Paper Citation Record · LEDGER

LLaVA-c: Continual Improved Visual Instruction Tuning

As of 14 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 9 inbound Pith citation observations for arXiv:2506.08666.

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

pith.paper-citation-record.v1
2506.08666 v2

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:10:48.568952Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:40:25.878281Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T04:27:36.596565Z

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy14
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 918910c0-bb35-481a-a65a-b4783dcc3d2d · outbound

This paper cites Improved baselines with visual instruction tuning.

LLaVA-c: Continual Improved Visual Instruction Tuning Improved baselines with visual instruction tuning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.387226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6650d064-5931-454f-958f-4d22c28aa3b5 · outbound

This paper cites Language models are few-shot learners.

LLaVA-c: Continual Improved Visual Instruction Tuning Language models are few-shot learners

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.392876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbf4840d-5202-40aa-806d-0e12ac51946b · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

LLaVA-c: Continual Improved Visual Instruction Tuning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.397985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dbeaec0-ea49-4770-9cb7-b6310d2ea7ba · outbound

This paper cites Visual instruction tuning.

LLaVA-c: Continual Improved Visual Instruction Tuning Visual instruction tuning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.403574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94a62543-d669-474c-b5e0-fc755d54274f · outbound

This paper cites Learning Transferable Visual Models From Natural Language Supervision.

LLaVA-c: Continual Improved Visual Instruction Tuning Learning Transferable Visual Models From Natural Language Supervision

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.408822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94031e9e-68a1-44ac-b7c7-263ca7fde382 · outbound

This paper cites Overcoming catastrophic forgetting in neural networks.Proceedings of the National Academy of Sciences, 114(13):3521–3526, 2017.

LLaVA-c: Continual Improved Visual Instruction Tuning Overcoming catastrophic forgetting in neural networks.Proceedings of the National Academy of Sciences, 114(13):3521–3526, 2017

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.414095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c157bcf3-e1d7-492c-a561-4f5fd9e61325 · outbound

This paper cites CoIN: A benchmark of continual instruction tuning for multimodel large language models.

LLaVA-c: Continual Improved Visual Instruction Tuning CoIN: A benchmark of continual instruction tuning for multimodel large language models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:49.169605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 98f92714-9f6e-473d-bdbb-0bc793e218a2 · outbound

This paper cites Orthogonal subspace learning for language model continual learning.

LLaVA-c: Continual Improved Visual Instruction Tuning Orthogonal subspace learning for language model continual learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.424011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3f9f4d7-c052-44d1-bb6b-6cb51cb02106 · outbound

This paper cites ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt.

LLaVA-c: Continual Improved Visual Instruction Tuning ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.428757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84a8c427-0c20-4055-8ed9-70c4581620fb · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

LLaVA-c: Continual Improved Visual Instruction Tuning PaLM: Scaling Language Modeling with Pathways

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.433679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20959fb6-6a5b-4938-966b-56cebd8b7c5c · outbound

This paper cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

LLaVA-c: Continual Improved Visual Instruction Tuning BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.439000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 053c828f-402a-4ee7-a797-332b586eb3a7 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

LLaVA-c: Continual Improved Visual Instruction Tuning MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.444403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef89c945-9811-4111-bcbc-231987dbfcfc · outbound

This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.

LLaVA-c: Continual Improved Visual Instruction Tuning InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.449567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3195398-5253-497d-a3c5-705797a42e3e · outbound

This paper cites Flamingo: a Visual Language Model for Few-Shot Learning.

LLaVA-c: Continual Improved Visual Instruction Tuning Flamingo: a Visual Language Model for Few-Shot Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.454540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf9ebd97-1d43-4a05-8f04-92367b71005e · outbound

This paper cites Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering.

LLaVA-c: Continual Improved Visual Instruction Tuning Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T05:10:48.709072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d081e199-2a22-4152-88d1-04b1bfa847e4 · outbound

This paper cites Learning visual n-grams from web data.

LLaVA-c: Continual Improved Visual Instruction Tuning Learning visual n-grams from web data

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:49.136607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3e71fcce-90a6-4474-9b57-62f06d9a5434 · outbound

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

LLaVA-c: Continual Improved Visual Instruction Tuning Podnet: Pooled outputs distillation for small-tasks incremental learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:49.117957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6e29d3ec-3c49-4a68-acc7-7ab8d947ee12 · outbound

This paper cites Learning to prompt for continual learning.

LLaVA-c: Continual Improved Visual Instruction Tuning Learning to prompt for continual learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:49.097712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 38fe239b-bdbc-4a5a-b7b7-a6413d62aaa2 · outbound

This paper cites Codaprompt: Co-designing prompt tuning and architecture for continual learning.

LLaVA-c: Continual Improved Visual Instruction Tuning Codaprompt: Co-designing prompt tuning and architecture for continual learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:49.079368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ad74fb26-7df3-4262-b8ce-542710d660da · outbound

This paper cites Kolesnikov, Georg Sperl, and Christoph H.

LLaVA-c: Continual Improved Visual Instruction Tuning Kolesnikov, Georg Sperl, and Christoph H

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:49.055382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7f3e0243-fec4-41b3-86d8-1336e29a2bff · outbound

This paper cites Wu, Yan-Jia Chen, Lijuan Wang, et al.

LLaVA-c: Continual Improved Visual Instruction Tuning Wu, Yan-Jia Chen, Lijuan Wang, et al

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:49.032309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7e420663-6a65-4a19-94bc-10f983836c93 · outbound

This paper cites R-dfcil: Relation-guided representation learning for data-free class incremental learning.

LLaVA-c: Continual Improved Visual Instruction Tuning R-dfcil: Relation-guided representation learning for data-free class incremental learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:49.014399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2cade2f1-0578-4a2a-9259-3d8b317a042a · outbound

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

LLaVA-c: Continual Improved Visual Instruction Tuning Der: Dynamically expandable representation for class incremental learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.495953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dadac92-a7a2-4ad8-9e4c-1992e04e0b62 · outbound

This paper cites Foster: Feature boosting and compression for class-incremental learning.

LLaVA-c: Continual Improved Visual Instruction Tuning Foster: Feature boosting and compression for class-incremental learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:48.984010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7444cb15-c796-4eb6-b0f0-ac525470e9a9 · outbound

This paper cites Dense network expansion for class incremental learning.

LLaVA-c: Continual Improved Visual Instruction Tuning Dense network expansion for class incremental learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:48.966081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 87967174-5d1d-40e3-a397-a57f8b57c82f · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

LLaVA-c: Continual Improved Visual Instruction Tuning Evaluating Object Hallucination in Large Vision-Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.510487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e8c0299-a2fe-444a-a299-ec5e852282b6 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

LLaVA-c: Continual Improved Visual Instruction Tuning MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.515483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b4d2220-9067-474d-876f-7cdba0da0ae3 · outbound

This paper cites MMBench: Is Your Multi-modal Model an All-around Player?.

LLaVA-c: Continual Improved Visual Instruction Tuning MMBench: Is Your Multi-modal Model an All-around Player?

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.520459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bedf29d-9374-4e2c-a4db-dc56ddc6feaf · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

LLaVA-c: Continual Improved Visual Instruction Tuning SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.525238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07117411-9876-4c2d-b492-65ad7e50d52d · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

LLaVA-c: Continual Improved Visual Instruction Tuning MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.529930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28b42e87-f23b-4352-860b-210c29fc50cd · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.

LLaVA-c: Continual Improved Visual Instruction Tuning Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.534756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44119101-e05a-49bd-8d9d-dc0c0fd78a88 · outbound

This paper cites Super-clevr: A virtual benchmark to diagnose domain robustness in visual reasoning.

LLaVA-c: Continual Improved Visual Instruction Tuning Super-clevr: A virtual benchmark to diagnose domain robustness in visual reasoning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:48.935367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a87b36ef-58eb-41e7-b5e4-677870ced87f · outbound

This paper cites Iconqa: A new benchmark for abstract diagram understanding and visual language reasoning.

LLaVA-c: Continual Improved Visual Instruction Tuning Iconqa: A new benchmark for abstract diagram understanding and visual language reasoning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.545072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406dbe0d-5354-419e-a427-a1f66f65b9b5 · outbound

This paper cites Clevr-math: A dataset for compositional language, visual and mathematical reasoning.

LLaVA-c: Continual Improved Visual Instruction Tuning Clevr-math: A dataset for compositional language, visual and mathematical reasoning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:48.907081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b24d8887-5fbe-44ec-be73-56f573a842e2 · outbound

This paper cites Multimodal ArXiv: A dataset for improving scientific comprehension of large vision-language models.

LLaVA-c: Continual Improved Visual Instruction Tuning Multimodal ArXiv: A dataset for improving scientific comprehension of large vision-language models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:48.890176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e594f537-2f6d-450d-9323-91b309ecba89 · outbound

This paper cites FigureQA: An Annotated Figure Dataset for Visual Reasoning.

LLaVA-c: Continual Improved Visual Instruction Tuning FigureQA: An Annotated Figure Dataset for Visual Reasoning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:48.564186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db99883a-7a5c-44b4-89c6-88cfa7c6816b · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

LLaVA-c: Continual Improved Visual Instruction Tuning Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:10:48.855786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7806090e-84e6-4469-8fa4-f32da693011a · outbound

This paper cites an unresolved cited work.

LLaVA-c: Continual Improved Visual Instruction Tuning Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:10:48.873025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 16477b54-956d-424c-8519-40a0a847c5a5 · inbound

Continual Learning for Generative AI: From LLMs to MLLMs and Beyond cites this paper.

Continual Learning for Generative AI: From LLMs to MLLMs and Beyond LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 132

Resolution: unresolved; no resolver link, observed 2026-08-07T00:40:25.878281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbeedfcf-7e66-4eee-b898-3a076d0788f5 · inbound

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training cites this paper.

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:31:27.352209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 636d4818-203b-4936-9b4c-8c855884d30c · inbound

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World cites this paper.

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-18T04:35:52.485445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1880571f-540e-4767-a529-5fc585ededaf · inbound

SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning cites this paper.

SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T05:33:14.642934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c34a5874-a9a4-43cd-8c09-c1a8815eca19 · inbound

The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models cites this paper.

The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:15:50.030652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 902ecbab-c9c3-4c63-8082-918a84822cd2 · inbound

CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning cites this paper.

CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T23:26:23.210706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aaeed10b-2db5-415b-8842-1d7148317907 · inbound

ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning cites this paper.

ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T22:36:17.979536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0317dca0-2546-4685-9303-259b9aeb5184 · inbound

GUI-AC: Enhancing Continual Learning in GUI Agents cites this paper.

GUI-AC: Enhancing Continual Learning in GUI Agents LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-07-03T04:27:36.598107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 57a3f1d4-6027-409d-a69d-0f7828fe4b78 · inbound

GUI-AC: Enhancing Continual Learning in GUI Agents cites this paper.

GUI-AC: Enhancing Continual Learning in GUI Agents LLaVA-c: Continual Improved Visual Instruction Tuning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-12T14:27:05.589465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.