Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs | Paper Citation Record

Observation 166a2c47-85ae-4c04-906c-9eee29fe86a9 · outbound

This paper cites Qwen3-VL Technical Report.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Qwen3-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.269672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be59d751-9b27-45f1-93fc-590044a5f705 · outbound

This paper cites Coig-cqia: Quality is all you need for chinese instruction fine-tuning, 2024.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Coig-cqia: Quality is all you need for chinese instruction fine-tuning, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.328330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05d1e918-7453-4f08-aeda-dba483f41331 · outbound

This paper cites Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models.Advances in neural information processing systems, 32, 2019.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models.Advances in neural information processing systems, 32, 2019

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.405091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3a293f-257b-4725-9561-cd6f6ba388f5 · outbound

This paper cites Baai-mtp dataset.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Baai-mtp dataset

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.489896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dccbc202-eb71-431c-a90a-e929ada7b54e · outbound

This paper cites FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.578691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b69c64be-4bfc-4880-8c75-5a0d9ff684d0 · outbound

This paper cites Honeybee: Locality-enhanced projector for multimodal llm.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Honeybee: Locality-enhanced projector for multimodal llm

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.649295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7868e2cf-7529-46d5-b645-eb23bab88664 · outbound

This paper cites Webqa: Multihop and multimodal qa.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Webqa: Multihop and multimodal qa

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.726553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c243006-424a-4db2-b9c6-014a5ba99d4d · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.826332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2335a39d-00c1-49f2-ada7-3d9eccb47a02 · outbound

This paper cites Sharegpt4v: Improving large multi-modal models with better captions.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Sharegpt4v: Improving large multi-modal models with better captions

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:50.986221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acab2e52-707d-4483-a256-c636ab96fd9b · outbound

This paper cites Reproducible scaling laws for contrastive language-image learning.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Reproducible scaling laws for contrastive language-image learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:51.146796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce5ec27-ebf6-4054-8c4b-ab3e8b33442d · outbound

This paper cites Think then embed: Generative context improves multimodal embedding.arXiv preprint arXiv:2510.05014, 2025.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Think then embed: Generative context improves multimodal embedding.arXiv preprint arXiv:2510.05014, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:51.273014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24da3b8c-1f04-49fd-abd6-26b21d0ed7f5 · outbound

This paper cites Visual dialog.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Visual dialog

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:51.393186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3afd858a-3cbb-45c8-9c88-1b34042db5d1 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Imagenet: A large-scale hierarchical image database

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:51.514888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48688fd7-db64-449c-a223-2b57973041c5 · outbound

This paper cites Bert: Pre-training of deep bidi- rectional transformers for language understanding.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Bert: Pre-training of deep bidi- rectional transformers for language understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:51.658647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 179adbdc-b9d6-47a0-a487-8597ebc8b8b6 · outbound

This paper cites Pact: Pruning and clustering-based token reduction for faster visual language models.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Pact: Pruning and clustering-based token reduction for faster visual language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:51.796555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31325f37-7599-413e-91ee-3397c878c3b1 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs An image is worth 16x16 words: Transformers for image recognition at scale

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:51.902230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43981ea6-2a2e-434c-a555-09f7d8b36f02 · outbound

This paper cites The pascal visual object classes challenge: A retrospective.International journal of computer vision, 111(1):98–136, 2015.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs The pascal visual object classes challenge: A retrospective.International journal of computer vision, 111(1):98–136, 2015

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:52.014405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46bf6137-d634-43fd-a7ac-5214bd75eebb · outbound

This paper cites ColPali: Efficient Document Retrieval with Vision Language Models.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs ColPali: Efficient Document Retrieval with Vision Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:52.116209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 183a65f1-5665-498b-9cbf-7a05848fb385 · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:52.280678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36da3974-7e5d-4c11-8b8a-6abe816d0e2d · outbound

This paper cites Vl-clip: Enhancing multimodal recommendations via visual grounding and llm-augmented clip embeddings.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Vl-clip: Enhancing multimodal recommendations via visual grounding and llm-augmented clip embeddings

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:52.411606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae888698-4138-4df4-bfa0-ca4c4b4bc9d8 · outbound

This paper cites Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:52.540683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d04b80f-cadd-4690-bdf0-76de269deeb4 · outbound

This paper cites Breaking the modality barrier: Universal embedding learning with multimodal llms.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Breaking the modality barrier: Universal embedding learning with multimodal llms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:52.677077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09dd4733-71ab-4e64-9960-30af4ee00814 · outbound

This paper cites Unime-v2: Mllm-as-a-judge for universal multimodal embedding learning.AAAI, 2026.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Unime-v2: Mllm-as-a-judge for universal multimodal embedding learning.AAAI, 2026

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:52.837118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa8ff887-223a-4a26-965b-f40dcfcec6f0 · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Vizwiz grand challenge: Answering visual questions from blind people

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:52.965109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82da0299-3d75-4c2d-ab49-b347be8f59b6 · outbound

This paper cites Efficient Multimodal Learning from Data-centric Perspective.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Efficient Multimodal Learning from Data-centric Perspective

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.053118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a5728c-d82b-42ed-b2c6-63046e03b7c3 · outbound

This paper cites The many faces of robustness: A critical analysis of out-of- distribution generalization.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs The many faces of robustness: A critical analysis of out-of- distribution generalization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.141125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d99ed3e6-fe96-4b1b-8de8-809fbf6fa007 · outbound

This paper cites Natural adversarial examples.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Natural adversarial examples

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.211095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d802671-6139-46ae-a30b-c63e2d2b8bd8 · outbound

This paper cites Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality.Advances in neural information processing systems, 36:31096–31116, 2023.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality.Advances in neural information processing systems, 36:31096–31116, 2023

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.278887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91081082-ff54-49d8-b4d1-911425dcc288 · outbound

This paper cites Open-domain visual entity recognition: Towards recognizing millions of wikipedia entities.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Open-domain visual entity recognition: Towards recognizing millions of wikipedia entities

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.357148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfb612ed-935a-4f4b-80d7-b1570230c04f · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.430200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bc95e34-6faa-4aaf-8c14-fbb97c7c3366 · outbound

This paper cites VideoRAG: Retrieval-Augmented Generation over Video Corpus.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs VideoRAG: Retrieval-Augmented Generation over Video Corpus

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.503874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acb3f71a-b666-48ae-aaf1-634564865cbe · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Scaling up visual and vision-language representation learning with noisy text supervision

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.580062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 977c4326-5f16-48ca-b8b6-6358a3d87dcf · outbound

This paper cites Rzenembed: Towards comprehensive multimodal retrieval.CoRR, abs/2510.27350, 2025.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Rzenembed: Towards comprehensive multimodal retrieval.CoRR, abs/2510.27350, 2025

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.640896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9095c6f-3ea3-4a98-b77b-b176b4c5dc82 · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs E5-V: Universal Embeddings with Multimodal Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.698736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f5a73a-ca73-436e-acd4-ea478d6def41 · outbound

This paper cites Vlm2vec: Training vision-language models for massive multimodal embedding tasks.ICLR, 2025.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Vlm2vec: Training vision-language models for massive multimodal embedding tasks.ICLR, 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.795182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25b78c6e-7297-431e-842c-9149d7217160 · outbound

This paper cites Referitgame: Referring to objects in photographs of natural scenes.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Referitgame: Referring to objects in photographs of natural scenes

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.858465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd25e9aa-bbbf-412f-b772-e53181d135bc · outbound

This paper cites The hateful memes challenge: Detecting hate speech in multimodal memes.Advances in neural information processing systems, 33:2611–2624, 2020.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs The hateful memes challenge: Detecting hate speech in multimodal memes.Advances in neural information processing systems, 33:2611–2624, 2020

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.910519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8b59236-ee56-45db-b021-deaa1d229b16 · outbound

This paper cites Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123(1):32–73, 2017.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123(1):32–73, 2017

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:53.976937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ba3d8cc-e5eb-4ab6-b1c9-027339cbd6c6 · outbound

This paper cites an unresolved cited work.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.032303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 213c22ef-aa82-46dd-97b9-45934dc05b11 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Gonzalez, Hao Zhang, and Ion Stoica

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.086589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c4ddbba-ec11-4314-9fdd-3a0ff0b81ff3 · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Llave: Large language and vision embedding models with hardness-weighted contrastive learning.CoRR, abs/2503.04812, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.147896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 929d70e2-7b2a-48cc-a0c1-b4a09760ae73 · outbound

This paper cites Ume-r1: Exploring reasoning-driven generative multimodal embeddings.arXiv preprint arXiv:2511.00405, 2025.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Ume-r1: Exploring reasoning-driven generative multimodal embeddings.arXiv preprint arXiv:2511.00405, 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.207577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a1b7cc-4327-4d06-8e40-7aaa6efa2abc · outbound

This paper cites Building and better understanding vision-language models: insights and future directions.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Building and better understanding vision-language models: insights and future directions

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.248497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8737e8ec-8fc9-461a-97ec-70b28ff7d280 · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs LLaVA-OneVision: Easy Visual Task Transfer

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.294979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28e058cf-59cc-429f-a3e6-6b3e1948a423 · outbound

This paper cites Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.360576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1f1732-8e9b-4c7c-97ae-e17119a92bef · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.428984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f1bd9c3-28b3-4f0a-9308-6f87286f58e3 · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.527590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcfcfc53-0e48-4a26-963a-ef15269b830b · outbound

This paper cites Silkie: Preference Distillation for Large Visual Language Models.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Silkie: Preference Distillation for Large Visual Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.615173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc433143-8e98-4778-8378-95c28f42aceb · outbound

This paper cites Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.697053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f805cdb2-ece6-4b0e-ad8e-6766ace1d552 · outbound

This paper cites Monkey: Image resolution and text label are important things for large multi-modal models.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Monkey: Image resolution and text label are important things for large multi-modal models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.749572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd0e4e57-7762-4cbd-815f-a76f08928956 · outbound

This paper cites MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.793364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c2cb28b-4ad8-41a6-9bed-55a112eca2a0 · outbound

This paper cites Microsoft coco: Common objects in context.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Microsoft coco: Common objects in context

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.860381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9143fca5-9bfc-428a-a83b-e062fc6b8bf0 · outbound

This paper cites Gres: Generalized referring expression segmentation.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Gres: Generalized referring expression segmentation

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.915681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 190b143f-5bb8-4e52-b0fd-96324161291e · outbound

This paper cites Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:54.954439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2de17b5a-c7b5-472b-9aba-918622fe9e6f · outbound

This paper cites Visual news: Benchmark and challenges in news image captioning.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Visual news: Benchmark and challenges in news image captioning

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.043738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f91ffe-ddfb-400a-bc06-bee301d4359a · outbound

This paper cites Improved baselines with visual instruction tuning.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Improved baselines with visual instruction tuning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.111831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f072e3e-75bf-43f4-a3e2-bcaf95f242df · outbound

This paper cites Exploiting transformation invariance and equivariance for self-supervised sound localisation.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Exploiting transformation invariance and equivariance for self-supervised sound localisation

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.197386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c6451b-e443-4568-9f64-85f32a287c39 · outbound

This paper cites Edis: Entity-driven image search over multimodal web content.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Edis: Entity-driven image search over multimodal web content

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.280158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00fcc7cc-c367-458a-93c4-218c97b71f19 · outbound

This paper cites Lamra: Large multimodal model as your advanced retrieval assistant.CVPR, 2024.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Lamra: Large multimodal model as your advanced retrieval assistant.CVPR, 2024

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.374183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a0d4ea-cc76-44ac-9e27-733a7b3bd8cb · outbound

This paper cites Image retrieval on real-life images with pre-trained vision-and-language models.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Image retrieval on real-life images with pre-trained vision-and-language models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.501729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45aa92c-f61c-4a21-931f-c62c279a5b61 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in Neural Information Processing Systems, 35:2507–2521, 2022.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Learn to explain: Multimodal reasoning via thought chains for science question answering.Advances in Neural Information Processing Systems, 35:2507–2521, 2022

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.620998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58ad22d6-b653-4236-9404-83176f58b5ae · outbound

This paper cites Unifying Multimodal Retrieval via Document Screenshot Embedding.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Unifying Multimodal Retrieval via Document Screenshot Embedding

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.730245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b18985b3-4092-4a88-8509-22269840a629 · outbound

This paper cites Visa: Retrieval augmented generation with visual source attribution.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Visa: Retrieval augmented generation with visual source attribution

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.841007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86b9a751-c795-4086-9ac3-21f8e45aeff7 · outbound

This paper cites Mmlongbench-doc: Benchmarking long-context document understanding with visualizations.Advances in Neural Information Processing Systems, 37:95963–96010, 2024.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Mmlongbench-doc: Benchmarking long-context document understanding with visualizations.Advances in Neural Information Processing Systems, 37:95963–96010, 2024

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:55.954787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c34fcdb9-e9d0-496e-b7d3-556391baf8b7 · outbound

This paper cites Vidore benchmark v2: Raising the bar for visual retrieval.arXiv preprint arXiv:2505.17166, 2025.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Vidore benchmark v2: Raising the bar for visual retrieval.arXiv preprint arXiv:2505.17166, 2025

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.034599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7064aa75-1c13-4bb3-b89f-41d8c54ce929 · outbound

This paper cites Generation and comprehension of unambiguous object descriptions.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Generation and comprehension of unambiguous object descriptions

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.106545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8adf7aa-019e-4dbc-b2ac-7fc6aa70587c · outbound

This paper cites Ok-vqa: A visual question answering benchmark requiring external knowledge.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Ok-vqa: A visual question answering benchmark requiring external knowledge

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.179526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3f7e06e-2efe-48a1-8021-d91f584d35a6 · outbound

This paper cites Chartqa: A benchmark for question answering about charts with visual and logical reasoning.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Chartqa: A benchmark for question answering about charts with visual and logical reasoning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.278664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74284f40-3807-4964-9064-ede3c1dffadd · outbound

This paper cites In- fographicvqa.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs In- fographicvqa

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.348173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0468aa6e-2419-4b77-92df-d4c586a2df12 · outbound

This paper cites Docvqa: A dataset for vqa on document images.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Docvqa: A dataset for vqa on document images

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.454771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b9ed98a-34ad-43c7-a485-f8ac7fb784f7 · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.545981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07739cff-4fdd-40ed-a91e-678f06fad60a · outbound

This paper cites Ops-mm-embedding-v1.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Ops-mm-embedding-v1

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.651977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b96811c7-27b7-4610-86cc-2b0c40849d8a · outbound

This paper cites Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.773017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c18fb213-721c-4e00-80c4-94d9f798838a · outbound

This paper cites Learning transferable visual models from natural language supervision.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Learning transferable visual models from natural language supervision

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.860259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d885533-b961-4aff-ac6c-87c1f239c3c9 · outbound

This paper cites A- okvqa: A benchmark for visual question answering using world knowledge.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs A- okvqa: A benchmark for visual question answering using world knowledge

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:56.955766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 004919ca-0b3c-4749-9a9e-1e8998d48a18 · outbound

This paper cites Objects365: A large-scale, high-quality dataset for object detection.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Objects365: A large-scale, high-quality dataset for object detection

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.082636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aafa2c93-40bf-4735-a64c-b8f7d18dbf5d · outbound

This paper cites Sharegpt-chinese-english-90k: A bilingual chinese-english human-machine dialogue dataset.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Sharegpt-chinese-english-90k: A bilingual chinese-english human-machine dialogue dataset

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.170835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e76efb8-36ed-4ea1-93e3-bfc2a5ee58ce · outbound

This paper cites Towards vqa models that can read.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Towards vqa models that can read

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.249296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24b1a7b5-fabe-48c9-99c0-5ccc3d4e1fe9 · outbound

This paper cites EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.341823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faabcb24-c86a-452e-a640-9a27f8a5cd1d · outbound

This paper cites Breaking the batch barrier (b3) of contrastive learning via smart batch mining.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Breaking the batch barrier (b3) of contrastive learning via smart batch mining

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.407098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fe26576-c358-45b5-a0c1-e3d8593f75b0 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Representation Learning with Contrastive Predictive Coding

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.478991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 596c61a7-975b-44b2-82cc-8b4996b6aef3 · outbound

This paper cites V3det: Vast vocabulary visual detection dataset.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs V3det: Vast vocabulary visual detection dataset

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.579567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 260f681b-8edd-4671-8ead-82b65f1cc844 · outbound

This paper cites To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.669229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abafe370-d164-4aaa-a5ea-aae9a7ffed09 · outbound

This paper cites ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.766049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b61da42-886d-4981-b2b8-e4323a7d785b · outbound

This paper cites N24news: A new dataset for multimodal news classification.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs N24news: A new dataset for multimodal news classification

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.854802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fb1d256-49c1-4dae-a81c-7c91b7fb32d9 · outbound

This paper cites Uniir: Training and benchmarking universal multimodal information retrievers.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Uniir: Training and benchmarking universal multimodal information retrievers

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:57.950522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25b135c0-e703-4dfe-ae65-1a345f848257 · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Fashion iq: A new dataset towards retrieving images by natural language feedback

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.024964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95610b8e-fecd-4fb0-88d1-7d010b0017b9 · outbound

This paper cites Sun database: Large- scale scene recognition from abbey to zoo.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Sun database: Large- scale scene recognition from abbey to zoo

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.105500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e645e263-3f3f-4f85-b91b-a49573b0af2c · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Improve Multi-Modal Embedding Learning via Explicit Hard Negative Gradient Amplifying

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.191649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63a04c57-ea50-4ac5-8c7b-f62b7f439f89 · outbound

This paper cites Topv: Compatible token pruning with inference time optimization for fast and low-memory multimodal vision language model.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Topv: Compatible token pruning with inference time optimization for fast and low-memory multimodal vision language model

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.293990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab8ebf9-b810-4d6a-8d88-74517a54428a · outbound

This paper cites an unresolved cited work.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Unresolved cited work

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.375026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8455edb3-1e95-443d-b124-2f249ab84a32 · outbound

This paper cites Visrag: Vision-based retrieval-augmented generation on multi- modality documents.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Visrag: Vision-based retrieval-augmented generation on multi- modality documents

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.475413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57d57324-eb6c-4f45-af97-3a5a3dadc5b7 · outbound

This paper cites RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.564725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1209586c-cb5d-475d-a83e-68d6e4e3ea33 · outbound

This paper cites Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness.arXiv preprint arXiv:2405.17220, 2024.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness.arXiv preprint arXiv:2405.17220, 2024

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.673363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba776f33-078c-43d5-a1df-22b946cefd29 · outbound

This paper cites When and why vision-language models behave like bags-of-words, and what to do about it?.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.781116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96607e15-d8cb-43f3-a865-9623378023ab · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Sigmoid loss for language image pre- training

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.884879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b079c7f-896a-4618-9d41-70ade8542c72 · outbound

This paper cites Long-clip: Unlocking the long-text capability of clip.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Long-clip: Unlocking the long-text capability of clip

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:58.969922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54fab929-540e-4984-9a36-29b9b97611d0 · outbound

This paper cites Notellm-2: Multimodal large representation models for recommendation.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs Notellm-2: Multimodal large representation models for recommendation

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:59.051193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64dd915b-aee1-431a-aa44-09440a33f759 · outbound

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

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:59.152618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba33d555-e37f-4f04-b8c6-f4f9b1180065 · outbound

This paper cites LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token.

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-03T04:20:59.229137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers