Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T12:42:49.344975Z
Paper Citation Record · LEDGER
As of 13 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 4 inbound Pith citation observations for arXiv:2411.17760.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T12:42:49.344975Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-10T17:18:40.043652Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-11T23:08:36.273358Z
41 of 41 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 9664206d-b1d4-4869-8eb1-0818ffc363dc · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Pixtral 12B
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5e3ee981-f43b-485c-9ede-81c4fea061cf · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Understanding Alignment in Multimodal LLMs: A Comprehensive Study
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 17e6d224-bede-4c49-b14f-71b440800297 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75bb9f34-627c-4ae2-815e-6857afc292fa · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d7091b5f-b2e2-45a6-adeb-5ff4feaac8d8 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Enhancing Large Vision Language Models with Self-Training on Image Comprehension
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af9c54af-75df-4baf-a867-4d0c221a1384 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach The Llama 3 Herd of Models
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c0df4a06-4e16-49d9-af38-74f31c16f0d1 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Multi-modal hal- lucination control by visual information grounding
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a6a8cf59-d076-4253-8f86-fb6f5e809efa · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach CLIPScore: A Reference-free Evaluation Metric for Image Captioning
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 372d4f4a-0fa0-4afe-b7ee-558f26b3504b · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Opera: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 33434ecd-d986-47a4-aa56-a16a269641ee · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Mitigating object hal- lucinations in large vision-language models through visual contrastive decoding
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 379e3394-eb4e-4230-89de-79b16e85e071 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Silkie: Preference Distillation for Large Visual Language Models
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fcd3d2ba-a673-4504-9a7c-c4e75ec25384 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2f0b93c8-b5df-4f57-9bc7-14f2f304cf2e · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Improved baselines with visual instruction tuning
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 359f8dce-5ce2-4753-be9e-407e9a530613 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 201c41a6-b09f-4247-875f-d7e42ef98740 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Visual instruction tuning
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fd6427e1-1030-4dc9-bea9-b48249d23e54 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 361d47bc-3e91-40a3-a0fc-e3bf17a30525 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Training language models to follow instructions with human feedback
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fa9b8285-67da-410a-b1cd-18b65fffeb48 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Direct preference optimization: Your language model is secretly a reward model
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a979d35e-c0be-4df4-bd71-34a8209f3ca7 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Object Hallucination in Image Captioning
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 660a6b1d-8f45-4379-a4f5-fc496e0a5cd4 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Aligning Large Multimodal Models with Factually Augmented RLHF
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 021fd46d-24eb-4e5f-abac-454855afb5ad · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach A Survey on Self-Evolution of Large Language Models
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation afac81d5-79f2-44d9-baed-07cc2a12bcca · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Planbench: An extensible benchmark for evaluating large language mod- els on planning and reasoning about change
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b76cbf24-7d04-465b-ad59-d167cca69c75 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation edea6d44-21f1-4b73-93e6-bf0f9cdef135 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach CogVLM: Visual Expert for Pretrained Language Models
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e873e831-6705-4fb1-932d-1d76b66ed484 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional hu- man feedback
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b75e6337-6f51-457c-8ca2-e82c3a73f64d · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a023b58-55ce-49b4-a52a-f0c56adade20 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fedf3290-a067-4888-9074-b4406b4c1ae6 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 88cb4e6c-d4a0-49fd-b3cc-5a46da43d503 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 584df2d3-30ba-4c47-9cc3-f1d50f109cfa · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c3de1e84-38b5-4f68-92d3-cb91b1ff467f · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Unresolved cited work
Reference 31
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8093b29e-f648-4049-a2ae-e032ca3521f3 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach - The salad is correctly noted as being part of the spread, but the caption could be more specific about the contents of the salad
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation f7d23ead-32f6-4401-8886-e3249bd6a60e · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach However, it inaccurately refers to a wine glass; the image shows glasses of what appears to be a juice or iced tea rather than wine glasses
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 4b3f4c28-64c5-45c3-9935-d37023f4c9c1 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach - The mention of a potted plant is inaccurate; while there is foliage in the background, it cannot be clearly identified as a potted plant
Reference 34
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2e97b3bb-d8b5-4eef-bf42-56d7646867ce · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach The scene includes forks but not knives
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation f94029b2-2584-4ce3-a07b-e72cce4a1f55 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Unresolved cited work
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 37d3f887-7c41-4f0b-ba8a-803fc1a0bf16 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Unresolved cited work
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8f869abc-499c-4d5b-b7f1-bf423f33c387 · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Unresolved cited work
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation aedf9a77-1b0b-4dd9-94a4-7e0014abfc5f · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach It connects this diagram to the essay's content, although it does not specify what the diagram illustrates
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 1185ff57-3593-4cce-ae4b-238674a23caf · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Unresolved cited work
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 11ce3f01-c141-48c3-96f2-abd6d739b99f · outbound
Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach Overall, the caption effectively captures the primary elements of the image, including the handwriting, topic, and visual characteristics
Reference 41
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0d0af034-c869-4ba6-b326-848eca0e2cd2 · inbound
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 612bf3fb-f15e-4b05-85a7-cc4a788cbf1d · inbound
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 700e3458-958d-4cc6-9c8f-fd54624f5400 · inbound
Visual Preference Optimization with Rubric Rewards Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6218e471-fbd3-45c2-985f-6b97bc14c7d4 · inbound
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.