{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SOOIMKHZRSH2CEMAZMH7X5BD4U","short_pith_number":"pith:SOOIMKHZ","canonical_record":{"source":{"id":"2406.02987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T06:36:43Z","cross_cats_sorted":[],"title_canon_sha256":"864b245cb24f61d8b0fe3e0287b5b617567da9678e4a5dce4550a013421f1c69","abstract_canon_sha256":"de84403aeb1e46f34ebe712a8bf9e58a8af90546fc250b72ce3e526eb8abb6d6"},"schema_version":"1.0"},"canonical_sha256":"939c8628f98c8fa11180cb0ffbf423e520e9717570b92ffbda230c3fb4d06dea","source":{"kind":"arxiv","id":"2406.02987","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02987","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02987v1","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02987","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"SOOIMKHZRSH2","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"SOOIMKHZRSH2CEMA","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"SOOIMKHZ","created_at":"2026-07-05T08:27:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SOOIMKHZRSH2CEMAZMH7X5BD4U","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T06:36:43Z","cross_cats_sorted":[],"title_canon_sha256":"864b245cb24f61d8b0fe3e0287b5b617567da9678e4a5dce4550a013421f1c69","abstract_canon_sha256":"de84403aeb1e46f34ebe712a8bf9e58a8af90546fc250b72ce3e526eb8abb6d6"},"schema_version":"1.0"},"canonical_sha256":"939c8628f98c8fa11180cb0ffbf423e520e9717570b92ffbda230c3fb4d06dea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:33.848369Z","signature_b64":"mW2VIs3omQ1re6nKFTQwwuSlIsDvyoyUxNtT3EVeacCoAPOjiEvBCtukAsqsd9vYnbOAz6Lj4M99FccyV1LWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"939c8628f98c8fa11180cb0ffbf423e520e9717570b92ffbda230c3fb4d06dea","last_reissued_at":"2026-07-05T08:27:33.847861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:33.847861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02987","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xzGSBDKrW+dfhKWYPM/KNyN8mNBnviHnAWHKrkRkFksaJQuobeWH446Mi24asACaXQ0Yg0F6tVn8aWpoiFRRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:04:07.942664Z"},"content_sha256":"fca2399475b52f12aee3b6dfe8a1ae09ad298489458c093ca2024bbea8698917","schema_version":"1.0","event_id":"sha256:fca2399475b52f12aee3b6dfe8a1ae09ad298489458c093ca2024bbea8698917"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SOOIMKHZRSH2CEMAZMH7X5BD4U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Multimodal Large Language Models with Multi-instance Visual Prompt Generator for Visual Representation Enrichment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxin Du, Ismail Tutar, Junzhou Huang, Karim Bouyarmane, Qi Li, Rob Barton, Shioulin Sam, Wenliang Zhong, Wenyi Wu","submitted_at":"2024-06-05T06:36:43Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved SOTA performance in various visual language tasks by fusing the visual representations with LLMs leveraging some visual adapters. In this paper, we first establish that adapters using query-based Transformers such as Q-former is a simplified Multi-instance Learning method without considering instance heterogeneity/correlation. We then propose a general component termed Multi-instance Visual Prompt Generator (MIVPG) to incorporate enriched visual representations into LLMs by taking advantage of instance correlation between images or patches"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02987","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.02987/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUXNJscjIZN/dOdCQecRTHOAlf2QIFCCMMM8dQ7nqJz8gbYRWOYgk64/pJdZPtsgRDGlhkWOtCZVSVRYZseiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:04:07.943047Z"},"content_sha256":"0e7f61642118db76bfc0be4ce9517694445452d6d63b60351b8455ac1d108f7a","schema_version":"1.0","event_id":"sha256:0e7f61642118db76bfc0be4ce9517694445452d6d63b60351b8455ac1d108f7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SOOIMKHZRSH2CEMAZMH7X5BD4U/bundle.json","state_url":"https://pith.science/pith/SOOIMKHZRSH2CEMAZMH7X5BD4U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SOOIMKHZRSH2CEMAZMH7X5BD4U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T07:04:07Z","links":{"resolver":"https://pith.science/pith/SOOIMKHZRSH2CEMAZMH7X5BD4U","bundle":"https://pith.science/pith/SOOIMKHZRSH2CEMAZMH7X5BD4U/bundle.json","state":"https://pith.science/pith/SOOIMKHZRSH2CEMAZMH7X5BD4U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SOOIMKHZRSH2CEMAZMH7X5BD4U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SOOIMKHZRSH2CEMAZMH7X5BD4U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"de84403aeb1e46f34ebe712a8bf9e58a8af90546fc250b72ce3e526eb8abb6d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T06:36:43Z","title_canon_sha256":"864b245cb24f61d8b0fe3e0287b5b617567da9678e4a5dce4550a013421f1c69"},"schema_version":"1.0","source":{"id":"2406.02987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02987","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02987v1","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02987","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"SOOIMKHZRSH2","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"SOOIMKHZRSH2CEMA","created_at":"2026-07-05T08:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"SOOIMKHZ","created_at":"2026-07-05T08:27:33Z"}],"graph_snapshots":[{"event_id":"sha256:0e7f61642118db76bfc0be4ce9517694445452d6d63b60351b8455ac1d108f7a","target":"graph","created_at":"2026-07-05T08:27:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.02987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved SOTA performance in various visual language tasks by fusing the visual representations with LLMs leveraging some visual adapters. In this paper, we first establish that adapters using query-based Transformers such as Q-former is a simplified Multi-instance Learning method without considering instance heterogeneity/correlation. We then propose a general component termed Multi-instance Visual Prompt Generator (MIVPG) to incorporate enriched visual representations into LLMs by taking advantage of instance correlation between images or patches","authors_text":"Boxin Du, Ismail Tutar, Junzhou Huang, Karim Bouyarmane, Qi Li, Rob Barton, Shioulin Sam, Wenliang Zhong, Wenyi Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T06:36:43Z","title":"Enhancing Multimodal Large Language Models with Multi-instance Visual Prompt Generator for Visual Representation Enrichment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02987","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fca2399475b52f12aee3b6dfe8a1ae09ad298489458c093ca2024bbea8698917","target":"record","created_at":"2026-07-05T08:27:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"de84403aeb1e46f34ebe712a8bf9e58a8af90546fc250b72ce3e526eb8abb6d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T06:36:43Z","title_canon_sha256":"864b245cb24f61d8b0fe3e0287b5b617567da9678e4a5dce4550a013421f1c69"},"schema_version":"1.0","source":{"id":"2406.02987","kind":"arxiv","version":1}},"canonical_sha256":"939c8628f98c8fa11180cb0ffbf423e520e9717570b92ffbda230c3fb4d06dea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"939c8628f98c8fa11180cb0ffbf423e520e9717570b92ffbda230c3fb4d06dea","first_computed_at":"2026-07-05T08:27:33.847861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:33.847861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mW2VIs3omQ1re6nKFTQwwuSlIsDvyoyUxNtT3EVeacCoAPOjiEvBCtukAsqsd9vYnbOAz6Lj4M99FccyV1LWAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:33.848369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fca2399475b52f12aee3b6dfe8a1ae09ad298489458c093ca2024bbea8698917","sha256:0e7f61642118db76bfc0be4ce9517694445452d6d63b60351b8455ac1d108f7a"],"state_sha256":"f9c32b897e4c3cf057d065535ccad6502c384e0af21138f7e069ca18115d77e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"naiqQEM1arACcvVUaa6zu1WS+mWE3WqaclVhrL7L3iLQ6R571iziybj1lWIn7hDYx2Y7/1kl4fAk9kPRFMRCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:04:07.947303Z","bundle_sha256":"3f06f99c91ee9ab7501d037f4189c2a39f35515663c73778a1ba871b197e9f91"}}