COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training | Paper Citation Record

Observation 2acbd428-3830-45fe-93d7-7c9c84b351b5 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.NeurIPS, 2022.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Flamingo: a visual language model for few-shot learning.NeurIPS, 2022

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.432127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1c5260d-c378-44c8-8aab-632a635aa5f4 · outbound

This paper cites Single-stage semantic segmentation from image labels.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Single-stage semantic segmentation from image labels

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.435687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7af55be0-2496-45be-b0f5-91b5cfa3523f · outbound

This paper cites Beit: Bert pre-training of image transformers.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Beit: Bert pre-training of image transformers

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.438584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb619a82-6ccc-4ec8-b9fb-ae8d943b713f · outbound

This paper cites Food-101–mining discriminative components with random forests.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Food-101–mining discriminative components with random forests

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.441778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f0282ec-5e69-4cd3-bb3d-83ea39aee8fd · outbound

This paper cites Coco- stuff: Thing and stuff classes in context.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Coco- stuff: Thing and stuff classes in context

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.444870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb87e830-9a4b-41c8-9b49-5b76c83f38cc · outbound

This paper cites Unsupervised learn- ing of visual features by contrasting cluster assignments.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Unsupervised learn- ing of visual features by contrasting cluster assignments

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.448023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1691d2f1-92b1-4bee-86bb-b7168eef9727 · outbound

This paper cites Emerg- ing properties in self-supervised vision transformers.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Emerg- ing properties in self-supervised vision transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.451411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d626e36a-75bb-4367-adba-49148d239221 · outbound

This paper cites Learn- ing to generate text-grounded mask for open-world semantic segmentation from only image-text pairs.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Learn- ing to generate text-grounded mask for open-world semantic segmentation from only image-text pairs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.454495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 146a3257-d629-41cb-946e-a8dab6caad62 · outbound

This paper cites Conceptual 12m: Pushing web-scale image-text pre- training to recognize long-tail visual concepts.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Conceptual 12m: Pushing web-scale image-text pre- training to recognize long-tail visual concepts

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.457364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af539555-6e7f-4cf7-81ce-21dd28a48688 · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Sharegpt4v: Improving large multi-modal models with better captions

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.460432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05374346-b9bb-4f52-9ec7-07d24727a305 · outbound

This paper cites A simple framework for contrastive learning of visual representations.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training A simple framework for contrastive learning of visual representations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.463365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51cd77d6-93a2-448a-8d1d-57492678cfa7 · outbound

This paper cites Intriguing properties of contrastive losses.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Intriguing properties of contrastive losses

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.466833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c66352b4-f5a5-494d-af9c-d757c89906f0 · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Reproducible scal- ing laws for contrastive language-image learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.469700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac515e9e-1cc8-417a-a635-90ae73bfe593 · outbound

This paper cites Describing textures in the wild.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Describing textures in the wild

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.472620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f047899-dd01-40f4-bd39-2fe402c8ff26 · outbound

This paper cites The cityscapes dataset for semantic urban scene understanding.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training The cityscapes dataset for semantic urban scene understanding

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.475572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d4c787a-b8b4-44b8-98af-ca5352b00144 · outbound

This paper cites Democratizing contrastive language-image pre- training: A clip benchmark of data, model, and supervision.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Democratizing contrastive language-image pre- training: A clip benchmark of data, model, and supervision

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.353984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d92ab704-8f91-40fc-b28e-11168bc64594 · outbound

This paper cites InstructBLIP: Towards general- purpose vision-language models with instruction tuning.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training InstructBLIP: Towards general- purpose vision-language models with instruction tuning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.346004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 65aa734b-2a1e-4806-87c8-a67628a91d5a · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Imagenet: A large-scale hierarchical image database

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.337905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9755562e-6caf-4b31-9f68-4c6310447869 · outbound

This paper cites Redcaps: Web-curated image-text data created by the people, for the people.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Redcaps: Web-curated image-text data created by the people, for the people

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.329703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9fdc2215-99ad-47db-b60b-e55efbff62bb · outbound

This paper cites Bert: Pre-training of deep bidirectional trans- formers for language understanding.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Bert: Pre-training of deep bidirectional trans- formers for language understanding

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.321406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 54b74ef3-05b9-41ce-9a5f-16e5f7372504 · outbound

This paper cites Maskclip: Masked self- distillation advances contrastive language-image pretraining.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Maskclip: Masked self- distillation advances contrastive language-image pretraining

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.313247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1790a824-4b22-4503-b7a3-b9e8bdc441a1 · outbound

This paper cites The pascal visual object classes challenge: A retrospective.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training The pascal visual object classes challenge: A retrospective

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.305043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8b5a8220-4685-42bb-8275-7fb415448414 · outbound

This paper cites Improving clip training with language rewrites.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Improving clip training with language rewrites

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.296907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e5c1d5e0-84cc-4f6e-b252-745503d192ec · outbound

This paper cites Learning gener- ative visual models from few training examples: An incre- mental bayesian approach tested on 101 object categories.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Learning gener- ative visual models from few training examples: An incre- mental bayesian approach tested on 101 object categories

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.288559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b77ac433-95a3-4132-8d29-870e71ba727c · outbound

This paper cites Dat- acomp: In search of the next generation of multimodal datasets.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Dat- acomp: In search of the next generation of multimodal datasets

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.279224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d4242c3e-b862-44ba-a27d-147635fc8e42 · outbound

This paper cites Pyramidclip: Hierarchi- cal feature alignment for vision-language model pretraining.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Pyramidclip: Hierarchi- cal feature alignment for vision-language model pretraining

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.270340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 47fc3fd9-cb86-4b10-ac76-f65eef6c157a · outbound

This paper cites Softclip: Softer cross-modal alignment makes clip stronger.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Softclip: Softer cross-modal alignment makes clip stronger

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.261682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b3efd4d9-4696-45e9-b65c-f24e80455272 · outbound

This paper cites HiCLIP: Contrastive language-image pre- training with hierarchy-aware attention.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training HiCLIP: Contrastive language-image pre- training with hierarchy-aware attention

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.253398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6d451149-5157-482a-ace4-e7c9c3d023d9 · outbound

This paper cites Bootstrap your own latent-a new approach to self-supervised learning.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Bootstrap your own latent-a new approach to self-supervised learning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.245173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0d814104-8839-4172-9320-a1fed898f0ba · outbound

This paper cites A survey on self-supervised learning: Algorithms, applications, and future trends.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training A survey on self-supervised learning: Algorithms, applications, and future trends

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.236823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b0170a05-e30f-49b9-b94e-122ecd1a81d9 · outbound

This paper cites Masked autoencoders are scalable vision learners.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Masked autoencoders are scalable vision learners

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.519556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2335dbc5-f7fe-40a0-a4dd-cca0ff73c0aa · outbound

This paper cites Probing image- language transformers for verb understanding.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Probing image- language transformers for verb understanding

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.223327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5d231367-4c5b-417e-8351-394b21ff393b · outbound

This paper cites Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.213999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ca07a299-f29a-421c-9e43-0a0971ec2ec0 · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.205124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fffa3571-1830-41bf-aa93-51728aa71ca9 · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Scaling up visual and vision-language representation learning with noisy text supervision

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.196645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1aca144b-b25e-4dee-9f8a-40c48c91ee2b · outbound

This paper cites JUWELS Cluster and Booster: Exascale Pathfinder with Modular Supercomputing Architecture at Juelich Supercomputing Centre.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training JUWELS Cluster and Booster: Exascale Pathfinder with Modular Supercomputing Architecture at Juelich Supercomputing Centre

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.188170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 28205008-6967-4e81-aef1-7cb092c5ae7b · outbound

This paper cites Expediting contrastive language-image pretraining via self-distilled encoders.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Expediting contrastive language-image pretraining via self-distilled encoders

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.179877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 40f8976a-0b8f-46b7-9d89-b3f3bced11f2 · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training 3d object representations for fine-grained categorization

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.538549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b4732ce-b8e6-4329-becc-b55ac72e6be0 · outbound

This paper cites Learning multiple layers of features from tiny images.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Learning multiple layers of features from tiny images

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.541200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b85dcf65-9397-4d82-9549-8f34ebb734f1 · outbound

This paper cites Veclip: Improving clip training via visual-enriched captions.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Veclip: Improving clip training via visual-enriched captions

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.162101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7e59a81b-f756-43c3-8aec-400d0b2d4ea2 · outbound

This paper cites Modeling caption diversity in contrastive vision- language pretraining.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Modeling caption diversity in contrastive vision- language pretraining

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.153526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7fd87592-cd6e-4d5e-9886-16ee48c13452 · outbound

This paper cites Uni- clip: Unified framework for contrastive language-image pre- training.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Uni- clip: Unified framework for contrastive language-image pre- training

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.549111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6db64e3b-95be-4353-9b3d-d4b5e785db79 · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.551755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43df981f-28fb-4fa4-8172-f298f464b8fa · outbound

This paper cites Addressing feature suppression in unsupervised visual representations.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Addressing feature suppression in unsupervised visual representations

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.134536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cf4fba8c-a748-4ffe-9b38-93ed858ea971 · outbound

This paper cites Su- pervision exists everywhere: A data efficient contrastive language-image pre-training paradigm.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Su- pervision exists everywhere: A data efficient contrastive language-image pre-training paradigm

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.126074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ee8fa206-f536-4ad2-aaa9-7756346109bf · outbound

This paper cites Evaluating object hallucination in large vision-language models.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Evaluating object hallucination in large vision-language models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.117155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e977972d-a9a7-491c-aa37-5f47d14a930e · outbound

This paper cites Scaling language-image pre-training via masking.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Scaling language-image pre-training via masking

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.563041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 270ad24b-2677-43c9-ab8d-e79c5d77fab9 · outbound

This paper cites Microsoft coco: Common objects in context.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Microsoft coco: Common objects in context

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.104111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 914a2adc-52a7-4af9-9e17-3b34d0f2a532 · outbound

This paper cites Improved baselines with visual instruction tuning.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Improved baselines with visual instruction tuning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.568397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7ae13cc-3bc3-4405-9b80-5b2596a65bac · outbound

This paper cites Visual instruction tuning.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Visual instruction tuning

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.090060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9b2c064d-bf1e-444d-9ba4-aa33aaf72ab8 · outbound

This paper cites MLLMs-Augmented Visual-Language Representation Learning.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training MLLMs-Augmented Visual-Language Representation Learning

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.573702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5896950-44b3-45f2-afbe-4760779e1c28 · outbound

This paper cites Decoupled Weight Decay Regularization.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Decoupled Weight Decay Regularization

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.576976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ef9242d-acb6-4c19-bba0-a6fea2e89433 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.580026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 373a3b4f-5f65-4bc8-adfc-055248b60599 · outbound

This paper cites Fine-Grained Visual Classification of Aircraft.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Fine-Grained Visual Classification of Aircraft

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.582789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3a5c50e-a21e-4dae-a5f6-609b1c42243a · outbound

This paper cites The role of context for object detection and se- mantic segmentation in the wild.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training The role of context for object detection and se- mantic segmentation in the wild

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.075691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0f800bc9-b72f-427b-a897-2cc42c6e7b24 · outbound

This paper cites Slip: Self-supervision meets language-image pre- training.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Slip: Self-supervision meets language-image pre- training

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.066074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2a966b05-2b8d-4cad-9d34-84187d5fb175 · outbound

This paper cites Silc: Improving vision language pretraining with self-distillation.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Silc: Improving vision language pretraining with self-distillation

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.056308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6d879a00-adcf-4924-86b2-9d24fce288ba · outbound

This paper cites Automated flower classification over a large number of classes.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Automated flower classification over a large number of classes

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.047364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0d779462-8cdc-4406-b167-3846f737a30e · outbound

This paper cites Docci: De- scriptions of connected and contrasting images.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Docci: De- scriptions of connected and contrasting images

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.038430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6fed06a7-ab62-4720-9f9a-80f41a01e56b · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Representation Learning with Contrastive Predictive Coding

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.599753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc963c2f-7d71-4e18-b421-44f0cac54772 · outbound

This paper cites Cats and dogs.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Cats and dogs

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.029089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 56516dae-85b5-4fc2-96f8-d28eebef2ac6 · outbound

This paper cites Language models are unsu- pervised multitask learners.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Language models are unsu- pervised multitask learners

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.605473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f7c7423-52ef-4fd7-b347-5671b729535b · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Learn- ing transferable visual models from natural language super- vision

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.014123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3e41a84c-d228-4333-9866-2c8738021ce2 · outbound

This paper cites Can contrastive learning avoid shortcut solutions? NeurIPS, 2021.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Can contrastive learning avoid shortcut solutions? NeurIPS, 2021

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:02.003410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 23470b4c-4ffa-4658-a4ac-1c38628389b6 · outbound

This paper cites Building vision-language models on solid foundations with masked distillation.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Building vision-language models on solid foundations with masked distillation

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.994418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5150e07e-858b-4834-82d4-a874478e2811 · outbound

This paper cites LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.616766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cb4a333-6b53-431b-9cea-627257c7ccfd · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.619938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d10c965-c3a8-47ef-8fb9-e9bad0d5d146 · outbound

This paper cites Conceptual captions: A cleaned, hypernymed, im- age alt-text dataset for automatic image captioning.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Conceptual captions: A cleaned, hypernymed, im- age alt-text dataset for automatic image captioning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.622729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9386d0-38c8-4069-96b9-d70be07cb39c · outbound

This paper cites Towards vqa models that can read.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Towards vqa models that can read

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.625540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c88223e4-099f-478e-afbf-79b9f07c9bf9 · outbound

This paper cites From Pixels to Prose: A Large Dataset of Dense Image Captions.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training From Pixels to Prose: A Large Dataset of Dense Image Captions

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.629788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2089c6b-2dbf-432e-b1e6-afb7b05f77a8 · outbound

This paper cites Feature dropout: Revisiting the role of augmentations in contrastive learning.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Feature dropout: Revisiting the role of augmentations in contrastive learning

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.969736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c7b6a6dc-e200-46fd-a1ff-931d19e6bebc · outbound

This paper cites Yfcc100m: The new data in multimedia research.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Yfcc100m: The new data in multimedia research

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.961726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4880a0f0-34e0-4f3d-85d4-a49d81b36f41 · outbound

This paper cites Winoground: Probing vision and language models for visio- linguistic compositionality.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Winoground: Probing vision and language models for visio- linguistic compositionality

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.953374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3259ba9a-d2b6-4802-b975-1155a34081fd · outbound

This paper cites Eyes wide shut? exploring the visual shortcomings of multimodal llms.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Eyes wide shut? exploring the visual shortcomings of multimodal llms

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.945166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0036db66-678d-4c50-9f3e-36526ca122af · outbound

This paper cites A picture is worth more than 77 text tokens: Evaluating clip- style models on dense captions.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training A picture is worth more than 77 text tokens: Evaluating clip- style models on dense captions

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.936681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2900c910-458d-49d5-b188-0413a190181e · outbound

This paper cites Mobile- clip: Fast image-text models through multi-modal reinforced training.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Mobile- clip: Fast image-text models through multi-modal reinforced training

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.927259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6849a673-9f1b-4338-b2d0-f7d815f05342 · outbound

This paper cites Sclip: Rethinking self-attention for dense vision-language inference.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Sclip: Rethinking self-attention for dense vision-language inference

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.918378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a1d627ca-69a2-4ce2-a4f2-b832652a5576 · outbound

This paper cites Lotlip: Improving language-image pre- training for long text understanding.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Lotlip: Improving language-image pre- training for long text understanding

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.909611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ef549f9d-6e36-4b5f-848d-041213f458dd · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Sun database: Large-scale scene recognition from abbey to zoo

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.900051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 720276a8-722b-40da-b1ec-19d16d439e14 · outbound

This paper cites Demystifying clip data.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Demystifying clip data

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.891558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 84b90c2c-6d4c-426c-bd13-23a655ec38fa · outbound

This paper cites Which features are learnt by con- trastive learning? on the role of simplicity bias in class col- lapse and feature suppression.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Which features are learnt by con- trastive learning? on the role of simplicity bias in class col- lapse and feature suppression

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.882225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3757f023-7e51-4f95-9c2e-f3aaf559ceff · outbound

This paper cites Alip: Adaptive language-image pre-training with synthetic cap- tion.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Alip: Adaptive language-image pre-training with synthetic cap- tion

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-12T00:59:01.664819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2730cf4a-de97-418a-ab08-573ba4d2a5d3 · outbound

This paper cites Filip: Fine-grained interactive language-image pre-training.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Filip: Fine-grained interactive language-image pre-training

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.868632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 01343171-1b51-4250-be3f-a5fbf6dddce0 · outbound

This paper cites From image descriptions to visual denotations: New similarity metrics for semantic inference over event descrip- tions.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training From image descriptions to visual denotations: New similarity metrics for semantic inference over event descrip- tions

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.860321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5beb5583-4a5c-4ff2-beb3-70e86ae85bde · outbound

This paper cites Coca: Contrastive captioners are image-text foundation models.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Coca: Contrastive captioners are image-text foundation models

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.851879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 97cffcac-a975-49b9-9869-0fb1cd7e82b1 · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for ex- pert agi.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for ex- pert agi

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.842833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6f3fa02b-44ab-492e-a293-65fd3b14c078 · outbound

This paper cites When and why vision- language models behave like bags-of-words, and what to do about it? ICLR, 2023.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training When and why vision- language models behave like bags-of-words, and what to do about it? ICLR, 2023

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.833392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c23bf18c-567b-448c-a311-acb698f5eac9 · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Sigmoid loss for language image pre-training

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.824877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2c698dfb-1afa-46f2-88ff-d0bfde6255f5 · outbound

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

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Long-clip: Unlocking the long-text capability of clip

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.815993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ec95625c-92c6-4024-9419-61aac0f964d3 · outbound

This paper cites Learning the unlearned: Mitigating feature suppression in contrastive learning.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Learning the unlearned: Mitigating feature suppression in contrastive learning

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.806542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1ffc3780-82ce-402e-84b0-b1c8857f3bc4 · outbound

This paper cites Dreamlip: Language- image pre-training with long captions.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Dreamlip: Language- image pre-training with long captions

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.797925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f2f462a3-d922-4a66-bd84-0fea60865499 · outbound

This paper cites Semantic under- standing of scenes through the ade20k dataset.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Semantic under- standing of scenes through the ade20k dataset

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.789021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0bf5983b-acfa-47f0-a1fe-d5ee5c46ed42 · outbound

This paper cites Extract free dense labels from clip.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Extract free dense labels from clip

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:59:01.779397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a3912940-b9a1-4d7d-88a2-3b51915297de · outbound

This paper cites Minigpt-4: Enhancing vision-language understanding with advanced large language models.

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training Minigpt-4: Enhancing vision-language understanding with advanced large language models

Reference 94

Resolution: malformed identifier; raw_fallback, observed 2026-08-12T00:59:01.770126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers