Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs | Paper Citation Record

Observation cf57972b-3253-4d67-8cc2-8dbcf447dd24 · outbound

This paper cites Language models are few-shot learners.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Language models are few-shot learners

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:24.184422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0d832a76-bf8a-4879-b8af-89e85431c105 · outbound

This paper cites In these works, they provided litmus tests for measuring how focused the attention patterns of particular models are and how they relate to model robustness.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs In these works, they provided litmus tests for measuring how focused the attention patterns of particular models are and how they relate to model robustness

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:22.984748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 80bb878e-7eab-488d-bf54-fac98f9d577b · outbound

This paper cites the standard deviation of the accuracy values divided by the number of different seeds.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs the standard deviation of the accuracy values divided by the number of different seeds

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:20.966369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7df17b61-bd53-4908-bfe4-0825ff4c8666 · outbound

This paper cites Frozen Transformers in Language Models Are Effective Visual Encoder Layers.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Frozen Transformers in Language Models Are Effective Visual Encoder Layers

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:17:16.472633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8067ec4b-4bd5-4eab-8942-b273bfb5247d · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:07.140211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0432910-0c1c-432f-b169-d2edd481baa3 · outbound

This paper cites Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:08.054862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6a28afd-2ec9-47d8-a024-7db7890eb3fc · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs DINOv2: Learning Robust Visual Features without Supervision

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:08.132343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5907d37-48d9-4cc7-9e57-bc8d05756ac8 · outbound

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

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Imagenet: A large-scale hierarchical image database

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:08.286198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3724c4e-8c25-47a4-8b1f-0025c935b7d9 · outbound

This paper cites Microsoft coco: Common objects in context.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Microsoft coco: Common objects in context

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:08.730823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb7affd-7b08-4c85-9bcd-6eb3e47e0215 · outbound

This paper cites Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:08.954914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54bfea88-6ae9-486d-80d8-fe4d093f67bc · outbound

This paper cites Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:09.069919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a846dd8-e028-4ee5-ad8d-aa0c10fafebe · outbound

This paper cites Understanding Why Neural Networks Generalize Well Through GSNR of Parameters.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Understanding Why Neural Networks Generalize Well Through GSNR of Parameters

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:09.234749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a964eac8-6510-4018-b4b1-d0208ec5c971 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Distilling the Knowledge in a Neural Network

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:09.364748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1b79421-ce28-4c47-b15b-bc68e211d958 · outbound

This paper cites SOLO: A Single Transformer for Scalable Vision-Language Modeling.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs SOLO: A Single Transformer for Scalable Vision-Language Modeling

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:09.614748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb34fdb-15b0-4387-afd5-973902d3b467 · outbound

This paper cites Layer Normalization.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Layer Normalization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:09.764750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36fc9a21-bae4-4c9b-82ca-5261a805f6d7 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Adam: A Method for Stochastic Optimization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:10.275076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9ac64ec-a47d-4723-b68d-338970fc7d57 · outbound

This paper cites Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:10.544749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 330ec6c4-24c3-4029-9c70-faf41c147242 · outbound

This paper cites Deep networks with stochastic depth.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Deep networks with stochastic depth

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:23.564748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dde40791-2763-47ba-85c7-68ab4f603424 · outbound

This paper cites mixup: Beyond Empirical Risk Minimization.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs mixup: Beyond Empirical Risk Minimization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:10.884728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e882166e-8e34-4822-a2a3-3639df5af93f · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:11.024571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3551f281-1f14-42b8-9919-51b480181047 · outbound

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

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs MMDetection: Open MMLab Detection Toolbox and Benchmark

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:11.224870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea12eca6-b266-45dc-be83-1cae9595b108 · outbound

This paper cites Quantifying the Carbon Emissions of Machine Learning.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Quantifying the Carbon Emissions of Machine Learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:11.392668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa83d959-90c6-4d5a-91d8-f7ecd2af6b26 · outbound

This paper cites Attention Entropies.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Attention Entropies

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:23.194826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fb0eeb87-84ec-4df2-8f9f-f3d8bb842029 · outbound

This paper cites an unresolved cited work.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:17:22.707460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b46e9033-6c7b-4434-83ac-9d401faf3c38 · outbound

This paper cites an unresolved cited work.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:17:22.273985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 23b300f3-d459-43fd-81fd-970983943bcc · outbound

This paper cites Finally, we highlight the high quality of the attention maps of LUViT in the Imagenet-Segmentation dataset [Gao et al., 2022] in Section B.3.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Finally, we highlight the high quality of the attention maps of LUViT in the Imagenet-Segmentation dataset [Gao et al., 2022] in Section B.3

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:21.994766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 308f5b8b-7143-4025-8fdd-d4e5232c97ad · outbound

This paper cites The results of both our reproduction of Pang et al.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs The results of both our reproduction of Pang et al

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:21.721932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2c539026-45a4-408b-8d8f-6f6784ee44f9 · outbound

This paper cites an unresolved cited work.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:17:21.364775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5dc585a5-23fb-4816-8628-515f380fa421 · outbound

This paper cites Each reported value is an average of three training runs with three seeds, (0, 1, 2), and the subscript ± denotes the standard error for each setting.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Each reported value is an average of three training runs with three seeds, (0, 1, 2), and the subscript ± denotes the standard error for each setting

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:20.534750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e26f0bfe-e2bf-4b04-861c-9b75690a5919 · outbound

This paper cites A cell in the downsampled mask is assigned a value of 1 if it overlaps with the original high-resolution mask.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs A cell in the downsampled mask is assigned a value of 1 if it overlaps with the original high-resolution mask

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:20.254747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 839f31c0-7bc6-4924-8a4c-354758aaeef4 · outbound

This paper cites an unresolved cited work.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:17:19.894763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c1b92f23-9be1-49a0-89cd-15577e5ca49c · outbound

This paper cites While LUViT differs from Pang et al.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs While LUViT differs from Pang et al

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:19.505420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation da3ffe0c-fa7e-4a2a-9b93-62a4ef5b3ec6 · outbound

This paper cites The authors quantified this alignment through demonstrating improved gradient-signal-to-noise ratio (GSNR) under the presence of the LLM block.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs The authors quantified this alignment through demonstrating improved gradient-signal-to-noise ratio (GSNR) under the presence of the LLM block

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:19.186193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5de44f84-dac2-4840-ac07-61247b0d0f55 · outbound

This paper cites Following up from this observation and taking inspirations from Tiwari and Shenoy [2023], Bai et al.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Following up from this observation and taking inspirations from Tiwari and Shenoy [2023], Bai et al

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:18.974743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b93c1078-e07f-4bf8-b17e-4ba73ffc0095 · outbound

This paper cites This auxiliary training objective distills the representations of the frozen-LLM-appended ViT to a vanilla ViT through a similarity loss in-between [Hinton et al., 2015].

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs This auxiliary training objective distills the representations of the frozen-LLM-appended ViT to a vanilla ViT through a similarity loss in-between [Hinton et al., 2015]

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:18.727982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d454685a-4cad-4bbe-8758-f8265300bd6a · outbound

This paper cites an unresolved cited work.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:17:17.959249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9fdb8a9a-67fb-40f9-a4c6-fe9a7102f9ac · outbound

This paper cites Notably, we utilize average pooling setting instead of relying on the [CLS] token for performing classification.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Notably, we utilize average pooling setting instead of relying on the [CLS] token for performing classification

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:17.384759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 698b20cc-0325-4398-a81c-e2335a8c7cb1 · outbound

This paper cites an unresolved cited work.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:17:17.103304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc64965e-b720-4e62-8ec6-4f0240a71397 · outbound

This paper cites renditions.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs renditions

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:16.834523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e6e964db-c461-44ad-aad6-b0501c535c97 · outbound

This paper cites Finally, the additional capacity baselines in Section 4 all have additional linear projection layers at the head, analogously with where they are placed in LUViT.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Finally, the additional capacity baselines in Section 4 all have additional linear projection layers at the head, analogously with where they are placed in LUViT

Reference 512

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:17:17.747453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7d8a0460-13f5-4f0f-ae51-22d3e18d2b07 · outbound

This paper cites an unresolved cited work.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Unresolved cited work

Reference 768

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:17:18.423887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 75a915c7-eb95-4384-a911-b85a519eb630 · outbound

This paper cites Benchmarking Neural Network Robustness to Common Corruptions and Perturbations.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:08.425779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 027f2cbc-e45a-4f23-a60b-184b396ade95 · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs BEiT: BERT Pre-Training of Image Transformers

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:07.315858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47bfb469-ff1f-4a19-829b-6e2b16311c60 · outbound

This paper cites Decoupled Weight Decay Regularization.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Decoupled Weight Decay Regularization

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:10.424828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d54a2bed-4601-40be-852d-3d6a8fecd470 · outbound

This paper cites EVEv2: Improved Baselines for Encoder-Free Vision-Language Models.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs EVEv2: Improved Baselines for Encoder-Free Vision-Language Models

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:09.482217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffa1e9e9-f158-4635-8296-6e50ca07ab6e · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:09.984740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d8588d1-12b7-4214-92d8-2a3c65addc25 · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:10.104743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb7e0bc-074e-4c44-b5fc-3728678743ab · outbound

This paper cites Noise or Signal: The Role of Image Backgrounds in Object Recognition.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Noise or Signal: The Role of Image Backgrounds in Object Recognition

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:08.554972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2a04bf1-b2b9-4a7c-9aef-03e91098f537 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs LLaMA: Open and Efficient Foundation Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:06.272206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebad85fb-f08e-4e2c-83cd-bf4aabd2f59e · outbound

This paper cites iBOT: Image BERT Pre-Training with Online Tokenizer.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs iBOT: Image BERT Pre-Training with Online Tokenizer

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:07.479266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8976a14b-d71a-4b71-a24b-64905332c8cf · outbound

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

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:06.519528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c1ae321-34d2-4f7c-8dfb-f4ce852f1aee · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:07.660329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f706a71-111d-4a0b-8e01-496b98b0c5c7 · outbound

This paper cites Vision as LoRA.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Vision as LoRA

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:07.858228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccd954c7-0920-4a4d-97e2-fd6224cf7758 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T21:17:06.711803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d3a361d-a3ff-45e4-8a4f-53d1e34cc2da · outbound

This paper cites an unresolved cited work.

Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Unresolved cited work

Reference 4096

Resolution: unresolved; raw_fallback, observed 2026-08-06T21:17:18.206814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers