ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads | Paper Citation Record

Observation 3259072f-c0c8-465c-8dad-8d1ea6d68f7c · outbound

This paper cites Attention attention everywhere: Monocular depth prediction with skip attention.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Attention attention everywhere: Monocular depth prediction with skip attention

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:25.503220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a6dff74-e5a1-4030-bc6e-f33e08baecd7 · outbound

This paper cites Self-supervised learning from images with a joint-embedding predictive architecture.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Self-supervised learning from images with a joint-embedding predictive architecture

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:25.562474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e73c98c1-debc-4e24-b8ee-4e211477e1ae · outbound

This paper cites Foundational Models Defining a New Era in Vision: A Survey and Outlook.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Foundational Models Defining a New Era in Vision: A Survey and Outlook

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:25.650110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ba129c2-f5bd-4a00-9077-29881ed2d33c · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:25.727381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b5833a3-8193-4182-a5db-69f97e246698 · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Beit: Bert pre-training of image transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:25.804823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dc0cbb8-fa7a-487f-899f-9edc42513260 · outbound

This paper cites Adabins: Depth estimation using adaptive bins.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Adabins: Depth estimation using adaptive bins

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:25.877859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 015458de-a05f-44a2-b47e-cb13db6d2f52 · outbound

This paper cites Language Models are Few-Shot Learners.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Language Models are Few-Shot Learners

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:25.951784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c79ea6be-af6d-4428-ae06-59686630daef · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Emerg- ing properties in self-supervised vision transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.014027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1cfa443-a58f-4865-9e6e-c8e2b946b5b0 · outbound

This paper cites MMDetection: Open MMLab Detection Toolbox and Benchmark.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads MMDetection: Open MMLab Detection Toolbox and Benchmark

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.091367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ae5764e-d0bb-4e12-88dd-7b3ebd393ebb · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.157579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41a51fa6-5d03-4d66-a720-74aeed9eb11b · outbound

This paper cites Mixformer: Mixing features across windows and dimensions.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Mixformer: Mixing features across windows and dimensions

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.216007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1627e6d-8d87-4f4f-b0a3-da425aa2dc82 · outbound

This paper cites Adaptformer: Adapt- ing vision transformers for scalable visual recognition.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Adaptformer: Adapt- ing vision transformers for scalable visual recognition

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.304768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f29d0633-c3aa-42a1-b7ef-8b85eda17217 · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads A simple framework for contrastive learning of visual representations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.365979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a9c32a1-630e-43b9-80ce-35eefb827812 · outbound

This paper cites Vision transformer adapter for dense predictions.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Vision transformer adapter for dense predictions

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.435734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ec0a4e6-e918-451e-907c-fc9cf16c620e · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.502832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b000884-592d-44fe-8e69-dfa7b8495789 · outbound

This paper cites Masked-attention mask transformer for universal image segmentation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Masked-attention mask transformer for universal image segmentation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.571580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be2d17de-c24f-42a2-8a14-b95afb121481 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.716702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e461f47-cf2c-4408-8883-c89bdcf751d9 · outbound

This paper cites Twins: Revisiting the design of spatial attention in vision transformers.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Twins: Revisiting the design of spatial attention in vision transformers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.893912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22d2b970-7161-4f76-a774-3ebcb701146b · outbound

This paper cites Mmsegmentation: Open- mmlab semantic segmentation toolbox and benchmark,.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Mmsegmentation: Open- mmlab semantic segmentation toolbox and benchmark,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:26.953108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ba021c-d6f1-44de-9e27-7679cb9af83c · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads The cityscapes dataset for semantic urban scene understanding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:27.156861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1dfef07-8d21-4eb9-89d1-5487746f385a · outbound

This paper cites Deformable convolutional networks.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Deformable convolutional networks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:27.322128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97a62938-dd01-4df9-9635-99b541c44670 · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Instructblip: Towards general- purpose vision-language models with instruction tuning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:45.255268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b61b55ad-462f-47c2-84d7-a8c558f6347e · outbound

This paper cites Scaling vision transformers to 22 billion pa- rameters.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Scaling vision transformers to 22 billion pa- rameters

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:45.180387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7d531c04-b57e-41e6-bd97-e66b886870ac · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads An image is worth 16x16 words: Trans- formers for image recognition at scale

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:27.826601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2fb3560-fa9d-430a-9bf8-7d30682d6726 · outbound

This paper cites Eva: Exploring the limits of masked visual representa- tion learning at scale.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Eva: Exploring the limits of masked visual representa- tion learning at scale

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:44.959574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e99d77dd-cc26-4d5e-8413-36dbbd58fb33 · outbound

This paper cites Deep ordinal regression net- work for monocular depth estimation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Deep ordinal regression net- work for monocular depth estimation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:44.652414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3fc27194-76cc-4bc4-ba45-1e646738c68a · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:44.431782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a9e5e659-6a19-4b56-947b-115dfb8a7e96 · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Bootstrap your own latent-a new approach to self-supervised learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:28.417640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45015805-4052-4acf-9c11-d527202d93be · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads A survey on self-supervised learning: Algorithms, applications, and future trends

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:44.169139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f47fa069-4e62-48af-a500-1b9cf28921cd · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Vizwiz grand challenge: Answering visual questions from blind people

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:44.132535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7809092b-2956-4525-a06b-6afbddc61f86 · outbound

This paper cites Flatten transformer: Vision transformer using fo- cused linear attention.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Flatten transformer: Vision transformer using fo- cused linear attention

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:43.979734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5edb397e-3521-460d-8699-efba01735197 · outbound

This paper cites Deep residual learning for image recognition.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Deep residual learning for image recognition

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:28.900404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efb7723a-88fc-4cd1-965a-18ab8b0b525c · outbound

This paper cites Mask r-cnn.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Mask r-cnn

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:43.851888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2983936a-1c41-4978-9176-afedc02cfe0d · outbound

This paper cites Momentum contrast for unsupervised visual rep- resentation learning.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Momentum contrast for unsupervised visual rep- resentation learning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:43.704596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1bbbe33b-d901-4c99-aee8-ec89037e9312 · outbound

This paper cites Masked autoencoders are scalable vision learners.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Masked autoencoders are scalable vision learners

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:43.450809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fd28fc32-2224-4c36-85e3-d8335af63ef9 · outbound

This paper cites Lora: Low-rank adaptation of large language models.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Lora: Low-rank adaptation of large language models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:43.236551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b2a137e0-97db-425e-84c9-ef78873510ca · outbound

This paper cites Introducing idefics: An open reproduction of state-of-the-art visual language model.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Introducing idefics: An open reproduction of state-of-the-art visual language model

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:43.026866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 442c063a-cfd3-441f-abc8-4d0d5d5b8b4b · outbound

This paper cites Oneformer: One transformer to rule universal image segmentation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Oneformer: One transformer to rule universal image segmentation

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:42.770096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4b8870aa-0c84-4aab-8234-897454c6b332 · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Scaling up visual and vision-language representation learning with noisy text supervision

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:42.424384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 38f5c9eb-7431-4405-9d1b-6e7d0b2c5bdd · outbound

This paper cites Vi- sual prompt tuning.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Vi- sual prompt tuning

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:42.116748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 967c7d6c-dad3-4300-b192-e839dd0a1f87 · outbound

This paper cites Convolutional Bypasses Are Better Vision Transformer Adapters.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Convolutional Bypasses Are Better Vision Transformer Adapters

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:29.789945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 530a8c4c-5fee-4b4a-b166-753686497d3c · outbound

This paper cites Fact: Factor-tuning for lightweight adaptation on vision transformer.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Fact: Factor-tuning for lightweight adaptation on vision transformer

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:41.890658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6824f71b-b31d-459c-912f-fdc7ad2c62c4 · outbound

This paper cites Segment any- thing.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Segment any- thing

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:41.606310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 38eac8ca-5c8a-400b-bc4a-c0c6258cc369 · outbound

This paper cites Similarity of neural network representa- tions revisited.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Similarity of neural network representa- tions revisited

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:41.308185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7ea0415c-00f6-4ded-b754-5d323829846a · outbound

This paper cites Mask dino: Towards a unified transformer-based framework for object detection and segmentation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Mask dino: Towards a unified transformer-based framework for object detection and segmentation

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:41.037793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 940846d3-e1ca-4e71-87c3-9ec17420200d · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:40.786115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 23514c34-1a8e-4d4a-9c7e-d94883a6abcd · outbound

This paper cites Benchmarking Detection Transfer Learning with Vision Transformers.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Benchmarking Detection Transfer Learning with Vision Transformers

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:29.983561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32c03cab-0be8-4dfe-a5bf-80fc4e7dc4f2 · outbound

This paper cites Exploring plain vision transformer backbones for object de- tection.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Exploring plain vision transformer backbones for object de- tection

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:40.500008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3c753889-975f-4647-b694-b46ae19bb292 · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Evaluating Object Hallucination in Large Vision-Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:30.053409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2bfbacc-3d5b-48d5-a79f-f8303ca9cd2c · outbound

This paper cites Visual Large Language Models for Generalized and Specialized Applications.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Visual Large Language Models for Generalized and Specialized Applications

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:30.084456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aedae50e-d8c5-429c-9a71-1036f9d57010 · outbound

This paper cites Binsformer: Revisiting adaptive bins for monocular depth estimation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Binsformer: Revisiting adaptive bins for monocular depth estimation

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:40.254830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 221cc480-74af-484c-a42a-739ca599f18c · outbound

This paper cites Microsoft coco: Common objects in context.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Microsoft coco: Common objects in context

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:40.127811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 402d1373-bcb3-4db1-be39-1f37bdff4500 · outbound

This paper cites Va-depthnet: A variational approach to single image depth prediction.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Va-depthnet: A variational approach to single image depth prediction

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:40.016625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b768bfb2-ceee-42df-8090-c5d879a4a74d · outbound

This paper cites Improved baselines with visual instruction tuning.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Improved baselines with visual instruction tuning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:39.840043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6edd2ff8-1d5b-47dd-a504-0b6a6778b6a7 · outbound

This paper cites Visual instruction tuning.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Visual instruction tuning

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:39.673372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e7808ca-2b1e-4969-aa9b-c350a195dae5 · outbound

This paper cites Mmbench: Is your multi-modal model an all-around player? In ECCV, pages 216–233, 2024.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Mmbench: Is your multi-modal model an all-around player? In ECCV, pages 216–233, 2024

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:39.540123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1892988f-deeb-4a54-b3c8-3f6bf66b9eb5 · outbound

This paper cites Swin transformer: Hierarchical vision transformer using shifted windows.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Swin transformer: Hierarchical vision transformer using shifted windows

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:39.389456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d909d31e-cc09-41ba-aa0e-caadb06e847b · outbound

This paper cites Swin transformer v2: Scaling up capacity and resolution.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Swin transformer v2: Scaling up capacity and resolution

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:39.235168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6ed1515f-7dfb-427c-ab4c-d713d70df107 · outbound

This paper cites A convnet for the 2020s.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads A convnet for the 2020s

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:30.465268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ce4e11f-e25b-4838-a428-f1eabc752a1f · outbound

This paper cites Decoupled Weight Decay Regularization.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Decoupled Weight Decay Regularization

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:30.511672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6311134e-0259-4838-a3c6-dba2c3df9297 · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:39.109290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e8725e5-96fc-4b70-a576-2f353482bd17 · outbound

This paper cites Time-memory-and parameter-efficient visual adaptation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Time-memory-and parameter-efficient visual adaptation

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:38.957515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3da4c4c1-c22e-4f7e-bf3f-9712bfd7926e · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads The role of context for object detection and se- mantic segmentation in the wild

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:30.668483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768dd031-b549-405a-821a-9093e571fb85 · outbound

This paper cites All in tokens: Uni- fying output space of visual tasks via soft token.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads All in tokens: Uni- fying output space of visual tasks via soft token

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:38.821616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a8e34fd1-ed0c-4efd-9b2b-ac77a0aaffaf · outbound

This paper cites Dinov2: Learning robust visual features without super- vision.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Dinov2: Learning robust visual features without super- vision

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:38.655320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1d470de2-7de9-4c78-931c-8d2c1eddd2f3 · outbound

This paper cites St-adapter: Parameter-efficient image-to-video transfer learning.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads St-adapter: Parameter-efficient image-to-video transfer learning

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:38.525231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eaaad0c8-d6bf-4eb8-8eb3-fd02189d1822 · outbound

This paper cites P3depth: Monocular depth estimation with a piecewise planarity prior.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads P3depth: Monocular depth estimation with a piecewise planarity prior

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:38.412615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7f985a76-b600-400d-92e2-203cf90d4391 · outbound

This paper cites idisc: Internal discretization for monocular depth estimation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads idisc: Internal discretization for monocular depth estimation

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:38.273501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 079de25f-fd81-44e1-b743-8dbb0879aa80 · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Learn- ing transferable visual models from natural language super- vision

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:38.084748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c5e79113-f7c9-476e-9772-452b273caa55 · outbound

This paper cites Do vision trans- formers see like convolutional neural networks? NeurIPS, 34:12116–12128, 2021.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Do vision trans- formers see like convolutional neural networks? NeurIPS, 34:12116–12128, 2021

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:37.867793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 34c1f187-4247-4add-8273-8f50d6476cfa · outbound

This paper cites Vi- sion transformers for dense prediction.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Vi- sion transformers for dense prediction

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:37.700892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0f13137d-2af3-4c93-a9ce-fde997b11f10 · outbound

This paper cites Learning multiple visual domains with residual adapters.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Learning multiple visual domains with residual adapters

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:37.533889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9e96e077-9e8c-4457-8363-09a34de5ffa2 · outbound

This paper cites Iebins: Iterative elastic bins for monocular depth estimation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Iebins: Iterative elastic bins for monocular depth estimation

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:37.365669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a70ce1e0-d841-45de-94e2-4d38e66e0718 · outbound

This paper cites Indoor segmentation and support inference from rgbd images.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Indoor segmentation and support inference from rgbd images

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:37.186757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8b5ff976-2a4b-4782-bbcd-1614c3ba9216 · outbound

This paper cites Efficientnet: Rethinking model scaling for convolutional neural networks.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Efficientnet: Rethinking model scaling for convolutional neural networks

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:37.004730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2ae3adb6-4b20-497d-9bf6-907e3b866b5e · outbound

This paper cites Training data-efficient image transformers & distillation through at- tention.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Training data-efficient image transformers & distillation through at- tention

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:36.824104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ebe46b12-e275-45aa-aa67-102b073baf57 · outbound

This paper cites Pvt v2: Improved baselines with pyramid vision transformer.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Pvt v2: Improved baselines with pyramid vision transformer

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:36.645650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0c88edec-f5a5-4c64-b025-35746b277c91 · outbound

This paper cites Internimage: Exploring large-scale vi- sion foundation models with deformable convolutions.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Internimage: Exploring large-scale vi- sion foundation models with deformable convolutions

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:36.458608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 287062d4-a3bf-4e7c-a07b-b40b8cf97fff · outbound

This paper cites Vit-comer: Vision transformer with convolu- tional multi-scale feature interaction for dense predictions.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Vit-comer: Vision transformer with convolu- tional multi-scale feature interaction for dense predictions

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:36.291060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 63817e5e-53f0-4dbe-8191-3fba7dda9178 · outbound

This paper cites Unified perceptual parsing for scene understand- ing.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Unified perceptual parsing for scene understand- ing

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:36.120647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8c4a6ed8-c6a8-4050-b989-c8a690177d4d · outbound

This paper cites Focal Self-attention for Local-Global Interactions in Vision Transformers.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Focal Self-attention for Local-Global Interactions in Vision Transformers

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:31.821493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0ab7dbb-5722-43e5-b715-e735e7f345e9 · outbound

This paper cites Depth anything: Unleashing the power of large-scale unlabeled data.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Depth anything: Unleashing the power of large-scale unlabeled data

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:35.912858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3c4781a8-e821-41d6-b17d-c6366900841e · outbound

This paper cites Visual tuning.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Visual tuning

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:35.783031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ee55490a-26a2-4b93-b9fa-1deade12af1d · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Coca: Contrastive captioners are image-text foundation models

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:35.629902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d3f3e392-39d7-424b-ac60-5e27922ff185 · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:32.186257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 152b1732-5b13-47fc-9073-523dd585f361 · outbound

This paper cites Neural window fully-connected crfs for monocular depth estimation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Neural window fully-connected crfs for monocular depth estimation

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:35.462006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e91391c4-2d1e-4b2f-8e56-80ab8e863f47 · outbound

This paper cites Spanet: Frequency-balancing token mixer using spectral pooling aggregation modulation.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Spanet: Frequency-balancing token mixer using spectral pooling aggregation modulation

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:35.307375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 722a9709-a5b9-4c82-934d-07082b6f963f · outbound

This paper cites Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:35.050142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a97d7428-4760-4ec0-ac4e-0d40505cc666 · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Sigmoid loss for language image pre-training

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:34.856362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f21ecd9-32a9-4f1f-8eda-75b0b2becc75 · outbound

This paper cites Memory efficient transformer adapter for dense pre- dictions.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Memory efficient transformer adapter for dense pre- dictions

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:34.680805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9add61c0-1e67-4eb3-9aac-443fa919854b · outbound

This paper cites A Survey of Large Language Models.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads A Survey of Large Language Models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:32.845078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d4daee-3c0d-4ae2-9304-95c7e4902b2a · outbound

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

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Semantic under- standing of scenes through the ade20k dataset

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:34.418231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 63af6f46-6ab1-4d00-8c30-9cb4d3a1d2cf · outbound

This paper cites A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-07T11:09:33.099450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6730720-017b-4f8a-8bd4-88f3cc8a04c2 · outbound

This paper cites Image bert pre-training with online tokenizer.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Image bert pre-training with online tokenizer

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:34.203844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8f1f3dac-08b2-47be-ac72-112bfc71bfd1 · outbound

This paper cites Conditional prompt learning for vision-language models.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Conditional prompt learning for vision-language models

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:33.984139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d994396c-d3b9-46b3-9c55-d3ef05e317a6 · outbound

This paper cites Learning to prompt for vision-language models.

ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads Learning to prompt for vision-language models

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:09:33.801518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers