images and videos that supports referring segmentation and conversation with minimal one-shot instruction tuning.","one_line_summary":"Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the LLM-generated instruction tokens can reliably guide SAM-2 to produce precise masks across complex video scenes without task-specific architectural changes or heavy fine-tuning.","pith_extraction_headline":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning."},"references":{"count":125,"sample":[{"doi":"","year":2015,"title":"Vqa: Visual question an- swering","work_id":"4f7b2ba9-84f5-40f4-8098-9380e897823d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":2,"cited_arxiv_id":"2308.12966","is_internal_anchor":true},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":3,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":2024,"title":"One token to seg them all: Language instructed reasoning segmentation in videos","work_id":"530daa38-715a-4558-b3a3-a6815a7b7604","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Language models are few-shot learners","work_id":"0640f028-a03b-4b3e-b61b-59f4dc45f798","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":125,"snapshot_sha256":"e92b0993659e5cb959521db9c098eb29a88fa395e46bdf26e2ead24e0756b1c3","internal_anchors":21},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c5a0eaf80ac15fff66dc43e957e0b934c253c88c53d0a75462d6131576c315cb"},"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":"2501.04001","created_at":"2026-05-17T23:38:48.000154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04001v3","created_at":"2026-05-17T23:38:48.000154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04001","created_at":"2026-05-17T23:38:48.000154+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXMJ2NHHAXOH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXMJ2NHHAXOHWMNF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXMJ2NHH","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":27,"sample":[{"citing_arxiv_id":"2505.16416","citing_title":"Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22558","citing_title":"GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20676","citing_title":"VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20110","citing_title":"SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14692","citing_title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2505.20122","citing_title":"MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2511.20886","citing_title":"V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2512.06673","citing_title":"Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2601.02018","citing_title":"Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2601.08831","citing_title":"3AM: 3egment Anything with Geometric Consistency in Videos","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2601.10611","citing_title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","ref_index":177,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14091","citing_title":"Venus-DeFakerOne: Unified Fake Image Detection & Localization","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13530","citing_title":"Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12953","citing_title":"Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03841","citing_title":"Training a Student Expert via Semi-Supervised Foundation Model Distillation","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10769","citing_title":"MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25886","citing_title":"MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26031","citing_title":"Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23935","citing_title":"2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00891","citing_title":"X2SAM: Any Segmentation in Images and Videos","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":215,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07415","citing_title":"ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14692","citing_title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22836","citing_title":"AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18665","citing_title":"APRVOS: 1st Place Winner of 5th PVUW MeViS-Audio Track","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI","json":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI.json","graph_json":"https://pith.science/api/pith-number/XXMJ2NHHAXOHWMNFGFBXUC4CXI/graph.json","events_json":"https://pith.science/api/pith-number/XXMJ2NHHAXOHWMNFGFBXUC4CXI/events.json","paper":"https://pith.science/paper/XXMJ2NHH"},"agent_actions":{"view_html":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI","download_json":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI.json","view_paper":"https://pith.science/paper/XXMJ2NHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04001&json=true","fetch_graph":"https://pith.science/api/pith-number/XXMJ2NHHAXOHWMNFGFBXUC4CXI/graph.json","fetch_events":"https://pith.science/api/pith-number/XXMJ2NHHAXOHWMNFGFBXUC4CXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/action/storage_attestation","attest_author":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/action/author_attestation","sign_citation":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/action/citation_signature","submit_replication":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/action/replication_record"}},"created_at":"2026-05-17T23:38:48.000154+00:00","updated_at":"2026-05-17T23:38:48.000154+00:00"}