Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs | Paper Citation Record

Observation 0398907c-d6d2-47b2-a837-b297d1ec5d04 · outbound

This paper cites Meta-adapters: Parameter ef- ficient few-shot fine-tuning through meta-learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta-adapters: Parameter ef- ficient few-shot fine-tuning through meta-learning

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:04.131906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6d44be06-e06a-4cf7-8e62-654c471a8646 · outbound

This paper cites Meta-learning with differentiable closed-form solvers.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta-learning with differentiable closed-form solvers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.134452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2773f58c-774f-4cf9-913a-1b49a686fb92 · outbound

This paper cites Language models are few-shot learners.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Language models are few-shot learners

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.142979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 759da982-b367-4826-b978-d2bec3875ee3 · outbound

This paper cites Cross-Domain Few-Shot Learning with Meta Fine-Tuning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Cross-Domain Few-Shot Learning with Meta Fine-Tuning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-11T23:49:03.042628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6164bfe4-553e-4a0e-954a-1ee7e3d32d9a · outbound

This paper cites LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.155342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98f0a992-d845-4112-bafd-bc6b50459adb · outbound

This paper cites Meta-learning via language model in-context tuning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta-learning via language model in-context tuning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:04.096899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9c0105b8-6747-40e2-9375-8cb96af366c5 · outbound

This paper cites Scaling Instruction-Finetuned Language Models.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Scaling Instruction-Finetuned Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.167253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6302d483-60fa-4130-8c41-ea088a873d2a · outbound

This paper cites Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.172820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55d85c64-64ef-4bd7-bef9-1f6995a75538 · outbound

This paper cites A Survey on In-context Learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs A Survey on In-context Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.178226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4397f209-fc49-4de8-9e79-5a580d1374fa · outbound

This paper cites Contrastive Model Inversion for Data-Free Knowledge Distillation.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Contrastive Model Inversion for Data-Free Knowledge Distillation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.184624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63bccb93-515f-471f-a58e-0cb33bd1cbfb · outbound

This paper cites Up to 100x faster data- free knowledge distillation.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Up to 100x faster data- free knowledge distillation

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:04.075600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5708a13d-bfd0-4324-b240-d6de891addbe · outbound

This paper cites Context-Aware Meta-Learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Context-Aware Meta-Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.195611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9576cb3c-48e7-493d-b7a8-65e8812bf5b1 · outbound

This paper cites Model- agnostic meta-learning for fast adaptation of deep networks.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Model- agnostic meta-learning for fast adaptation of deep networks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:04.048319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation be3b4612-f74a-4243-ac22-231e943c781b · outbound

This paper cites Styleadv: Meta style adversarial training for cross-domain few-shot learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Styleadv: Meta style adversarial training for cross-domain few-shot learning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:04.028401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e0814a38-e52c-4204-ba05-994e92b0de07 · outbound

This paper cites On the effectiveness of parameter-efficient fine-tuning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs On the effectiveness of parameter-efficient fine-tuning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:04.008522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b20f672c-0898-4b0f-8207-528475496e7d · outbound

This paper cites Clip-adapter: Better vision-language models with feature adapters.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Clip-adapter: Better vision-language models with feature adapters

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.219408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2a36af5-b307-45bf-aba0-ef00fd7bb434 · outbound

This paper cites Know where you’re going: Meta-learning for parameter-efficient fine-tuning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Know where you’re going: Meta-learning for parameter-efficient fine-tuning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.972440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3df9cc27-a4e3-4023-aa38-fa02beff9771 · outbound

This paper cites Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.231977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7376e1aa-cfe5-42e4-9844-59777a4178c4 · outbound

This paper cites A broader study of cross-domain few-shot learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs A broader study of cross-domain few-shot learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.950577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 09762856-406f-42fc-9ed0-c29637a2a080 · outbound

This paper cites Gradvit: 9 Gradient inversion of vision transformers.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Gradvit: 9 Gradient inversion of vision transformers

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.927687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8bb711c1-9f0f-4ea8-8aa8-ee0f09296f97 · outbound

This paper cites Towards a Unified View of Parameter-Efficient Transfer Learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Towards a Unified View of Parameter-Efficient Transfer Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.250584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acd18b08-8764-46a5-8a69-7c68abb8d055 · outbound

This paper cites Towards a unified view of parameter-efficient transfer learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Towards a unified view of parameter-efficient transfer learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.905735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 96f52803-948f-47de-8db4-c5c112cbd286 · outbound

This paper cites Revisiting data-free knowledge distilla- tion with poisoned teachers.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Revisiting data-free knowledge distilla- tion with poisoned teachers

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.881719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation afa819e1-16ab-484d-97a8-9495e1172286 · outbound

This paper cites Meta- learning the difference: preparing large language models for efficient adaptation.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta- learning the difference: preparing large language models for efficient adaptation

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.862353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 43933b22-cd7b-44c2-ad0f-780c6454d2ae · outbound

This paper cites Parameter-efficient transfer learning for nlp.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Parameter-efficient transfer learning for nlp

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.280736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fdfb6b8-2834-4cfa-89ad-e0a1858fcac6 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs LoRA: Low-Rank Adaptation of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.286143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66314701-0626-40e1-a278-d60b7440024f · outbound

This paper cites Pushing the limits of simple pipelines for few-shot learning: External data and fine-tuning make a difference.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Pushing the limits of simple pipelines for few-shot learning: External data and fine-tuning make a difference

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.828602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6c525abc-d9e1-4087-a956-b32cb615b343 · outbound

This paper cites Sparse model inversion: Ef- ficient inversion of vision transformers for data-free appli- cations.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Sparse model inversion: Ef- ficient inversion of vision transformers for data-free appli- cations

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.808035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f48bd6a3-6be4-4a1a-adcc-8369362582ab · outbound

This paper cites Architecture, dataset and model- scale agnostic data-free meta-learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Architecture, dataset and model- scale agnostic data-free meta-learning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.790863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e5538d31-8485-4076-8270-909a6a52e945 · outbound

This paper cites Learning to Learn from APIs: Black-Box Data-Free Meta-Learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Learning to Learn from APIs: Black-Box Data-Free Meta-Learning

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-08-11T23:49:02.811308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 24e5e0b6-0edf-47bb-a3c8-f0b900d38ef1 · outbound

This paper cites LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.313137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67e4d478-98e5-41d8-aa77-99000b29bdc0 · outbound

This paper cites Diversity-aware meta visual prompting.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Diversity-aware meta visual prompting

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.772301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1267bdaa-20b1-4db1-8fa0-010abb1b5c26 · outbound

This paper cites OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.323710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efad1bf9-512b-43ac-8b9e-fd5108628ea6 · outbound

This paper cites Rethinking Efficient Tuning Methods from a Unified Perspective.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Rethinking Efficient Tuning Methods from a Unified Perspective

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-11T23:49:02.733698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6b9c6ca0-ad0e-4ab6-9fb9-66b63f48d5a8 · outbound

This paper cites All tokens matter: Token labeling for training better vision transform- ers.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs All tokens matter: Token labeling for training better vision transform- ers

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.753681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 911b7ce2-6f46-481b-a298-bacb50eb329e · outbound

This paper cites Adaptive gradient-based meta-learning methods.Ad- vances in Neural Information Processing Systems, 32, 2019.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Adaptive gradient-based meta-learning methods.Ad- vances in Neural Information Processing Systems, 32, 2019

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.734959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8e67df79-a96d-4d35-a080-8a84b58376eb · outbound

This paper cites Token fusion: Bridging the gap between token pruning and token merging.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Token fusion: Bridging the gap between token pruning and token merging

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.715201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 000d9fc0-8c14-4581-93b2-57792137d3a6 · outbound

This paper cites Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.354758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4ff5f66-6d52-4bb4-9a2f-7cffd3c661f9 · outbound

This paper cites Surgical fine- tuning improves adaptation to distribution shifts.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Surgical fine- tuning improves adaptation to distribution shifts

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.697646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 92fb4fdd-4403-439c-9dcf-7e3a1cdf0fff · outbound

This paper cites Patch similarity aware data-free quantization for vision transformers.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Patch similarity aware data-free quantization for vision transformers

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.680222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cbe51bc8-866c-48a9-86a5-0bae69b3b300 · outbound

This paper cites Psaq-vit v2: Toward accurate and general data-free quanti- zation for vision transformers.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Psaq-vit v2: Toward accurate and general data-free quanti- zation for vision transformers

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.663624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6740e6a6-3d75-4691-86ac-3f1fdfbe0eca · outbound

This paper cites Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.379022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f8a181a-60c6-49a4-9f42-bea66e05abb9 · outbound

This paper cites Few- shot parameter-efficient fine-tuning is better and cheaper than in-context learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Few- shot parameter-efficient fine-tuning is better and cheaper than in-context learning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.645142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4782d2d7-16ee-4f89-a6d5-b0404f8473c0 · outbound

This paper cites Small scale data-free knowledge distillation.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Small scale data-free knowledge distillation

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.623743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 848cac0e-3ddc-4fb2-9e94-703102b2f999 · outbound

This paper cites Matcher: Segment anything with one shot using all-purpose feature matching.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Matcher: Segment anything with one shot using all-purpose feature matching

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.598581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f2a9e153-e96f-4920-a3a1-a7a2859a8ccb · outbound

This paper cites DFRD: Data-free robustness distillation 10 for heterogeneous federated learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs DFRD: Data-free robustness distillation 10 for heterogeneous federated learning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.578020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6a1ced4e-8f0b-4104-a2f6-673b79bb86a3 · outbound

This paper cites MetaICL: Learning to learn in context.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs MetaICL: Learning to learn in context

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.548306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9644603e-d628-4d48-bc8d-df1f2fa2b869 · outbound

This paper cites Meta learning to bridge vision and language models for mul- timodal few-shot learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta learning to bridge vision and language models for mul- timodal few-shot learning

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.526604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fbdb9dc0-4022-4722-9d0d-45ae88edbebb · outbound

This paper cites On First-Order Meta-Learning Algorithms.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs On First-Order Meta-Learning Algorithms

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.416026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fd652f5-1824-4e59-99e2-37a95c63cc4f · outbound

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

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Automated flower classification over a large number of classes

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.421377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab31a570-5dcb-4296-bb01-b310e905a47d · outbound

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

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Dynamicvit: Efficient vision transformers with dynamic token sparsification

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.426404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4117e486-ab06-4127-984c-14d44cb9c82c · outbound

This paper cites Data-free knowledge distillation for fine-grained visual cat- egorization.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Data-free knowledge distillation for fine-grained visual cat- egorization

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.484986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 812c7cdc-4a7d-41c4-91f0-8ebbdf5eb21e · outbound

This paper cites Prototypical networks for few-shot learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Prototypical networks for few-shot learning

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.467187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e7595bca-dab0-4482-8153-dc3c2735b9fb · outbound

This paper cites Meta-transfer learning for few-shot learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta-transfer learning for few-shot learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.449516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 932ebb3d-8600-4da0-9145-6ca26b92106b · outbound

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

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Training data-efficient image transformers & distillation through at- tention

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.428379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0ad02cc7-945c-473b-b5a7-c5bd2eae24d1 · outbound

This paper cites Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-08-11T23:49:02.625769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8179444d-7cbd-4bc0-82c6-83c2d03e7f37 · outbound

This paper cites Nayer: Noisy layer data generation for efficient and effective data-free knowl- edge distillation.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Nayer: Noisy layer data generation for efficient and effective data-free knowl- edge distillation

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.410579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f8ecaca5-9874-4888-bd03-6e3cda50cc81 · outbound

This paper cites Meta-dataset: A dataset of datasets for learning to learn from few examples.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta-dataset: A dataset of datasets for learning to learn from few examples

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.393273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9001b451-1bdb-4926-9f7a-aa8a3eb9ab29 · outbound

This paper cites Matching networks for one shot learning.Ad- vances in neural information processing systems , 29, 2016.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Matching networks for one shot learning.Ad- vances in neural information processing systems , 29, 2016

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.373994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a388596d-3a7c-42ee-8022-cc48ba878758 · outbound

This paper cites Transformers learn in-context by gradient descent.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Transformers learn in-context by gradient descent

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.355102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9c432c83-e4e3-4eb6-b477-b82667b308b5 · outbound

This paper cites The Caltech-UCSD Birds-200- 2011 Dataset.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs The Caltech-UCSD Birds-200- 2011 Dataset

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.337131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 449d0797-3a36-4462-a80f-d50725ba3ccf · outbound

This paper cites Generalizing to unseen domains: A survey on do- main generalization.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Generalizing to unseen domains: A survey on do- main generalization

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.319922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 33ed02de-3979-495f-8d79-c48f10ee878a · outbound

This paper cites De-confounded data-free knowledge distillation for handling distribution shifts.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs De-confounded data-free knowledge distillation for handling distribution shifts

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.301668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ceaf2101-e809-4f01-a8fe-f897d279ebdf · outbound

This paper cites Meta learning on a sequence of imbalanced domains with difficulty awareness.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta learning on a sequence of imbalanced domains with difficulty awareness

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:02.505639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03601704-7229-410a-a2d2-a4adb1c18feb · outbound

This paper cites Meta-learning without data via wasserstein distributionally- robust model fusion.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta-learning without data via wasserstein distributionally- robust model fusion

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.269704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e69481af-ecd4-4a12-92e8-23b7ca3cbd2a · outbound

This paper cites Task groupings regular- ization: Data-free meta-learning with heterogeneous pre- trained models.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Task groupings regular- ization: Data-free meta-learning with heterogeneous pre- trained models

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.251892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fe82fd05-b513-4d59-8ec0-2b9685999930 · outbound

This paper cites Free: Faster and better data-free meta-learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Free: Faster and better data-free meta-learning

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.232310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1480a2e9-8234-4da5-8788-795281c2a89a · outbound

This paper cites pi-tuning: Transferring multimodal foundation models with optimal multi-task inter- polation.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs pi-tuning: Transferring multimodal foundation models with optimal multi-task inter- polation

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.214334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ff3a4ad4-5a20-4c68-be03-b081ff19249b · outbound

This paper cites Mole: Mixture of lora experts.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Mole: Mixture of lora experts

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.197254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8d6881d8-eebb-41ee-993b-035f8e2254bf · outbound

This paper cites Meta-personalizing vision- language models to find named instances in video.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Meta-personalizing vision- language models to find named instances in video

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.176649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8fee081b-75ed-4feb-9cc7-e8e1ccf8f167 · outbound

This paper cites 11 Dreaming to distill: Data-free knowledge transfer via deep- inversion.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs 11 Dreaming to distill: Data-free knowledge transfer via deep- inversion

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.157971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ba09bb1e-f0a7-450d-8ee7-f58cb2be3da3 · outbound

This paper cites Bayesian model-agnostic meta-learning.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Bayesian model-agnostic meta-learning

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.140780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fb429769-24eb-4211-acad-35c833b74666 · outbound

This paper cites Data-free knowledge distillation via feature exchange and activation region constraint.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Data-free knowledge distillation via feature exchange and activation region constraint

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T23:49:03.119951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8e0c5053-03fe-4f80-be6e-5286445c7357 · outbound

This paper cites recycle in-domain LoRAs.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs recycle in-domain LoRAs

Reference 74

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T23:49:03.099626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8148cc35-cdda-462a-8523-40df5a658ba6 · outbound

This paper cites an unresolved cited work.

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-11T23:49:03.081209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers