Paper Citation Record · LEDGER

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion

As of 10 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2506.09999.

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

pith.paper-citation-record.v1
2506.09999 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T22:11:15.904202Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

40 of 40 outbound references displayed

verified exact1
verified fuzzy23
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5d5b6c48-feb4-4f49-b484-b8bcf7c30ec9 · outbound

This paper cites icarl: Incre- mental classifier and representation learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion icarl: Incre- mental classifier and representation learning,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.367880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ce3c2460-feb3-471b-992f-24f1c691d832 · outbound

This paper cites Expe- rience replay for continual learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Expe- rience replay for continual learning,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.354289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 163bcb0d-15a7-49ae-b0a5-29ca213f37e7 · outbound

This paper cites Gradient Projection Memory for Continual Learning.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Gradient Projection Memory for Continual Learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.762865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 187d60d2-927e-4a20-ac60-d6fbea461ce2 · outbound

This paper cites Continual learning with foundation models: An empirical study of latent replay,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Continual learning with foundation models: An empirical study of latent replay,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.329326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b9753a1f-cb5b-44dd-af4b-c39e6ac2b399 · outbound

This paper cites Learning without forgetting,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Learning without forgetting,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.316160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 794ef0f3-f9e9-4415-af3f-46dcaee10dd4 · outbound

This paper cites Rotate your networks: Better weight consolidation and less catastrophic forgetting,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Rotate your networks: Better weight consolidation and less catastrophic forgetting,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.304176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e6fb5003-b3bf-44f0-9b05-1a821902ddb8 · outbound

This paper cites Continual learning by asymmetric loss approximation with single-side overestimation,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Continual learning by asymmetric loss approximation with single-side overestimation,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.292653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 852e6957-6ae9-43f6-9edf-72f301167457 · outbound

This paper cites Continual learning with extended kronecker-factored approximate curvature,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Continual learning with extended kronecker-factored approximate curvature,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.280053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a5955e6f-d781-4b50-a361-dda3047ba004 · outbound

This paper cites Podnet: Pooled outputs distillation for small-tasks incremental learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Podnet: Pooled outputs distillation for small-tasks incremental learning,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.266198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 63d27a18-4738-4f88-8af9-4c735284e47e · outbound

This paper cites Gdumb: A simple approach that questions our progress in continual learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Gdumb: A simple approach that questions our progress in continual learning,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.340567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7b206c2e-bc28-4d12-af39-b420ad91d269 · outbound

This paper cites Few-shot class-incremental learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Few-shot class-incremental learning,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.254074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1b1d200a-059e-4d11-a238-0e099c432f9a · outbound

This paper cites Der: Dynamically expandable representation for class incremental learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Der: Dynamically expandable representation for class incremental learning,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.797526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94723332-7e4d-452a-b1e9-8d07886ef790 · outbound

This paper cites Dytox: Trans- formers for continual learning with dynamic token expansion,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Dytox: Trans- formers for continual learning with dynamic token expansion,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.234950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 082dedb4-a9be-47b1-91c8-42f71829721b · outbound

This paper cites Dense network ex- pansion for class incremental learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Dense network ex- pansion for class incremental learning,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.222276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 13e0349b-9d07-4a83-8576-f6acb060da2a · outbound

This paper cites Compacter: Efficient low-rank hypercomplex adapter layers,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Compacter: Efficient low-rank hypercomplex adapter layers,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.210060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b6923959-bbad-43dd-973a-d4671905dccc · outbound

This paper cites 1% vs 100%: Parameter-efficient low rank adapter for dense predictions,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion 1% vs 100%: Parameter-efficient low rank adapter for dense predictions,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.198313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2f74ac19-ec8d-431f-8a78-e771515e8bff · outbound

This paper cites A unified continual learning framework with general parameter-efficient tuning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion A unified continual learning framework with general parameter-efficient tuning,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.815132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25e26edc-adce-41cf-8676-b027c37e4555 · outbound

This paper cites Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.818414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7a6c1d4-0441-4273-8e65-d3697c9cb105 · outbound

This paper cites Vmt-adapter: Parameter- efficient transfer learning for multi-task dense scene understanding,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Vmt-adapter: Parameter- efficient transfer learning for multi-task dense scene understanding,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.177115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0bac4473-897d-4842-a849-bb1db245eda5 · outbound

This paper cites Visual prompt tuning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Visual prompt tuning,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.825633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f42beb7-9897-4369-bf2f-ddd2f0e55992 · outbound

This paper cites Learning to prompt for continual learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Learning to prompt for continual learning,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.830095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64adf66c-4b4b-4093-b72d-536d880fd89c · outbound

This paper cites Dualprompt: Complementary prompting for rehearsal-free continual learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Dualprompt: Complementary prompting for rehearsal-free continual learning,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.834090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59232cca-1cbb-43d3-b4a1-e0da85580de1 · outbound

This paper cites Coda-prompt: Contin- ual decomposed attention-based prompting for rehearsal-free continual learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Coda-prompt: Contin- ual decomposed attention-based prompting for rehearsal-free continual learning,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.838103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91ba8720-aa03-4d6e-9b6a-c4c90128cdcf · outbound

This paper cites Don't Stop Learning: Towards Continual Learning for the CLIP Model.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Don't Stop Learning: Towards Continual Learning for the CLIP Model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.841825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d61ab965-f30a-4a50-b925-4fc29d478144 · outbound

This paper cites Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.845746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c73f1fb-7792-47b7-9ef7-c5ad7b79e679 · outbound

This paper cites Boosting continual learning of vision-language models via mixture-of-experts adapters,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Boosting continual learning of vision-language models via mixture-of-experts adapters,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.849972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cca9b97d-0606-4c1a-850d-895990b69af4 · outbound

This paper cites Towards continual egocentric activity recognition: A multi-modal egocentric activity dataset for continual learning,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Towards continual egocentric activity recognition: A multi-modal egocentric activity dataset for continual learning,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.128336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 561204c3-19de-4870-a950-26e107ba30b1 · outbound

This paper cites Vision-sensor attention based continual multimodal egocentric activity recognition,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Vision-sensor attention based continual multimodal egocentric activity recognition,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.117575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 42054f5a-de95-4acb-9eb2-fb40822602c4 · outbound

This paper cites Audioclip: Extending clip to image, text and audio,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Audioclip: Extending clip to image, text and audio,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.106042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bfa46d02-d3e2-44a0-b16b-1b3a64d1cd1c · outbound

This paper cites Mmg-ego4d: Multimodal generalization in egocentric action recognition,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Mmg-ego4d: Multimodal generalization in egocentric action recognition,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.093429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8ff40c8f-aad6-40c4-a2ee-9f416d9d1c1c · outbound

This paper cites A Survey on Mixture of Experts in Large Language Models.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion A Survey on Mixture of Experts in Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.868173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b478311-ff89-44b3-af9c-ea1254535c8e · outbound

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

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion LoRA: Low-Rank Adaptation of Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.872024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20d7cbae-1ff9-4f89-8f7f-04253d02066e · outbound

This paper cites Multilayer perceptron (mlp),.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Multilayer perceptron (mlp),

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.082189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e2d1f87c-22d1-4c56-8751-609fd03a271d · outbound

This paper cites Don't forget, there is more than forgetting: new metrics for Continual Learning.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Don't forget, there is more than forgetting: new metrics for Continual Learning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.879475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4bf2c91-ec3d-4ab5-b348-1aa46c786e7f · outbound

This paper cites ARIC: An Activity Recognition Dataset in Classroom Surveillance Images.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion ARIC: An Activity Recognition Dataset in Classroom Surveillance Images

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-08T22:11:15.961871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f1bea081-834d-46a3-ba0f-3b2c80b4c6f3 · outbound

This paper cites Multimodality helps unimodality: Cross-modal few-shot learning with multimodal models,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Multimodality helps unimodality: Cross-modal few-shot learning with multimodal models,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.071058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cbda5bbf-b709-46b3-8a41-eea00791f0ee · outbound

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

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion An image is worth 16x16 words: Trans- formers for image recognition at scale,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.059484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 13e8b51b-f91e-4464-9e51-66d4fdc1a784 · outbound

This paper cites Esresne(x)t-fbsp: Learning robust time-frequency transformation of audio,.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Esresne(x)t-fbsp: Learning robust time-frequency transformation of audio,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:11:16.048272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1d7a1aa7-f71a-4725-9a5a-881baa3af23d · outbound

This paper cites Decoupled Weight Decay Regularization.

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion Decoupled Weight Decay Regularization

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.900590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfbb0797-5320-4baa-a459-c255cf0b9490 · outbound

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

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T22:11:15.904202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.