Paper Citation Record · LEDGER

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

As of 19 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 4 inbound Pith citation observations for arXiv:2506.19848.

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

pith.paper-citation-record.v1
2506.19848 v1

Coverage vector

measured 70 of 70 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:30:21.640667Z

measured 74 of 74 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:55:50.973218Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T00:10:52.889170Z

Reference resolution

70 of 70 outbound references displayed

verified exact0
verified fuzzy17
unresolved52
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1194e040-1202-4a3b-a3ab-e4493c099e2e · outbound

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

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.346925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd1d742-2250-4161-bcd0-a63d84662a02 · outbound

This paper cites Qwen2.5-VL Technical Report.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.352597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 899d65ea-605f-4324-8dbc-9a462037e244 · outbound

This paper cites Hallucination of Multimodal Large Language Models: A Survey.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Hallucination of Multimodal Large Language Models: A Survey

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.357011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc31f824-cfde-40f6-8a57-3e95bef40b48 · outbound

This paper cites Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.361234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86b0af9f-37cd-4421-80de-f080c3d507a1 · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.365268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ddf7c82-2a1f-4a43-b308-42963a0c94ce · outbound

This paper cites Sharegpt4v: Improving large multi-modal models with better captions.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Sharegpt4v: Improving large multi-modal models with better captions

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.369879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 232bb052-a488-4139-b90a-db696ee72945 · outbound

This paper cites Sharegpt4video: Improving video understanding and generation with better captions.Advances in Neural Information Processing Systems, 37:19472–19495, 2024.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Sharegpt4video: Improving video understanding and generation with better captions.Advances in Neural Information Processing Systems, 37:19472–19495, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.374112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 956d6ff3-2e1c-4782-87d2-19cb45576514 · outbound

This paper cites Open-llava-next: An open-source implementation of llava-next series for facilitat- ing the large multi-modal model community.https://github.com/xiaoachen98/Open-LLaVA-NeXT , 2024.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Open-llava-next: An open-source implementation of llava-next series for facilitat- ing the large multi-modal model community.https://github.com/xiaoachen98/Open-LLaVA-NeXT , 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.464216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f74ad12e-996c-4c0c-932d-f67a3b5dfee8 · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.382358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58999624-24c1-4df0-8a88-88d2e369d97c · outbound

This paper cites Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.386756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14802a9e-513a-4870-bb1c-641c6bef301a · outbound

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

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.391223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb07c46-21a3-4682-9278-b0c890ced8d4 · outbound

This paper cites MM-IFEngine: Towards Multimodal Instruction Following.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing MM-IFEngine: Towards Multimodal Instruction Following

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.395096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba3f5f63-7133-45d7-83aa-f1f0dc1c0b6c · outbound

This paper cites Benchmarking and Improving Detail Image Caption.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Benchmarking and Improving Detail Image Caption

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.398824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfdcdcb9-dde5-4a40-ad37-0f57f8a02c56 · outbound

This paper cites Vlmevalkit: An open-source toolkit for evaluating large multi-modality models.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Vlmevalkit: An open-source toolkit for evaluating large multi-modality models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.402911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 249a3e78-117b-4c22-9298-b07413a8067c · outbound

This paper cites Improving clip training with language rewrites.Advances in Neural Information Processing Systems, 36:35544–35575, 2023.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Improving clip training with language rewrites.Advances in Neural Information Processing Systems, 36:35544–35575, 2023

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.444486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f5509eb8-46c1-446e-bb9a-5d5541675a7b · outbound

This paper cites Eva: Exploring the limits of masked visual representation learning at scale.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Eva: Exploring the limits of masked visual representation learning at scale

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.410549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49a73119-b28f-49ef-af48-e4ad5c1f9b3a · outbound

This paper cites Ic9600: A benchmark dataset for automatic image complexity assessment.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(01):1–17, 2023.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Ic9600: A benchmark dataset for automatic image complexity assessment.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(01):1–17, 2023

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.423241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c9d7b64a-425c-4940-bbed-bff2ab2b7a46 · outbound

This paper cites Imageinwords: Unlocking hyper-detailed image descriptions, 2024.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Imageinwords: Unlocking hyper-detailed image descriptions, 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.410900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dc754695-bbd4-46a3-8f63-b0955ad04015 · outbound

This paper cites The Llama 3 Herd of Models.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing The Llama 3 Herd of Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.421614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95e41511-0bb0-44f7-8dc9-d0b7ee1dc27a · outbound

This paper cites Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.425500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb56781f-ce3b-41b9-8530-dd91f0f952f8 · outbound

This paper cites Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.429233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 538615cf-305a-4137-9b6d-9e3a569fbaa3 · outbound

This paper cites Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.433181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a6508ee-8599-46df-a5e0-f797a2eba695 · outbound

This paper cites Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.437515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a078e7be-9a77-4f55-a236-7c4e43a8ea2f · outbound

This paper cites CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.441372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f031ab7f-1aa4-4258-9539-659958223b2c · outbound

This paper cites Adu: Adaptive detection of unknown categories in black-box domain adaptation.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Adu: Adaptive detection of unknown categories in black-box domain adaptation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.382225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bd2a8f2c-a29f-435e-8031-592e311144f1 · outbound

This paper cites Veclip: Improving clip training via visual-enriched captions.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Veclip: Improving clip training via visual-enriched captions

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.449624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4262ea31-b8cc-42bb-bd54-1ed105f262c9 · outbound

This paper cites LAION-5B: A New Era of Open Large-scale Multimodal Datasets, 2022.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing LAION-5B: A New Era of Open Large-scale Multimodal Datasets, 2022

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.363061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 40d48064-ee00-4ebc-984a-1f07bbe261d6 · outbound

This paper cites Mitigating object hallucinations in large vision-language models through visual contrastive decoding.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Mitigating object hallucinations in large vision-language models through visual contrastive decoding

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.456427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28b79ed9-5551-4b82-b2e8-fd27e63b5c65 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.343134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c4d50d11-d1ff-4973-92ac-d88b9885b378 · outbound

This paper cites DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.464143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1ca1f7c-f38e-4397-a5d0-a0c1492abd04 · outbound

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

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Evaluating Object Hallucination in Large Vision-Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.467770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2a961e1-a5cd-4bdf-86c7-4a305cb9aaf9 · outbound

This paper cites an unresolved cited work.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:30:22.330559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 010ba671-e19f-4418-8be8-493dc8c5cd0e · outbound

This paper cites Grounding 3D Scene Affordance From Egocentric Interactions.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Grounding 3D Scene Affordance From Egocentric Interactions

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.475174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51e84157-12f6-4cc8-883d-8f55af0794ae · outbound

This paper cites Improved baselines with visual instruction tuning.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Improved baselines with visual instruction tuning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.479353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e1eedf8-ceab-4d1a-ab28-8e8c2422557c · outbound

This paper cites Visual Instruction Tuning.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Visual Instruction Tuning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.483286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1edc3c0-1566-4916-8a7b-7a8d2d214b49 · outbound

This paper cites A Survey on Hallucination in Large Vision-Language Models.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing A Survey on Hallucination in Large Vision-Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.487659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff9c46d3-5958-4ca8-bd8c-4c935b12e1bb · outbound

This paper cites Paying more attention to image: A training-free method for alleviating hallucination in lvlms.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Paying more attention to image: A training-free method for alleviating hallucination in lvlms

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.492214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8983ad3d-ffe6-423a-8e4c-056a0479e28c · outbound

This paper cites MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.496411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac6a5000-de90-4487-8fa0-eb6106fd6337 · outbound

This paper cites Visual-RFT: Visual Reinforcement Fine-Tuning.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.501310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92905a7b-6ba2-4c25-93fe-49f1133f1126 · outbound

This paper cites MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.507165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b2dd15-f3a9-46ee-b058-8902a4d84537 · outbound

This paper cites LLaMA 4 Models, 2025.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing LLaMA 4 Models, 2025

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.304938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b910c38b-2a8c-4195-ad35-4ff7e7546599 · outbound

This paper cites Docci: Descriptions of connected and contrasting images.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Docci: Descriptions of connected and contrasting images

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.516625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cfa5e0a-e2a3-4f4d-a2c0-53b09093fb38 · outbound

This paper cites Chatgpt.https://chat.openai.com/, 2023.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Chatgpt.https://chat.openai.com/, 2023

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.284873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e8687744-f4d8-4ddd-aecb-8e6acf57ac4d · outbound

This paper cites Gpt-4v(ision) system card.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Gpt-4v(ision) system card

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.525501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 688261e9-cdbd-4cb3-a5d7-cfecd01d483d · outbound

This paper cites Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.532404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 336d5bca-329a-45bd-a2d9-d90580afc681 · outbound

This paper cites Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.537076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1131b7a0-48d8-4fba-82e4-9a6c75aa0aa3 · outbound

This paper cites Glamm: Pixel grounding large multimodal model.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Glamm: Pixel grounding large multimodal model

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.542132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 102e882d-e025-46db-a6ad-55f00a30f7f8 · outbound

This paper cites Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.257432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e69665ae-af7c-4524-82ba-19e7859f0dd6 · outbound

This paper cites Descriptive caption enhancement with visual specialists for multimodal perception.arXiv preprint arXiv:2412.14233, 2024.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Descriptive caption enhancement with visual specialists for multimodal perception.arXiv preprint arXiv:2412.14233, 2024

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.550601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03e39ec1-c5dc-4dcb-a655-5aad110f1693 · outbound

This paper cites X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.554689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9eda35a-64a6-4952-a0ab-2e5a5bfd0135 · outbound

This paper cites Aligning Large Multimodal Models with Factually Augmented RLHF.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.558769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa5e912d-7b66-46b2-bc96-acdecc3f72d6 · outbound

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

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.562862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc5f46d0-dc93-4738-a8ef-aaf49c27b2e0 · outbound

This paper cites A picture is worth more than 77 text tokens: Evaluating clip-style models on dense captions.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing A picture is worth more than 77 text tokens: Evaluating clip-style models on dense captions

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.243677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eea95389-3355-455a-a68d-066ff04460be · outbound

This paper cites Common subspace for model and similarity: Phrase learning for caption generation from images.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Common subspace for model and similarity: Phrase learning for caption generation from images

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.228582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a97b1593-3422-49d3-82da-ee561ba61b14 · outbound

This paper cites Contrastive region guidance: Improving grounding in vision-language models without training.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Contrastive region guidance: Improving grounding in vision-language models without training

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.209162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 59c74586-ed16-4de0-9da6-2c34d197fbed · outbound

This paper cites Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.579345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f167734f-7c30-4b59-8533-132b5d573bba · outbound

This paper cites VideoRoPE: What Makes for Good Video Rotary Position Embedding?.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing VideoRoPE: What Makes for Good Video Rotary Position Embedding?

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.583543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 382215c7-67c8-4b50-abca-e0ceaa465502 · outbound

This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.587807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64806f49-161e-4d56-aa8e-cb26f5dd936c · outbound

This paper cites Altogether: Image Captioning via Re-aligning Alt-text.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Altogether: Image Captioning via Re-aligning Alt-text

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.592235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc18bfe2-8182-4c96-99cf-dd688cd20071 · outbound

This paper cites Woodpecker: Hallucination correction for multimodal large language models.Science China Information Sciences, 67(12):220105, 2024.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Woodpecker: Hallucination correction for multimodal large language models.Science China Information Sciences, 67(12):220105, 2024

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.596932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1895fc64-31f8-46d5-8074-6069960cf683 · outbound

This paper cites Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.600960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbc28bfb-e29b-4a74-93fd-ba4ddd4207ca · outbound

This paper cites Capsfusion: Rethinking image-text data at scale.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Capsfusion: Rethinking image-text data at scale

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.181030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cb9eac3c-d3a8-4456-85a5-82a3f4b5f632 · outbound

This paper cites Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.609708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f2a9247-4cf8-42d9-9435-fe23fb62ed5a · outbound

This paper cites InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.613881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a49984a-583c-4989-8c47-235ffc566225 · outbound

This paper cites Recognize anything: A strong image tagging model.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Recognize anything: A strong image tagging model

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.617932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 320140f0-88f5-461d-ae07-408a96261f17 · outbound

This paper cites OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T18:30:21.622247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ca300c7-a156-4f3f-affb-1acd58425647 · outbound

This paper cites Describe more details about the [Object].

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Describe more details about the [Object]

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.155723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b246e20a-7d31-4762-898a-77100b275c04 · outbound

This paper cites Instructions: Describe more details about the oven.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Instructions: Describe more details about the oven

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.143730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2dea20cf-015d-4cf2-9a37-2921312b64e1 · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:30:22.116183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b5cb4164-54b6-40ad-939c-81202bf559b6 · outbound

This paper cites Limitations.

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing Limitations

Reference 256

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T18:30:22.131012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 61b793eb-4b1f-449e-a480-548d2d78de90 · inbound

SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience cites this paper.

SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-05T23:55:50.973218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 909b480f-cc88-4ceb-92a9-a48cf0da6589 · inbound

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning cites this paper.

CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T15:19:50.902512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1857817-b6bf-460c-b2cf-5b9ddea88f20 · inbound

Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning cites this paper.

Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-03T12:31:19.632698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06ac6dee-7941-4b8d-b165-2aa7ce6d0158 · inbound

DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions cites this paper.

DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:10:52.894245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.