Paper Citation Record · LEDGER

MAny: Merge Anything for Multimodal Continual Instruction Tuning

As of 28 July 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2604.14016.

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

pith.paper-citation-record.v1
2604.14016 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T13:55:28.165204Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-28T06:31:03.373048+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

20 of 20 outbound references displayed

verified exact14
verified fuzzy3
unresolved0
parse uncertain0
malformed identifier2
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5c7f77ff-ce6b-46f1-bf00-a219b7ec0e7d · outbound

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

MAny: Merge Anything for Multimodal Continual Instruction Tuning Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-10T14:00:29.561819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 275646f7-ca68-4846-8f34-63658e36152a · outbound

This paper cites Less confidence, less forgetting: Learning with a humbler teacher in exemplar-free class- incremental learning.Neural Networks, 179:106513, 2024a.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Less confidence, less forgetting: Learning with a humbler teacher in exemplar-free class- incremental learning.Neural Networks, 179:106513, 2024a

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.541841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 36aa5c4e-e506-48ee-aedb-a63dd87365b1 · outbound

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

MAny: Merge Anything for Multimodal Continual Instruction Tuning PathVQA: 30000+ Questions for Medical Visual Question Answering

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:14:19.084463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 0fc3d18f-7015-469b-956c-8b50d67cac58 · outbound

This paper cites Editing Models with Task Arithmetic.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Editing Models with Task Arithmetic

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-13T08:09:13.515542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 29d3f563-2bd4-4c99-993b-0bc71b21af61 · outbound

This paper cites Dataless Knowledge Fusion by Merging Weights of Language Models.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Dataless Knowledge Fusion by Merging Weights of Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.580560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 10aff106-e66e-4979-984b-852330a11a9d · outbound

This paper cites Oasis: Online sample selection for continual visual instruction tuning.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Oasis: Online sample selection for continual visual instruction tuning

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.552133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation e173f440-0352-4b12-9057-3066b03bb133 · outbound

This paper cites Multimodal continual instruction tuning with dynamic gradient guidance.arXiv preprint arXiv:2511.15164.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Multimodal continual instruction tuning with dynamic gradient guidance.arXiv preprint arXiv:2511.15164

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.557088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation c6f7b924-964b-4b6d-928c-f54dc5d0333c · outbound

This paper cites CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning.

MAny: Merge Anything for Multimodal Continual Instruction Tuning CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.531333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 09bf74f3-f314-4858-96c4-79b0e6080f01 · outbound

This paper cites Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T00:02:52.610735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 99a75181-e4b7-45c0-bf8d-304883aded0d · outbound

This paper cites IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning.

MAny: Merge Anything for Multimodal Continual Instruction Tuning IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.586555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 038c60c5-6268-4778-ad2c-e05514b2c45f · outbound

This paper cites CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging.

MAny: Merge Anything for Multimodal Continual Instruction Tuning CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.571356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 9b52cb3e-5e18-4605-bc7d-297fea23bfba · outbound

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

MAny: Merge Anything for Multimodal Continual Instruction Tuning LLaMA: Open and Efficient Foundation Language Models

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-10T14:00:29.575685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 056cc5fe-642b-43bd-aec9-82367a3c3def · outbound

This paper cites FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis.

MAny: Merge Anything for Multimodal Continual Instruction Tuning FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.566704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 37fcb617-94c0-4ec1-b9b2-165aecb4802c · outbound

This paper cites Progressive lora for multimodal continual instruction tuning.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Progressive lora for multimodal continual instruction tuning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T20:12:51.324603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation fd228553-dd43-4912-bb7b-e7b2204e2a89 · outbound

This paper cites Modalprompt: Towards efficient multimodal continual instruction tuning with dual-modality guided prompt.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Modalprompt: Towards efficient multimodal continual instruction tuning with dual-modality guided prompt

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T20:12:51.328062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 89ff5b68-2c8e-4f14-a36a-240ff5619c85 · outbound

This paper cites L} 3:fort= 1tondo 4:1.

MAny: Merge Anything for Multimodal Continual Instruction Tuning L} 3:fort= 1tondo 4:1

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T20:12:51.331119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 9f7c570d-7159-40b2-b381-bfc99ba444bd · outbound

This paper cites LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention.

MAny: Merge Anything for Multimodal Continual Instruction Tuning LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.525179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 2c1a13ac-7dc2-4cb2-921e-0df7296c2dfd · outbound

This paper cites Mllm-cl: Continual learning for multimodal large language models.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Mllm-cl: Continual learning for multimodal large language models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.515311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation d92c4ec9-62a8-4c4c-9959-3650f4eff597 · outbound

This paper cites an unresolved cited work.

MAny: Merge Anything for Multimodal Continual Instruction Tuning Unresolved cited work

Reference 19

Resolution: malformed identifier; arxiv_id, observed 2026-05-10T14:00:29.520062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Observation 5a9a1234-8374-4fbd-a31d-b40f12be360c · outbound

This paper cites On the MLLM-DCL benchmark, the batch size is reduced to 8, with learning rates of 2e-5 for LLaV A and 1e-4 for InternVL.

MAny: Merge Anything for Multimodal Continual Instruction Tuning On the MLLM-DCL benchmark, the batch size is reduced to 8, with learning rates of 2e-5 for LLaV A and 1e-4 for InternVL

Reference 20

Resolution: malformed identifier; arxiv_id, observed 2026-05-10T14:00:29.510283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-28T06:31:03.373048+00:00.

Pith citing papers

No inbound Pith citation observations are available.