Paper Citation Record · LEDGER

Continual Learning in Vision-Language Models via Aligned Model Merging

As of 8 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 6 inbound Pith citation observations for arXiv:2506.03189.

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

pith.paper-citation-record.v1
2506.03189 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:13:44.072901Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T16:19:25.059081Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T14:38:28.618294Z

Reference resolution

22 of 22 outbound references displayed

verified exact2
verified fuzzy7
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4ef75ae6-ac9c-4b8f-ba59-f93575baf2f6 · outbound

This paper cites an unresolved cited work.

Continual Learning in Vision-Language Models via Aligned Model Merging Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:13:46.722563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d49cf55c-dda8-4fe0-b900-f4b74541a716 · outbound

This paper cites Fusing finetuned models for better pretraining.

Continual Learning in Vision-Language Models via Aligned Model Merging Fusing finetuned models for better pretraining

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:42.124288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afb968f0-77ff-4ff8-bb26-af2e3d0b0261 · outbound

This paper cites How to Merge Your Multimodal Models Over Time?.

Continual Learning in Vision-Language Models via Aligned Model Merging How to Merge Your Multimodal Models Over Time?

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:13:44.658600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4101a6c8-5453-44f8-b066-ae04db996fda · outbound

This paper cites Kembhavi, M.

Continual Learning in Vision-Language Models via Aligned Model Merging Kembhavi, M

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:13:46.291282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0d3ca982-d6ef-4874-9269-ad3aebe56ed6 · outbound

This paper cites Learning Attentional Mixture of LoRAs for Language Model Continual Learning.

Continual Learning in Vision-Language Models via Aligned Model Merging Learning Attentional Mixture of LoRAs for Language Model Continual Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:43.137652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4380326-7d8a-488d-8a6c-fefd41b3b9b7 · outbound

This paper cites LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks.

Continual Learning in Vision-Language Models via Aligned Model Merging LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:43.254006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5f8f3f7-5271-491b-9174-f91cfe0675f9 · outbound

This paper cites The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse.

Continual Learning in Vision-Language Models via Aligned Model Merging The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:13:44.334300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f463f304-8578-4c88-a309-10c4972c1fda · outbound

This paper cites an unresolved cited work.

Continual Learning in Vision-Language Models via Aligned Model Merging Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:13:45.687330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f8a668b0-9d71-4fde-8766-903060a4af11 · outbound

This paper cites Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment.

Continual Learning in Vision-Language Models via Aligned Model Merging Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:43.689031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd4a6e48-87b3-483c-b0b7-775d4fc9568c · outbound

This paper cites We used the best hyperparameters reported by Beyer et al.

Continual Learning in Vision-Language Models via Aligned Model Merging We used the best hyperparameters reported by Beyer et al

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:13:45.503630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6fba70f4-e967-47c3-b680-9a3390768025 · outbound

This paper cites Baselines We used a LoRA rank of 32 for all baselines.

Continual Learning in Vision-Language Models via Aligned Model Merging Baselines We used a LoRA rank of 32 for all baselines

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:13:45.331014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 28542678-6e95-4e94-80a8-4911dd39e937 · outbound

This paper cites At each time step, we report the average forgetting on seen tasks so far (lower is better).

Continual Learning in Vision-Language Models via Aligned Model Merging At each time step, we report the average forgetting on seen tasks so far (lower is better)

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:13:45.161725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9994f912-b970-4cd3-bdd1-93d17180029a · outbound

This paper cites In contrast, merging demonstrates greater robustness to these task variations.

Continual Learning in Vision-Language Models via Aligned Model Merging In contrast, merging demonstrates greater robustness to these task variations

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:13:44.927081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5aa130d6-3a08-4964-a631-0b732ee1575a · outbound

This paper cites Soup to go: mitigating forgetting during continual learning with model averaging.

Continual Learning in Vision-Language Models via Aligned Model Merging Soup to go: mitigating forgetting during continual learning with model averaging

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:42.925177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fe3712f-fcfb-429f-a207-fee8c2ba982f · outbound

This paper cites Don’tforget, thereismorethanforgetting: new metrics for continual learning.

Continual Learning in Vision-Language Models via Aligned Model Merging Don’tforget, thereismorethanforgetting: new metrics for continual learning

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:13:46.507830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9175bb53-8694-447a-87aa-e80a26b1b2d9 · outbound

This paper cites Editing Models with Task Arithmetic.

Continual Learning in Vision-Language Models via Aligned Model Merging Editing Models with Task Arithmetic

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:42.567852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18f32e32-86e2-459f-97d7-219fd7d64e2f · outbound

This paper cites On Tiny Episodic Memories in Continual Learning.

Continual Learning in Vision-Language Models via Aligned Model Merging On Tiny Episodic Memories in Continual Learning

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:41.939706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79d3fe60-aae9-4339-8372-9a6011244763 · outbound

This paper cites icarl: Incrementalclassifierandrepresentation learning.

Continual Learning in Vision-Language Models via Aligned Model Merging icarl: Incrementalclassifierandrepresentation learning

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:13:45.874169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5d3df987-0317-48bb-b9f8-4349e98f1c8e · outbound

This paper cites Averaging Weights Leads to Wider Optima and Better Generalization.

Continual Learning in Vision-Language Models via Aligned Model Merging Averaging Weights Leads to Wider Optima and Better Generalization

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:42.702115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f80782f5-82fe-415d-a6af-19b27362809e · outbound

This paper cites an unresolved cited work.

Continual Learning in Vision-Language Models via Aligned Model Merging Unresolved cited work

Reference 2023

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:13:46.071657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0e4d076c-1cde-4c4f-9839-c86e4fd7d445 · outbound

This paper cites an unresolved cited work.

Continual Learning in Vision-Language Models via Aligned Model Merging Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:13:46.905472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e5093490-477b-4a7f-b7f4-8003fd429957 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Continual Learning in Vision-Language Models via Aligned Model Merging BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:42.219343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9f4fa37b-6fc2-4e6c-ac28-0de2d49d3eb6 · inbound

Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks cites this paper.

Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks Continual Learning in Vision-Language Models via Aligned Model Merging

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T11:26:02.204702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a43963e3-ac4d-4175-a0c6-f3ca4611686e · inbound

Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks cites this paper.

Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks Continual Learning in Vision-Language Models via Aligned Model Merging

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T16:19:25.059081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f44fb004-3313-4fb6-a032-aa6675021ae4 · inbound

ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging cites this paper.

ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging Continual Learning in Vision-Language Models via Aligned Model Merging

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:12:18.078464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3699b2d5-7e38-4fc3-8200-0f92c437a7cb · inbound

Amnesia: A Stealthy Replay Attack on Continual Learning Dreams cites this paper.

Amnesia: A Stealthy Replay Attack on Continual Learning Dreams Continual Learning in Vision-Language Models via Aligned Model Merging

Reference 60

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T12:18:06.672725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b76f2e21-89fb-4c48-af4c-2fce9a9d651b · inbound

Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning cites this paper.

Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning Continual Learning in Vision-Language Models via Aligned Model Merging

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-03T14:38:28.619687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 58294f10-753f-46e2-895f-e3ea0d455fe2 · inbound

Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation cites this paper.

Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation Continual Learning in Vision-Language Models via Aligned Model Merging

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T00:57:43.881234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.