Illuminating Visual Identity in Universal Multimodal Embeddings | Paper Citation Record

Observation 2363b7d3-81bd-4afc-a3da-8fe99693d3db · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Illuminating Visual Identity in Universal Multimodal Embeddings Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:13.346553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd4f6e0e-b313-4b2c-89cf-b70b0de3e3dc · outbound

This paper cites Unicom: Universal and Compact Representation Learning for Image Retrieval.

Illuminating Visual Identity in Universal Multimodal Embeddings Unicom: Universal and Compact Representation Learning for Image Retrieval

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:13.403233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88636538-b85b-48d0-8d11-55c14ce56b5b · outbound

This paper cites Qwen2.5-VL Technical Report.

Illuminating Visual Identity in Universal Multimodal Embeddings Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:13.493030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dd964af-ecc0-4d72-b6a0-0b501e81ebdb · outbound

This paper cites LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders.

Illuminating Visual Identity in Universal Multimodal Embeddings LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:13.611224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a64de592-e3dc-479b-8d0b-49625f0cf298 · outbound

This paper cites Flame: Frozen large language models enable data-efficient language-image pre- training.

Illuminating Visual Identity in Universal Multimodal Embeddings Flame: Frozen large language models enable data-efficient language-image pre- training

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:13.727986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e7d481e-e174-4d49-a57f-18746709650d · outbound

This paper cites mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data.

Illuminating Visual Identity in Universal Multimodal Embeddings mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:13.812234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce543fff-5dde-46e1-bc81-2031f0eb2874 · outbound

This paper cites Murag: Multimodal retrieval-augmented generator for open question answering over images and text.

Illuminating Visual Identity in Universal Multimodal Embeddings Murag: Multimodal retrieval-augmented generator for open question answering over images and text

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:13.932581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ab3143-6da5-4689-99ea-34a6d71ff4a8 · outbound

This paper cites Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks.

Illuminating Visual Identity in Universal Multimodal Embeddings Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:14.058096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2d25ea6-cd73-4d60-9e7a-3ef01090b387 · outbound

This paper cites Opengpt-4o-image: A com- prehensive dataset for advanced image generation and edit- ing.arXiv preprint arXiv:2509.24900, 2025.

Illuminating Visual Identity in Universal Multimodal Embeddings Opengpt-4o-image: A com- prehensive dataset for advanced image generation and edit- ing.arXiv preprint arXiv:2509.24900, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:14.225875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ced016ae-bb8a-4efa-8861-ef6d4e4a0e19 · outbound

This paper cites Think then embed: Generative context improves multimodal embedding.arXiv preprint arXiv:2510.05014,.

Illuminating Visual Identity in Universal Multimodal Embeddings Think then embed: Generative context improves multimodal embedding.arXiv preprint arXiv:2510.05014,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:14.394360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1503431a-f199-4920-89fd-2aa1bdbb0418 · outbound

This paper cites Arcface: Additive angular margin loss for deep face recognition.

Illuminating Visual Identity in Universal Multimodal Embeddings Arcface: Additive angular margin loss for deep face recognition

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:14.494829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84c5eb15-19db-4409-9a10-8ec3f53b88d7 · outbound

This paper cites Efficient and discriminative image feature extrac- tion for universal image retrieval.

Illuminating Visual Identity in Universal Multimodal Embeddings Efficient and discriminative image feature extrac- tion for universal image retrieval

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:14.665447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6675d07d-4f80-441a-9de8-552a76f22541 · outbound

This paper cites DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data.

Illuminating Visual Identity in Universal Multimodal Embeddings DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:14.825424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e1ac40a-362b-4648-b680-886b4dcee7b4 · outbound

This paper cites Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup.

Illuminating Visual Identity in Universal Multimodal Embeddings Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:14.991222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 036f4965-2c3d-44eb-95c6-f35eb5cbe0a1 · outbound

This paper cites SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation.

Illuminating Visual Identity in Universal Multimodal Embeddings SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.155373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2d55248-5423-4de2-bd52-c4b22dd1ce2b · outbound

This paper cites Breaking the modality barrier: Universal embedding learning with multimodal llms.arXiv preprint arXiv:2504.17432, 2025.

Illuminating Visual Identity in Universal Multimodal Embeddings Breaking the modality barrier: Universal embedding learning with multimodal llms.arXiv preprint arXiv:2504.17432, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.239595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 809043bb-8bd1-4a11-8630-d35cce3060a4 · outbound

This paper cites Unime-v2: Mllm-as-a-judge for uni- versal multimodal embedding learning.arXiv preprint arXiv:2510.13515, 2025.

Illuminating Visual Identity in Universal Multimodal Embeddings Unime-v2: Mllm-as-a-judge for uni- versal multimodal embedding learning.arXiv preprint arXiv:2510.13515, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.281060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6a7724b-16fd-42e0-8e92-c11485f0cb06 · outbound

This paper cites jina-embeddings-v4: Universal embeddings for multimodal multilingual retrieval.

Illuminating Visual Identity in Universal Multimodal Embeddings jina-embeddings-v4: Universal embeddings for multimodal multilingual retrieval

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.356047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44a9300e-5520-4cee-ae65-51ce664fb9c2 · outbound

This paper cites Ms-celeb-1m: A dataset and benchmark for large-scale face recognition.

Illuminating Visual Identity in Universal Multimodal Embeddings Ms-celeb-1m: A dataset and benchmark for large-scale face recognition

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.495874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f71a18a8-5f8a-4d10-ae47-c58f4fb9ad44 · outbound

This paper cites In Defense of the Triplet Loss for Person Re-Identification.

Illuminating Visual Identity in Universal Multimodal Embeddings In Defense of the Triplet Loss for Person Re-Identification

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.565316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07e17851-bee6-46b0-aa54-affa8b247483 · outbound

This paper cites Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022.

Illuminating Visual Identity in Universal Multimodal Embeddings Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.678112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31614ed6-7a1a-41c3-bc9d-bc694a947a15 · outbound

This paper cites Llm2clip: Powerful language model unlocks richer visual representation.arXiv preprint arXiv:2411.04997, 2024.

Illuminating Visual Identity in Universal Multimodal Embeddings Llm2clip: Powerful language model unlocks richer visual representation.arXiv preprint arXiv:2411.04997, 2024

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.751502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e5169f5-85b8-4aad-a134-ca2008b0f153 · outbound

This paper cites Scaling up visual and vision-language representa- tion learning with noisy text supervision.

Illuminating Visual Identity in Universal Multimodal Embeddings Scaling up visual and vision-language representa- tion learning with noisy text supervision

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.861413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aec1c32d-63af-40d8-a722-e6794830ce73 · outbound

This paper cites E5-V: Universal Embeddings with Multimodal Large Language Models.

Illuminating Visual Identity in Universal Multimodal Embeddings E5-V: Universal Embeddings with Multimodal Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:15.906861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c618cf0-6d98-493e-af7c-dc803f18a35b · outbound

This paper cites Vlm2vec: Training vision-language models for massive multimodal embedding tasks.

Illuminating Visual Identity in Universal Multimodal Embeddings Vlm2vec: Training vision-language models for massive multimodal embedding tasks

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:22.560698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 68e4c1a0-4d0d-436a-b85c-8bffd421c7ac · outbound

This paper cites Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval.

Illuminating Visual Identity in Universal Multimodal Embeddings Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:16.106644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69f665ef-4a45-4d80-a72b-0487e08fa2e7 · outbound

This paper cites Ilias: Instance-level image retrieval at scale.

Illuminating Visual Identity in Universal Multimodal Embeddings Ilias: Instance-level image retrieval at scale

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:22.326487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 73ae2735-f4c0-4927-ba64-3ea619c019e7 · outbound

This paper cites jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images.

Illuminating Visual Identity in Universal Multimodal Embeddings jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:16.254863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a65a327a-6dda-4007-b95c-ae815c88f5d0 · outbound

This paper cites 3d object representations for fine-grained categorization.

Illuminating Visual Identity in Universal Multimodal Embeddings 3d object representations for fine-grained categorization

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:22.112459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4d378f39-698e-463e-b460-d32df3b19ecd · outbound

This paper cites Llave: Large language and vision embedding models with hardness-weighted contrastive learning.arXiv preprint arXiv:2503.04812, 2025.

Illuminating Visual Identity in Universal Multimodal Embeddings Llave: Large language and vision embedding models with hardness-weighted contrastive learning.arXiv preprint arXiv:2503.04812, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:16.514852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fdaf9ed-6939-417d-b030-3aef457a9870 · outbound

This paper cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models.

Illuminating Visual Identity in Universal Multimodal Embeddings NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:16.588928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5aa0e80-d869-447d-9cf1-3cc72948598d · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Illuminating Visual Identity in Universal Multimodal Embeddings LLaVA-OneVision: Easy Visual Task Transfer

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:16.658249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c7a46d-5e3a-4422-ba4e-2b86744e564a · outbound

This paper cites MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization.

Illuminating Visual Identity in Universal Multimodal Embeddings MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-04T20:43:17.744970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6dc4ce12-4e7a-495b-8c25-13ae83d0a9db · outbound

This paper cites Personalvideo: High id-fidelity video customization without dynamic and semantic degradation.

Illuminating Visual Identity in Universal Multimodal Embeddings Personalvideo: High id-fidelity video customization without dynamic and semantic degradation

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:21.903587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 77dbe72f-dc1e-4ac4-ae64-923d92c34748 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

Illuminating Visual Identity in Universal Multimodal Embeddings Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:16.848115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20c6ace6-e135-4bb5-a263-204f179e002a · outbound

This paper cites Open-Sora Plan: Open-Source Large Video Generation Model.

Illuminating Visual Identity in Universal Multimodal Embeddings Open-Sora Plan: Open-Source Large Video Generation Model

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:16.957129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6134962-d0e8-4c11-8465-dabdb4092ea0 · outbound

This paper cites UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation.

Illuminating Visual Identity in Universal Multimodal Embeddings UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.032612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55759e70-7d51-48d1-ae24-01e839854cf1 · outbound

This paper cites Mm-embed: Universal multimodal retrieval with multimodal llms.

Illuminating Visual Identity in Universal Multimodal Embeddings Mm-embed: Universal multimodal retrieval with multimodal llms

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:21.674734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 97524d2e-81b4-4eaf-b53f-630d677d6522 · outbound

This paper cites IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval.

Illuminating Visual Identity in Universal Multimodal Embeddings IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.179548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c0a19dd-6584-43e3-8e78-f2306bde46d5 · outbound

This paper cites Automatic synthetic data and fine- grained adaptive feature alignment for composed person re- trieval.

Illuminating Visual Identity in Universal Multimodal Embeddings Automatic synthetic data and fine- grained adaptive feature alignment for composed person re- trieval

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:21.464572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9f181751-f6ec-46ee-8eeb-b9440fc26489 · outbound

This paper cites Sphereface: Deep hypersphere embedding for face recognition.

Illuminating Visual Identity in Universal Multimodal Embeddings Sphereface: Deep hypersphere embedding for face recognition

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.260553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 775382e5-b8cc-4a14-a21b-127769462100 · outbound

This paper cites Large- scale vehicle re-identification in urban surveillance videos.

Illuminating Visual Identity in Universal Multimodal Embeddings Large- scale vehicle re-identification in urban surveillance videos

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:21.260878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bcfdc93d-0712-4382-8ac6-8d4129837f68 · outbound

This paper cites Lamra: Large multimodal model as your advanced retrieval assistant.

Illuminating Visual Identity in Universal Multimodal Embeddings Lamra: Large multimodal model as your advanced retrieval assistant

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:21.013085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 45cf1584-619d-4bbf-bf45-0b149e00568f · outbound

This paper cites Deepfashion: Powering robust clothes recognition and retrieval with rich annotations.

Illuminating Visual Identity in Universal Multimodal Embeddings Deepfashion: Powering robust clothes recognition and retrieval with rich annotations

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:20.814995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8091a9df-dbd6-42d8-81e4-7712ab156d92 · outbound

This paper cites VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents.

Illuminating Visual Identity in Universal Multimodal Embeddings VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.273022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6eef85d-e283-41e8-8d54-c2db472faef7 · outbound

This paper cites A culturally-aware benchmark for person re-identification in modest attire.Engineering Ap- plications of Artificial Intelligence, 158:111494, 2025.

Illuminating Visual Identity in Universal Multimodal Embeddings A culturally-aware benchmark for person re-identification in modest attire.Engineering Ap- plications of Artificial Intelligence, 158:111494, 2025

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:20.638218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 421feeaf-c31b-42ed-a906-f54525ffb7e8 · outbound

This paper cites Deep metric learning via lifted structured fea- ture embedding.

Illuminating Visual Identity in Universal Multimodal Embeddings Deep metric learning via lifted structured fea- ture embedding

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:20.392243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5898f116-c7ce-4c52-b079-08ad080bd6a7 · outbound

This paper cites RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification.

Illuminating Visual Identity in Universal Multimodal Embeddings RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.284647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eaf0447-583f-46d7-8672-60cb21b66218 · outbound

This paper cites Revisiting oxford and paris: Large-scale image retrieval benchmarking.

Illuminating Visual Identity in Universal Multimodal Embeddings Revisiting oxford and paris: Large-scale image retrieval benchmarking

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:20.266199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 624f29d7-4559-42a1-9e5c-1285ade0939e · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Illuminating Visual Identity in Universal Multimodal Embeddings Learning transferable visual models from natural language supervi- sion

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.290997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e24db9c0-0477-404c-b96c-4fa04bdd4ca2 · outbound

This paper cites Performance measures and a data set for multi-target, multi-camera tracking.

Illuminating Visual Identity in Universal Multimodal Embeddings Performance measures and a data set for multi-target, multi-camera tracking

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:20.078583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3aa65bd2-642e-44e9-9f56-f9c3284cf5c8 · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

Illuminating Visual Identity in Universal Multimodal Embeddings EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.297183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51c43246-bcb5-42d8-85e2-138c2169789b · outbound

This paper cites Visual named entity linking: A new dataset and a baseline.

Illuminating Visual Identity in Universal Multimodal Embeddings Visual named entity linking: A new dataset and a baseline

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:19.950019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9297161b-4cfe-43c4-8db0-90ab72749cd6 · outbound

This paper cites Breaking the batch barrier (b3) of contrastive learning via smart batch mining.arXiv preprint arXiv:2505.11293, 2025.

Illuminating Visual Identity in Universal Multimodal Embeddings Breaking the batch barrier (b3) of contrastive learning via smart batch mining.arXiv preprint arXiv:2505.11293, 2025

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.303217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b175f18-ce65-49f6-b80d-f97439b0ad29 · outbound

This paper cites SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features.

Illuminating Visual Identity in Universal Multimodal Embeddings SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.306059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610fae48-b01c-4259-8dc5-e769b16bfb37 · outbound

This paper cites The inaturalist species classification and de- tection dataset.

Illuminating Visual Identity in Universal Multimodal Embeddings The inaturalist species classification and de- tection dataset

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.309133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4055274-555e-4706-a121-2c528e67943e · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Illuminating Visual Identity in Universal Multimodal Embeddings Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.312239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60351181-dd15-4ad5-9198-04f7cc56be39 · outbound

This paper cites InstantID: Zero-shot Identity-Preserving Generation in Seconds.

Illuminating Visual Identity in Universal Multimodal Embeddings InstantID: Zero-shot Identity-Preserving Generation in Seconds

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.315397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e875a0a6-b8b5-442d-8947-11f2f9821327 · outbound

This paper cites GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset.

Illuminating Visual Identity in Universal Multimodal Embeddings GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.318655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 932e528f-e291-479a-afd3-bda7ba484c26 · outbound

This paper cites Uniir: Train- ing and benchmarking universal multimodal information re- trievers.

Illuminating Visual Identity in Universal Multimodal Embeddings Uniir: Train- ing and benchmarking universal multimodal information re- trievers

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:19.787105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6755346c-bcb1-4235-8fe7-e6c08722c841 · outbound

This paper cites Google landmarks dataset v2-a large-scale benchmark for instance-level recognition and retrieval.

Illuminating Visual Identity in Universal Multimodal Embeddings Google landmarks dataset v2-a large-scale benchmark for instance-level recognition and retrieval

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:19.613019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 99e89c04-a22a-4938-bea5-2df5c91abf9e · outbound

This paper cites Fashion iq: A new dataset towards retrieving images by natural language feedback.

Illuminating Visual Identity in Universal Multimodal Embeddings Fashion iq: A new dataset towards retrieving images by natural language feedback

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:19.467311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d03ce222-b0c5-458c-aa79-c6143ef507e5 · outbound

This paper cites Forb: a flat object retrieval benchmark for universal im- age embedding.Advances in Neural Information Processing Systems, 36:25448–25460, 2023.

Illuminating Visual Identity in Universal Multimodal Embeddings Forb: a flat object retrieval benchmark for universal im- age embedding.Advances in Neural Information Processing Systems, 36:25448–25460, 2023

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:19.366074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 46449807-f27c-469a-8b8c-f762153cc6e0 · outbound

This paper cites Withanyone: Towards control- lable and id consistent image generation.arXiv preprint arXiv:2510.14975, 2025.

Illuminating Visual Identity in Universal Multimodal Embeddings Withanyone: Towards control- lable and id consistent image generation.arXiv preprint arXiv:2510.14975, 2025

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.333489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2e52caf-a117-4d20-864f-ee1847e6c1db · outbound

This paper cites Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying.

Illuminating Visual Identity in Universal Multimodal Embeddings Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.336608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e9efb2-e9f0-4622-8961-558d1fdb1567 · outbound

This paper cites Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese.

Illuminating Visual Identity in Universal Multimodal Embeddings Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.339889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7af4341d-dbac-4eda-b7b4-20a07289fc47 · outbound

This paper cites A large-scale car dataset for fine-grained categorization and verification.

Illuminating Visual Identity in Universal Multimodal Embeddings A large-scale car dataset for fine-grained categorization and verification

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:19.229304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e90943c0-354b-48fb-82e6-fcba2ef6a499 · outbound

This paper cites Deep learning for person re- identification: A survey and outlook.IEEE transactions on pattern analysis and machine intelligence, 44(6):2872–2893,.

Illuminating Visual Identity in Universal Multimodal Embeddings Deep learning for person re- identification: A survey and outlook.IEEE transactions on pattern analysis and machine intelligence, 44(6):2872–2893,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:19.085925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7cd99d99-95d9-4e89-a6ef-3f036daaf510 · outbound

This paper cites Learning Face Representation from Scratch.

Illuminating Visual Identity in Universal Multimodal Embeddings Learning Face Representation from Scratch

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.348652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac953921-ea05-4cee-a1ac-eed9274e9d03 · outbound

This paper cites The met dataset: Instance-level recognition for artworks.

Illuminating Visual Identity in Universal Multimodal Embeddings The met dataset: Instance-level recognition for artworks

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.941829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2bd6fb3a-74be-4cc9-a278-c3e40dd7f15b · outbound

This paper cites Towards universal image embed- dings: A large-scale dataset and challenge for generic image representations.

Illuminating Visual Identity in Universal Multimodal Embeddings Towards universal image embed- dings: A large-scale dataset and challenge for generic image representations

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.824469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9cbd0a3e-e878-45fd-857a-ffbc63cac070 · outbound

This paper cites Udon: Universal dynamic online distilla- tion for generic image representations.Advances in Neural Information Processing Systems, 37:86836–86859, 2024.

Illuminating Visual Identity in Universal Multimodal Embeddings Udon: Universal dynamic online distilla- tion for generic image representations.Advances in Neural Information Processing Systems, 37:86836–86859, 2024

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.694822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 931fdf07-6b8d-4b55-98f8-1f24ea3029e9 · outbound

This paper cites CoCa: Contrastive Captioners are Image-Text Foundation Models.

Illuminating Visual Identity in Universal Multimodal Embeddings CoCa: Contrastive Captioners are Image-Text Foundation Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.360998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8178b8ee-26cc-4913-9162-c5f2d8ad71e5 · outbound

This paper cites VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents.

Illuminating Visual Identity in Universal Multimodal Embeddings VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.364610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c629151-d8cf-4adc-8784-379eba4fed65 · outbound

This paper cites Identity- preserving text-to-video generation by frequency decompo- sition.

Illuminating Visual Identity in Universal Multimodal Embeddings Identity- preserving text-to-video generation by frequency decompo- sition

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.558554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 40690f5a-428d-4b23-8919-477e13ee1eb5 · outbound

This paper cites Sigmoid loss for language image pre-training.

Illuminating Visual Identity in Universal Multimodal Embeddings Sigmoid loss for language image pre-training

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.370533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b18f833e-7fe4-4b36-9661-ab9b29429545 · outbound

This paper cites Prod- uct1m: Towards weakly supervised instance-level product retrieval via cross-modal pretraining.

Illuminating Visual Identity in Universal Multimodal Embeddings Prod- uct1m: Towards weakly supervised instance-level product retrieval via cross-modal pretraining

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.413590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5fd02a67-b5ed-461a-99b7-0bc1bf3d7fdd · outbound

This paper cites MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions.

Illuminating Visual Identity in Universal Multimodal Embeddings MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.376305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fd7f93b-194a-406e-b802-404beba054a2 · outbound

This paper cites Assess- ing and learning alignment of unimodal vision and language models.

Illuminating Visual Identity in Universal Multimodal Embeddings Assess- ing and learning alignment of unimodal vision and language models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.379454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dde37f5-d3b3-4440-9a43-fc552cb4ac59 · outbound

This paper cites Beyond frontal faces: Improving per- son recognition using multiple cues.

Illuminating Visual Identity in Universal Multimodal Embeddings Beyond frontal faces: Improving per- son recognition using multiple cues

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.275526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a68bac3d-d1c0-410e-b9bb-f932ca113872 · outbound

This paper cites GME: Improving Universal Multimodal Retrieval by Multimodal LLMs.

Illuminating Visual Identity in Universal Multimodal Embeddings GME: Improving Universal Multimodal Retrieval by Multimodal LLMs

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.485401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ea36a60-e6aa-4864-a5f7-160629ce6583 · outbound

This paper cites Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models.

Illuminating Visual Identity in Universal Multimodal Embeddings Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-04T20:43:17.489048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e18f69cb-8fdc-4673-917f-1354f340451b · outbound

This paper cites Magicmirror: Id-preserved video generation in video diffusion transformers.

Illuminating Visual Identity in Universal Multimodal Embeddings Magicmirror: Id-preserved video generation in video diffusion transformers

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.119414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0d85fe8b-7bc2-406a-87ae-95816f61eebe · outbound

This paper cites Scalable person re-identification: A benchmark.

Illuminating Visual Identity in Universal Multimodal Embeddings Scalable person re-identification: A benchmark

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.035923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation da79ef23-b212-4b4f-999e-de3b37100501 · outbound

This paper cites Scalable person re-identification: A benchmark.

Illuminating Visual Identity in Universal Multimodal Embeddings Scalable person re-identification: A benchmark

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:18.010772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 10ef6a1b-c816-419f-b476-c14682660d44 · outbound

This paper cites Cartoon face recognition: A bench- mark dataset.

Illuminating Visual Identity in Universal Multimodal Embeddings Cartoon face recognition: A bench- mark dataset

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:17.983167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 47e166c9-8827-4454-9a0a-97499ad8221c · outbound

This paper cites Megapairs: Massive data synthesis for universal multi- modal retrieval.

Illuminating Visual Identity in Universal Multimodal Embeddings Megapairs: Massive data synthesis for universal multi- modal retrieval

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T20:43:17.963805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7f78a490-0d0c-41d6-bd8c-2321a9113e37 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

Illuminating Visual Identity in Universal Multimodal Embeddings InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 89

Resolution: malformed identifier; no resolver link, observed 2026-08-04T20:43:17.507439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers