Paper Citation Record · LEDGER

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models

As of 7 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 3 inbound Pith citation observations for arXiv:2506.07077.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.07077 v1

Coverage vector

measured 71 of 71 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:47:34.282348Z

measured 74 of 74 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T21:14:48.430536Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-02T17:27:14.947625Z

Reference resolution

71 of 71 outbound references displayed

verified exact2
verified fuzzy28
unresolved40
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a9bb2b7d-690a-4b6c-8c4f-83a34c826b36 · outbound

This paper cites Deep learning with differential privacy.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Deep learning with differential privacy

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:28.517772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc731327-723a-40e4-90bb-a44c68cbaf28 · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:28.586725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbe472b5-1225-4b3d-bc10-56e9671d71b3 · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Flamingo: a visual language model for few-shot learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:28.633686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0faa10cf-31c9-4dc5-9209-91548ae0ed9f · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:28.684671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fa7581d-ea78-4d6a-a4bf-ae4df64800c9 · outbound

This paper cites Training with noise is equivalent to tikhonov regularization.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Training with noise is equivalent to tikhonov regularization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:28.779704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f2047cd-9391-405e-a12b-5faab9070547 · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:28.850462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad99cce9-fe23-446f-b2ac-14dbcc911d28 · outbound

This paper cites Instructblip: Towards general-purpose vision-language models with instruction tuning, 2023.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Instructblip: Towards general-purpose vision-language models with instruction tuning, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:28.937160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdf3fb01-e97b-4a8b-841f-59ca5f440c63 · outbound

This paper cites Security and privacy challenges of large language models: A survey.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Security and privacy challenges of large language models: A survey

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.553756Z

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 84350ce8-06bb-48f8-93d9-03147144d33c · outbound

This paper cites Differential privacy.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Differential privacy

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:29.158234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 579d8b04-1225-473d-b669-440588c1b0f3 · outbound

This paper cites The algorithmic foundations of differential privacy.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models The algorithmic foundations of differential privacy

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.528648Z

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 ba73bc6b-a27c-4557-8f46-615cafa236ac · outbound

This paper cites Differentially Private Steering for Large Language Model Alignment.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Differentially Private Steering for Large Language Model Alignment

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:47:35.261379Z

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 65395437-0670-4bca-a9c8-0316afae9457 · outbound

This paper cites Which tokens to use? investigating token reduction in vision transformers.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Which tokens to use? investigating token reduction in vision transformers

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.511851Z

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 566cc5f3-6c34-42e7-ae01-d5c72acc1532 · outbound

This paper cites PathVQA: 30000+ Questions for Medical Visual Question Answering.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models PathVQA: 30000+ Questions for Medical Visual Question Answering

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:29.667469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a968413-87a9-4672-af60-a2682e90566f · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Lora: Low-rank adaptation of large language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:29.778173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb32c6a1-87e3-443c-9f3f-38ba4225d358 · outbound

This paper cites Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:29.878452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df28eeb7-af0f-4ff9-a7dd-f1a00fd1d656 · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:29.949896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf1d460-63e5-40dd-b2af-ecedbab055a3 · outbound

This paper cites End-to-end privacy preserving deep learning on multi-institutional medical imaging.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models End-to-end privacy preserving deep learning on multi-institutional medical imaging

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.475193Z

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 378320bf-f8dc-4ac5-b82d-1f2ef7c8f3f2 · outbound

This paper cites Differentially Private Language Models Benefit from Public Pre-training.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Differentially Private Language Models Benefit from Public Pre-training

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.110883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea46335-f6ac-46c6-826b-7c5fc7d14902 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Adam: A Method for Stochastic Optimization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.206986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 758a44d4-419e-4b49-8e9f-41735cf74084 · outbound

This paper cites Spvit: Enabling faster vision transformers via latency- aware soft token pruning.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Spvit: Enabling faster vision transformers via latency- aware soft token pruning

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.459221Z

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 32a03ccd-4b49-4603-a19b-a56f93f3c00d · outbound

This paper cites A dataset of clinically generated visual questions and answers about radiology images.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models A dataset of clinically generated visual questions and answers about radiology images

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.336425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec59502-7814-4b25-8c17-4c2bfd16c7a9 · outbound

This paper cites Llava-med: Training a large language-and-vision assistant for biomedicine in one day.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Llava-med: Training a large language-and-vision assistant for biomedicine in one day

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.404953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bea30493-c320-4dd2-9826-374a3fc7a60f · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.477101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bb86e9d-62bb-49fc-bc34-853a12dacb3d · outbound

This paper cites Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.547245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 382b8d0a-7c39-420c-bdab-553eb70cf307 · outbound

This paper cites Large Language Models Can Be Strong Differentially Private Learners.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Large Language Models Can Be Strong Differentially Private Learners

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.616876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 576a3d5a-4e3d-452c-9639-62ff25c085ef · outbound

This paper cites Membership inference attacks against large vision-language models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Membership inference attacks against large vision-language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.670329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d42a091e-0dec-4f74-90ca-5d8be6704bf2 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.763753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1e3d07f-04ec-498d-9942-b5481f5b2e23 · outbound

This paper cites Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.826841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43953c4c-3458-409a-8b7c-9d2a32644ecf · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.393248Z

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 103c3e27-f7ef-4b64-bcd5-3c80f5d62aaf · outbound

This paper cites Unveiling a universal relationship between the f(R) parameter and neutron star properties.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Unveiling a universal relationship between the f(R) parameter and neutron star properties

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T05:47:35.003649Z

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 cefdda7f-7b51-4ca3-91ca-b7f7af2f1283 · outbound

This paper cites Learning Differentially Private Recurrent Language Models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Learning Differentially Private Recurrent Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:31.039463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e40e413f-c0aa-41c6-a58c-2f531de2116d · outbound

This paper cites The impact of multimodal large language models on health care’s future.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models The impact of multimodal large language models on health care’s future

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.376981Z

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 6eccc5c5-6f18-49d1-8cc9-ca0bacab1616 · outbound

This paper cites Rényi differential privacy.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Rényi differential privacy

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:31.202224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0e7abcc-0ffd-4f84-8e0b-de79efb054f0 · outbound

This paper cites Regularizing deep neu- ral networks by noise: Its interpretation and optimization.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Regularizing deep neu- ral networks by noise: Its interpretation and optimization

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.359899Z

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 9ad27907-e473-4248-84df-8c6c2cca50a2 · outbound

This paper cites Language models are unsupervised multitask learners.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Language models are unsupervised multitask learners

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:31.355013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a16c27-7510-4c89-8265-700d1539e048 · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Learning transferable visual models from natural language supervision

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:31.417921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3b2b608-a864-48a7-8123-4a574813c17c · outbound

This paper cites Dynamicvit: Efficient vision transformers with dynamic token sparsification.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:31.474290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f09af41f-e664-441e-9def-97d51fca9297 · outbound

This paper cites Seco de Herrera, et al.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Seco de Herrera, et al

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.312518Z

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 32f4e6e6-ece9-42e8-9929-fee91fb03fea · outbound

This paper cites Membership inference attacks against machine learning models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Membership inference attacks against machine learning models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:31.638762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4adc5666-0f86-43f2-a7ff-a0ea23ae2df7 · outbound

This paper cites Towards vqa models that can read.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Towards vqa models that can read

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:31.730216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aec7e3d0-9ed4-4d03-a6d0-ab21969bb975 · outbound

This paper cites Differentially private image classification by learning priors from random processes.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Differentially private image classification by learning priors from random processes

Reference 41

Resolution: verified exact; raw_fallback, observed 2026-08-07T05:47:34.773292Z

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 78c5b743-d256-4814-b1be-04a752662912 · outbound

This paper cites Private Fine-tuning of Large Language Models with Zeroth-order Optimization.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Private Fine-tuning of Large Language Models with Zeroth-order Optimization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:31.952969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be1a816c-192e-4b72-b860-4f4fa2c992ce · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.042603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6000fa5-f4a4-403e-9b46-56ec7bf20067 · outbound

This paper cites FastVLM: Efficient Vision Encoding for Vision Language Models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models FastVLM: Efficient Vision Encoding for Vision Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.126006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7810090-a4c4-418c-bb66-f0d1405eb04d · outbound

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

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.203358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e989ec4-2b16-4122-a1eb-702df63ed0d8 · outbound

This paper cites Cogvlm: Visual expert for pretrained language models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Cogvlm: Visual expert for pretrained language models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.276458Z

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 e373d67e-061c-4794-8c4d-0df6c0f5e0c6 · outbound

This paper cites Joint token pruning and squeezing towards more aggressive compression of vision transformers.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Joint token pruning and squeezing towards more aggressive compression of vision transformers

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.261036Z

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 0c229ab8-67ad-4164-89d4-c22b7b707e97 · outbound

This paper cites Improving differentially-private deep learning with gradients index pruning,.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Improving differentially-private deep learning with gradients index pruning,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.245210Z

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 b9649a70-ea0e-4728-a5d8-fa79fc68f371 · outbound

This paper cites Visionzip: Longer is better but not necessary in vision language models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Visionzip: Longer is better but not necessary in vision language models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.566186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25fa7251-23fe-422d-8680-caf89deb1404 · outbound

This paper cites Differentially Private Fine-tuning of Language Models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Differentially Private Fine-tuning of Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.651397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b266d738-2622-4c8b-ba28-3685a65db844 · outbound

This paper cites Large scale private learning via low-rank reparametrization.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Large scale private learning via low-rank reparametrization

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.215258Z

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 29bc9a3a-8af8-435f-9a57-1517c0775cba · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models OPT: Open Pre-trained Transformer Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.803460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d5db1f-8095-427d-b945-8d6152a1c6f3 · outbound

This paper cites MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.902897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2f6fd31-86bc-41fb-b679-c91f8208a5ab · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Fine-Tuning Language Models from Human Preferences

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:32.960834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e88c0e69-e830-4527-8951-2c1f412f2536 · outbound

This paper cites Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.199352Z

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 fe51645e-5431-47a7-bb65-28c678c203af · outbound

This paper cites Limitations.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Limitations

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.183692Z

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 9b76857f-ce68-412f-8266-3dbffc7f95c9 · outbound

This paper cites • All the theorems, formulas, and proofs in the paper should be numbered and cross- referenced.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models • All the theorems, formulas, and proofs in the paper should be numbered and cross- referenced

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.167606Z

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 2041c9f5-f7fb-4a71-bd4f-ffdc3953d360 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Guidelines: • The answer NA means that the paper does not include experiments

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.151911Z

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 28a40c2c-841f-4f3b-a21b-0b9a0026df12 · outbound

This paper cites Guidelines: • The answer NA means that paper does not include experiments requiring code.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Guidelines: • The answer NA means that paper does not include experiments requiring code

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.136783Z

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 19d0eb18-724b-4487-99b8-7beb427fa779 · outbound

This paper cites • The experimental setting should be presented in the core of the paper to a level of detail that is necessary to appreciate the results and make sense of them.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models • The experimental setting should be presented in the core of the paper to a level of detail that is necessary to appreciate the results and make sense of them

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.119911Z

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 0d7cfbe5-3caa-4cff-8316-7ca5a73b0c6c · outbound

This paper cites Guidelines: • The answer NA means that the paper does not include experiments.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Guidelines: • The answer NA means that the paper does not include experiments

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.105347Z

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 2867b894-b8b7-4a14-957c-b97906cd2a2e · outbound

This paper cites • The paper should indicate the type of compute workers CPU or GPU, internal cluster, or cloud provider, including relevant memory and storage.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models • The paper should indicate the type of compute workers CPU or GPU, internal cluster, or cloud provider, including relevant memory and storage

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.031135Z

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 c9713667-8ea8-4a0c-8c95-3267a41d3d24 · outbound

This paper cites Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:36.775217Z

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 4a236b3b-7372-4c14-948f-ae79215ec0c4 · outbound

This paper cites • If the authors answer NA or No, they should explain why their work has no societal impact or why the paper does not address societal impact.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models • If the authors answer NA or No, they should explain why their work has no societal impact or why the paper does not address societal impact

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:36.512506Z

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 448099dd-b1ff-4bc3-89ab-068fca5ff9b2 · outbound

This paper cites Guidelines: • The answer NA means that the paper poses no such risks.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Guidelines: • The answer NA means that the paper poses no such risks

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:33.875218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bf4c08d-3f3e-44db-a123-f837cf3e7e44 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not use existing assets.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Guidelines: • The answer NA means that the paper does not use existing assets

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:36.155251Z

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 4c380288-8a9b-46ba-a9ad-713424ffdce1 · outbound

This paper cites an unresolved cited work.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:47:35.959418Z

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 3c4bdef4-4f4b-4253-bb4c-27e2a4857bb7 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:35.774144Z

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 6a7035cd-7642-41df-80d1-b8e26c797ec4 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:35.671899Z

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 01785de6-590c-40b1-9a63-a60484acabc8 · outbound

This paper cites 28 Answer: [Yes] Justification: The core methodology of this research is centered on the differential private fine-tuning of Multimodal Large Language Models (MLLMs).

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models 28 Answer: [Yes] Justification: The core methodology of this research is centered on the differential private fine-tuning of Multimodal Large Language Models (MLLMs)

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:35.520788Z

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 ce7c417a-74dc-4cf8-a02f-7e74ee352a08 · outbound

This paper cites net/forum.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models net/forum

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:47:37.229881Z

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.

Pith citing papers

Observation 046a90ea-9531-4b16-94ab-e5f017af8042 · inbound

When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing cites this paper.

When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T17:07:13.125469Z

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 0b22ccf6-4d7c-4e82-8806-24f460a1bfe6 · inbound

Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs cites this paper.

Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-02T17:27:14.949694Z

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 ad8ef6b5-f439-4f8c-ab85-e5b16c72a09a · inbound

PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window cites this paper.

PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T21:14:48.430536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.