{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K33NUP5CX2S3LDZFOBJQ3FGO46","short_pith_number":"pith:K33NUP5C","schema_version":"1.0","canonical_sha256":"56f6da3fa2bea5b58f2570530d94cee786231321603dc1d374530f3a0ce033b6","source":{"kind":"arxiv","id":"2309.03905","version":2},"attestation_state":"computed","paper":{"title":"ImageBind-LLM: Multi-modality Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chris Liu, Han Xiao, Hongsheng Li, Jiaming Han, Kaipeng Zhang, Peng Gao, Peng Xu, Renrui Zhang, Shuai Ren, Song Wen, Wenqi Shao, Xiangyu Yue, Xiaoxin Chen, Xudong Lu, Yafei Wen, Yu Qiao, Ziyu Guo","submitted_at":"2023-09-07T17:59:45Z","abstract_excerpt":"We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tuning, different from which, our ImageBind-LLM can respond to multi-modality conditions, including audio, 3D point clouds, video, and their embedding-space arithmetic by only image-text alignment training. During training, we adopt a learnable bind network to align the embedding space between LLaMA and ImageBind's image encoder. Then, the image features transformed by the bind network are added to word tokens of all l"},"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":"2309.03905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2023-09-07T17:59:45Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"90ac6111753f97d35446f8e8707ceb062e26a124c47d9fd93b418e4c9dacade4","abstract_canon_sha256":"9bc94451c27df238adc59c95376bc71be3afb1eb15d3025c5420923dc482327f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:44.186453Z","signature_b64":"spG5iFvvzWb/SxarpnYWe43WYDr3DxsI9UOkEAFGYOx1jH+CaeUx1JamBkyVFtsnQr7S8STdxB/WDFzZ+7Z/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56f6da3fa2bea5b58f2570530d94cee786231321603dc1d374530f3a0ce033b6","last_reissued_at":"2026-07-05T06:49:44.185967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:44.185967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImageBind-LLM: Multi-modality Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chris Liu, Han Xiao, Hongsheng Li, Jiaming Han, Kaipeng Zhang, Peng Gao, Peng Xu, Renrui Zhang, Shuai Ren, Song Wen, Wenqi Shao, Xiangyu Yue, Xiaoxin Chen, Xudong Lu, Yafei Wen, Yu Qiao, Ziyu Guo","submitted_at":"2023-09-07T17:59:45Z","abstract_excerpt":"We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tuning, different from which, our ImageBind-LLM can respond to multi-modality conditions, including audio, 3D point clouds, video, and their embedding-space arithmetic by only image-text alignment training. During training, we adopt a learnable bind network to align the embedding space between LLaMA and ImageBind's image encoder. Then, the image features transformed by the bind network are added to word tokens of all l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.03905","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/2309.03905/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":"2309.03905","created_at":"2026-07-05T06:49:44.186028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.03905v2","created_at":"2026-07-05T06:49:44.186028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.03905","created_at":"2026-07-05T06:49:44.186028+00:00"},{"alias_kind":"pith_short_12","alias_value":"K33NUP5CX2S3","created_at":"2026-07-05T06:49:44.186028+00:00"},{"alias_kind":"pith_short_16","alias_value":"K33NUP5CX2S3LDZF","created_at":"2026-07-05T06:49:44.186028+00:00"},{"alias_kind":"pith_short_8","alias_value":"K33NUP5C","created_at":"2026-07-05T06:49:44.186028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.17015","citing_title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2410.14702","citing_title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18257","citing_title":"CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07575","citing_title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14624","citing_title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01891","citing_title":"Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2311.10122","citing_title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02689","citing_title":"Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11043","citing_title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23860","citing_title":"Exploring Audio Hallucination in Egocentric Video Understanding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11043","citing_title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07895","citing_title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46","json":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46.json","graph_json":"https://pith.science/api/pith-number/K33NUP5CX2S3LDZFOBJQ3FGO46/graph.json","events_json":"https://pith.science/api/pith-number/K33NUP5CX2S3LDZFOBJQ3FGO46/events.json","paper":"https://pith.science/paper/K33NUP5C"},"agent_actions":{"view_html":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46","download_json":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46.json","view_paper":"https://pith.science/paper/K33NUP5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.03905&json=true","fetch_graph":"https://pith.science/api/pith-number/K33NUP5CX2S3LDZFOBJQ3FGO46/graph.json","fetch_events":"https://pith.science/api/pith-number/K33NUP5CX2S3LDZFOBJQ3FGO46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46/action/storage_attestation","attest_author":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46/action/author_attestation","sign_citation":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46/action/citation_signature","submit_replication":"https://pith.science/pith/K33NUP5CX2S3LDZFOBJQ3FGO46/action/replication_record"}},"created_at":"2026-07-05T06:49:44.186028+00:00","updated_at":"2026-07-05T06:49:44.186028+00:00"}