Pith. sign in

Paper Citation Record · LEDGER

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment

As of 10 August 2026, this Paper Citation Record lists 100 of 143 outbound references and 5 inbound Pith citation observations for arXiv:2506.05384.

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

pith.paper-citation-record.v1
2506.05384 v2

Coverage vector

measured 100 of 143 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:22:51.589424Z

measured 105 of 105 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T12:31:11.070908Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T08:45:35.591791Z

Reference resolution

100 of 143 outbound references displayed

  • verified exact2
  • verified fuzzy4
  • unresolved93
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5e3062a3-881c-438f-8753-4a3274c0fedd · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Flamingo: a visual language model for few-shot learning

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:42.996193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:42.996193Z digest=sha256:f7f29b137e63bf951bf63f42b0bfcec9e4cae146a367ed17ff6a1b926a6b2fd9

Observation 8a05f739-afd6-4eda-afaf-66d0079d3abe · outbound

This paper cites Qwen2.5-VL Technical Report.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Qwen2.5-VL Technical Report

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.038873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.038873Z digest=sha256:5facc17c4661ffea85338681d6c65ce721db64d678d57e8570155c65da7451f9

Observation 8337e0d9-3071-4c76-9049-7d91bc98beb8 · outbound

This paper cites Deep neural networks for no-reference and full-reference image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Deep neural networks for no-reference and full-reference image quality assessment

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.120027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.120027Z digest=sha256:1648fd2db01873ace52cde3e6e64ee881ff2b70d82cfc41c24279cf1952c8cbd

Observation 0f9767c2-b6a9-41ab-b57e-de9d3bd079c7 · outbound

This paper cites Phocolens: Photorealistic and consistent reconstruction in lensless imaging.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Phocolens: Photorealistic and consistent reconstruction in lensless imaging

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.178702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.178702Z digest=sha256:b48acadb7227426bc7d27fc1750d32f6670fa93f6fba1605540127d7475360aa

Observation 2245206f-11ef-4b6d-80a0-ec5258b1c28b · outbound

This paper cites A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.210066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.210066Z digest=sha256:11dc8d0c49ff5f16faebd1ee406015c89e8f2c2a5b5a9db3788e51c6095adcbd

Observation ab358159-7b1c-4bc5-8aeb-f6651ff31d89 · outbound

This paper cites Q-ground: Image quality grounding with large multi-modality models.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Q-ground: Image quality grounding with large multi-modality models

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.286724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.286724Z digest=sha256:2a718051362655767884ba85182ad8b8f58e46bda0775d3406e2f37d323088b8

Observation e4b7da5b-bc24-463e-8819-5ec68cdeec50 · outbound

This paper cites Promptiqa: Boosting the performance and generalization for no-reference image quality assessment via prompts.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Promptiqa: Boosting the performance and generalization for no-reference image quality assessment via prompts

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.361908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.361908Z digest=sha256:aa7f58796cbeb2dce6bdfe423fac7bcdd89cb75a92010d8e3d09f1a683e27d88

Observation f250c247-cb08-44dc-a9b6-eeedb1f6ef44 · outbound

This paper cites SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.430265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.430265Z digest=sha256:69a468d3741c639b42650dc276d768ed6348e1a9e1125d671c4fe7697ba96f1d

Observation 944be268-6eaf-4487-8fff-51625d463f74 · outbound

This paper cites Study of subjective and objective naturalness assessment of ai-generated images.IEEE Transactions on Circuits and Systems for Video Technology, 2024.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Study of subjective and objective naturalness assessment of ai-generated images.IEEE Transactions on Circuits and Systems for Video Technology, 2024

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.484367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.484367Z digest=sha256:0e48bbe7141df17f3d06facadc7a0e1c480ca7453366b5d3e87e31dbd359c842

Observation 3380e968-4e5a-447c-a0f4-152ef8d77d0d · outbound

This paper cites Prompt-based test-time real image dehazing: a novel pipeline.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Prompt-based test-time real image dehazing: a novel pipeline

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.560340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.560340Z digest=sha256:51811b07434b17374f0ea227f77f27f78f30f323ca68471878a4904b371ef2ed

Observation 215dd89a-a1b0-444c-b896-80b1d15aadfd · outbound

This paper cites Perceptual image quality assessment with transformers.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Perceptual image quality assessment with transformers

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.600871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.600871Z digest=sha256:bf44296e600c3fbc4cfe10bfe2f4b0360dcbc8683390391d007c0cb9b2665b7e

Observation faf89e3e-9e7c-4914-8369-b261db64c681 · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.692048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.692048Z digest=sha256:bde4a0d02d2bd561b58e4c111fe44d1be6d90fa0f1443815e07943dd548d2931

Observation 94018c48-c4d1-4868-90ea-eb29e9df386f · outbound

This paper cites Deep rein- forcement learning from human preferences.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Deep rein- forcement learning from human preferences

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.801197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.801197Z digest=sha256:ad30a04e1561afb2ea2559de9ffb9a9df6822d8c592873b8261d6a11c9cad26f

Observation 0594f54a-f833-4bdb-84c2-b5429b517872 · outbound

This paper cites Perceptual quality assessment of smartphone photography.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Perceptual quality assessment of smartphone photography

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.859410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.859410Z digest=sha256:23a35b530d223dcf68982d195715753f8daedae0788495eb9c8e77167d4bde6c

Observation 71df64aa-e36a-4090-8976-71efa250f1fb · outbound

This paper cites Live in the wild image quality challenge database.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Live in the wild image quality challenge database

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:43.944823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:43.944823Z digest=sha256:56f4908c02b80a35479f5aebae720c0ee8154e642c025e759420ae1e72663980

Observation 495d0e1e-d0ff-47be-90bc-6b32d3d4cab2 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.007832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.007832Z digest=sha256:5d4a86b5318c896def79db48d8a4bcec5a9c685e23ff77195ad085da8642042c

Observation 23dca6e3-ebf9-46de-8494-cb092f44b9b5 · outbound

This paper cites Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.051500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.051500Z digest=sha256:32f7c066f88f3f32890ed3d145139a43b6fcfc4ea6e96d0751ac6d2625de2b2d

Observation f508f699-bcde-4e9c-a34e-a5808673d366 · outbound

This paper cites Image quality metrics: Psnr vs.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Image quality metrics: Psnr vs

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.165206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.165206Z digest=sha256:fa92ddd457bd05fce3905df9f5eb624bd3ebd9db950350ee92d547c3be8b05e1

Observation 9f7d73d4-2194-4f4d-8581-e108a7d5f074 · outbound

This paper cites Koniq-10k: An ecologically valid database for deep learning of blind image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Koniq-10k: An ecologically valid database for deep learning of blind image quality assessment

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.272300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.272300Z digest=sha256:c83a123e0f2b70af7ba5fc95b181a57973ec84cbe482cf81863ba421e00cc184

Observation a384c7a2-df11-41f7-9a72-a3f33d76f6ea · outbound

This paper cites Musiq: Multi-scale image quality transformer.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Musiq: Multi-scale image quality transformer

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.307210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.307210Z digest=sha256:9bd17bbb65b3de322a90f9d597d88582de404bae925ac12febbf205d3cdb9614

Observation 01d831bb-3c67-42b0-a5dc-aba5dd619660 · outbound

This paper cites Most apparent distortion: full-reference image quality assessment and the role of strategy.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Most apparent distortion: full-reference image quality assessment and the role of strategy

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.451950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.451950Z digest=sha256:adf2375e1c716e745ff672f5a887bbc4f572622741e43d29283dec32286dfb21

Observation 66eee500-8d0b-4b5f-898b-152a70e6abf5 · outbound

This paper cites Agiqa-3k: An open database for ai-generated image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Agiqa-3k: An open database for ai-generated image quality assessment

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.537837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.537837Z digest=sha256:fd927c4aa447bab2e89f68224bea4364392f14dacd723a94c13d7f4ecbacd1a0

Observation cbea88d5-b09d-4b6e-82d7-82189c35ae25 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.601563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.601563Z digest=sha256:375b8fd50d9093c7f7e502e9e43c1a5fa2da061f6d561e472f44688e85406d6f

Observation af69b475-a00a-4cc2-8388-fb419e9b0713 · outbound

This paper cites Q-Insight: Understanding Image Quality via Visual Reinforcement Learning.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.700327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.700327Z digest=sha256:f91ebfc7c2fce6d70135e8a39c64f138d6c7104b6160ada9e475c2cc1532b081

Observation d775c01f-f2c3-4d5b-bfa2-8f51902a7b91 · outbound

This paper cites Kadid-10k: A large-scale artificially distorted iqa database.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Kadid-10k: A large-scale artificially distorted iqa database

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.733872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.733872Z digest=sha256:abcbb0d78b770d47772d1e4823e3b7862fba618ac0036c508d10ac53b6f6ae93

Observation e73c82f7-598b-40ed-bfca-1f47dd5be824 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.808986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.808986Z digest=sha256:88893ef3fe5b90f0e30885cc00b132eef7eab5b128873fb7ef5dd971593b066b

Observation 83d37042-b9f1-4fa1-9225-05f29939120a · outbound

This paper cites Rankiqa: Learning from rankings for no- reference image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Rankiqa: Learning from rankings for no- reference image quality assessment

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.894043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.894043Z digest=sha256:06c3b1892325ce49b4a61480fde451aa7dd055a8788e11a5b55befd288118318

Observation b6c33788-4c66-4db0-953e-224c2a4de005 · outbound

This paper cites Cid: Iq–a new image quality database.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Cid: Iq–a new image quality database

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:44.992553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:44.992553Z digest=sha256:697f74e8a0a109a19efbe8cfd67204b3d01c5a2f0273220ac9fa4d4f3cbdd410

Observation 1fc98cc6-0ec4-4457-93f7-6330c7f265c0 · outbound

This paper cites InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.145896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.145896Z digest=sha256:df7e5a0f0407ca3b3f92364077d58f0daf42d06ce25b499e2d3b4c283cfc5031

Observation b589a7ea-3bd6-4128-99e9-0f89e207c519 · outbound

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

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Visual-RFT: Visual Reinforcement Fine-Tuning

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.208749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.208749Z digest=sha256:953fac8304ff0029c0d37573a16d697541da07b5a659328a81851c422d153dec

Observation 7319e903-7492-446e-ba4a-e1960f4ec777 · outbound

This paper cites UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.285035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.285035Z digest=sha256:a5215a30808b92fe7d7030081b37258d7354ed4226b537134637a1e24ebe725e

Observation 4c0cab02-1962-478f-b333-a5b5a79be75a · outbound

This paper cites Learning a no-reference quality metric for single-image super-resolution.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Learning a no-reference quality metric for single-image super-resolution

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.345145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.345145Z digest=sha256:b5405fc2d7747cfd5046f1eb2ecbfda340610863efe53928f294831005cf952b

Observation 55b7b1b0-66a5-4241-841f-3b109d9f1107 · outbound

This paper cites End-to-end blind image quality assessment using deep neural networks.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment End-to-end blind image quality assessment using deep neural networks

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.421560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.421560Z digest=sha256:d6901db4b024ff2b45db2bbec5da71d60a7c04113f5a62887f66ad10aecef3c4

Observation d2a79e74-ae17-4b1d-9c96-1556d9a6341e · outbound

This paper cites No-reference image quality assessment in the spatial domain.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment No-reference image quality assessment in the spatial domain

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.478843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.478843Z digest=sha256:1709ea77239f97220d9c09da63f610ec58a451aae90c3a5fdcffd9d9f13dc8cf

Observation 801d2841-59a3-40f2-83bf-a1840c95bfeb · outbound

This paper cites Making a ¡ °completely blind¡± image quality analyzer.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Making a ¡ °completely blind¡± image quality analyzer

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.636953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.636953Z digest=sha256:cb77c7f32812d1490344c724e0e3f12e024a9e2950ea84882238ead1c170cda7

Observation 5fc98678-9933-45fa-a771-8c53f26914ae · outbound

This paper cites Human-level control through deep reinforcement learning.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Human-level control through deep reinforcement learning

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.788187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.788187Z digest=sha256:09459c75bbf2b32a0c080cce05553fba528dedc2ccb71227f744a04fec1d9018

Observation ab4db865-2c86-47cb-91ce-843cb9a3bd71 · outbound

This paper cites A two-step framework for constructing blind image quality indices.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment A two-step framework for constructing blind image quality indices

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:45.964616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:45.964616Z digest=sha256:9777b2f0b3a32dbb6a91ce1b90445ed3d4c6faa8959050660147ac62c5ba3ac5

Observation b843b709-b139-4753-9eac-752145acfedc · outbound

This paper cites Blind image quality assessment: From natural scene statistics to perceptual quality.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Blind image quality assessment: From natural scene statistics to perceptual quality

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:46.100684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:46.100684Z digest=sha256:ffad5170a0def995fbd438f26c7e9878dfb07e61095147d996ae16456be89ce6

Observation 8a9b4dc2-2bc5-4a6f-95e0-ccb6fec3a349 · outbound

This paper cites Blind image quality assessment using a deep bilinear convolutional neural network.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Blind image quality assessment using a deep bilinear convolutional neural network

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:46.204124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:46.204124Z digest=sha256:a72239f4622d88ca90cc465990ba7af58910af5ec2844228e983c9d0672fe4ca

Observation 0a54c4a0-569f-4014-9790-4319d07af2ac · outbound

This paper cites Training language models to follow instructions with human feedback.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Training language models to follow instructions with human feedback

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:46.385887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:46.385887Z digest=sha256:e2774a4e2e7ac1083d782809b63e2b701fd413a42fd5d143fe3c578c6597f0a1

Observation c9cc2324-a571-4895-822c-83e6c158173a · outbound

This paper cites MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:46.567623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:46.567623Z digest=sha256:a3469a875188010399e4a204e1982fdc2ded7c63b03f4a1d232046d345ec8a02

Observation 19ae3b72-7f91-4063-b2ec-222dc939191d · outbound

This paper cites Image database tid2013: Peculiarities, results and perspectives.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Image database tid2013: Peculiarities, results and perspectives

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:46.676465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:46.676465Z digest=sha256:e26c7911be0cc50ea714b05b0247711577f21a22cacd31a81619c977cc113b31

Observation 6210cf54-2d26-4fea-bb92-f54a8a03d51b · outbound

This paper cites Tid2008-a database for evaluation of full-reference visual quality assessment metrics.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Tid2008-a database for evaluation of full-reference visual quality assessment metrics

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:46.790374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:46.790374Z digest=sha256:d389a5c874ed2d4a7c2bfded2be1d4759e5bc271f4b0109d25631a283952dc15

Observation 1d81b1cd-e44f-446d-b32c-641a22a98cc7 · outbound

This paper cites Pieapp: Perceptual image-error assessment through pairwise preference.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Pieapp: Perceptual image-error assessment through pairwise preference

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:46.894950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:46.894950Z digest=sha256:5f0c0315ff30b122fb9a25f9c0f09a872b44f9ab0ccf10e6bcc84afb044f0151

Observation 1e1698de-8439-40d1-bbe8-7e79ee8478e6 · outbound

This paper cites Blind image quality assessment: A natural scene statistics approach in the dct domain.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Blind image quality assessment: A natural scene statistics approach in the dct domain

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:47.012587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:47.012587Z digest=sha256:2221bac7eb1115d5cfb265051824e05dd9b26dcde6f8d9965d0736ae62c313fc

Observation d53ece29-985e-4071-9c60-730b769eb2c1 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Proximal Policy Optimization Algorithms

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:47.156059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:47.156059Z digest=sha256:589b664d42bfdcec4c7537895dc9e30eae88763e8e4661642314a032b4606895

Observation 1d106e0a-caf1-4589-a8a0-5c7963549d1c · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:47.315251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:47.315251Z digest=sha256:bf856fe514f279d57eb66b147224614689a0c15f61b97eba1c755022bcc18094

Observation d4521ee9-58d8-46b0-a36b-2cc576aa49c1 · outbound

This paper cites Image information and visual quality.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Image information and visual quality

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:47.417861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:47.417861Z digest=sha256:2d3255ce7bbaa0ea9c87515454eec0f3e686798196b909d3496228c28054b7bb

Observation 00340765-bc0a-4c5c-9b1d-3daacf62324d · outbound

This paper cites A statistical evaluation of recent full reference image quality assessment algorithms.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment A statistical evaluation of recent full reference image quality assessment algorithms

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:47.532235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:47.532235Z digest=sha256:087d5c94a184383a1156cd90792f5986bb4d714a7ad7ff12a44a17370c686b2b

Observation 11997311-cacb-429e-87cd-3be562bd8175 · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:47.716144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:47.716144Z digest=sha256:51235ba43af258b85ebbc82b28a6529c437315cfa07a1fd8d069bc16efacd8f0

Observation 446590fa-a179-49ad-93c7-fe66d56ffbf1 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment HybridFlow: A Flexible and Efficient RLHF Framework

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:47.879209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:47.879209Z digest=sha256:d4c046b80d59ecbe3c181f427c98bd778ca5cf80408a6ad9373b5a43f495c2c9

Observation a4363afd-462b-4ec9-9908-64c7b8537846 · outbound

This paper cites Mastering the game of go with deep neural networks and tree search.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Mastering the game of go with deep neural networks and tree search

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:47.975509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:47.975509Z digest=sha256:f055191ca428e79873dc816d86c76cc8e85017b371c0b0f49a62d3b7dddcc356

Observation 7715d83b-c46a-4598-aa9c-1d6d4ec1092d · outbound

This paper cites Blindly assess image quality in the wild guided by a self-adaptive hyper network.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Blindly assess image quality in the wild guided by a self-adaptive hyper network

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.028769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.028769Z digest=sha256:1db71d79cffae30057f44188a7bad76beb1b8c316dbab6ec931f0c6bca9d9d74

Observation 3e5c15d5-b3fd-4acb-ba5d-77489c6398a9 · outbound

This paper cites Graphiqa: Learning distortion graph representations for blind image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Graphiqa: Learning distortion graph representations for blind image quality assessment

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.115849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.115849Z digest=sha256:d16c3797d8eb4f4889bef4b0956b84e72d81d0960e3d45503be85d976997337a

Observation a6428483-cc5f-4e7a-9c3d-94887cb9b68f · outbound

This paper cites Nima: Neural image assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Nima: Neural image assessment

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.214310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.214310Z digest=sha256:d2e08f8279074c11ff9bdb3b337f02767119bdd905411732b527e36dcefa7eeb

Observation 5e8500fb-13c9-47d6-a6a1-c8ddc2baf39d · outbound

This paper cites Learning a blind measure of perceptual image quality.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Learning a blind measure of perceptual image quality

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.285651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.285651Z digest=sha256:375f9a7aab2a63f4995a72cefa6634917f875ecb825582dee0f9fad2d3478ce5

Observation dd6f523b-f60f-4d45-8a1a-c1a466700eab · outbound

This paper cites Internlm: A multilingual language model with progressively enhanced capabilities, 2023.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Internlm: A multilingual language model with progressively enhanced capabilities, 2023

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.381377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.381377Z digest=sha256:d11097e89911e3913972ef9d76ab9fdeb8761738c2d72471d28343bd7dfbeac0

Observation b7f272a8-d1a3-4bff-b30f-a425f9b2b75b · outbound

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

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Gpt-4v (ision) system card

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.447207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.447207Z digest=sha256:94e1b561f592b6aa43538d7abd77e0c1372b846bb6fca6cc6417d661e5eecbb6

Observation 13061859-7674-4faa-bf1c-398617065adc · outbound

This paper cites Exploring clip for assessing the look and feel of images.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Exploring clip for assessing the look and feel of images

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.541738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.541738Z digest=sha256:9a88c42d8096f4dace7670bac4136ecfc19c4ea4acaaf46f89b26c92e6e41625

Observation e131f97c-9eb0-403e-9ac9-d5a488482f7d · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Image quality assessment: from error visibility to structural similarity

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.620080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.620080Z digest=sha256:7710de06dfb2eacc414088f3e5d9dec89346f31b3e546b49c297deae03666fd5

Observation adf2f297-a7f8-42f7-bfae-8ad83440b995 · outbound

This paper cites MP-GUI: Modality Perception with MLLMs for GUI Understanding.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment MP-GUI: Modality Perception with MLLMs for GUI Understanding

Reference 61

Resolution
verified exact
local_arxiv, observed 2026-08-07T11:22:55.089749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:48.737064Z digest=sha256:73c7fc767db9984aef1e1b4db3f17eb5194f0b3efa483c3940e9608a89c7666c

Observation 65cf78c1-f762-4134-85a9-5a22fc707003 · outbound

This paper cites Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.836267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.836267Z digest=sha256:9da472956709b57578ac1720a0baabf885d0b4bac3f2060a2794df65367052b0

Observation a694c952-93db-4643-ac21-0439f6bcf5aa · outbound

This paper cites Q-instruct: Improving low-level visual abilities for multi-modality foundation models.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Q-instruct: Improving low-level visual abilities for multi-modality foundation models

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:48.909722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:48.909722Z digest=sha256:595196ff519462e38329102050520b804e57865091c4e54419d26c6a178a9071

Observation d500d21a-2e70-43a0-8902-5c69d2502cea · outbound

This paper cites Towards open-ended visual quality comparison.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Towards open-ended visual quality comparison

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.004345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.004345Z digest=sha256:17e1174b446c6118eba234cb94e7c9b7773b1fe4677a067190b9c87b88197034

Observation 20d2e0ef-6dab-416c-9872-e1d8cced16b7 · outbound

This paper cites A comprehensive study of multimodal large language models for image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment A comprehensive study of multimodal large language models for image quality assessment

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.098769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.098769Z digest=sha256:a924c720b24cc66ba3783256976a7e38508cb42b894080e1b0d65ac6a145e9b7

Observation ca304a87-8e6c-4327-ace1-eaf7144c601f · outbound

This paper cites Maniqa: Multi-dimension attention network for no-reference image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Maniqa: Multi-dimension attention network for no-reference image quality assessment

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.173436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.173436Z digest=sha256:f8c6d2e9766147bad2a8c4f4006929556e7aae870935a01b7cc1a06895659ec2

Observation f92efe22-d80e-4cef-b895-bbc562aa1c73 · outbound

This paper cites mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.261080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.261080Z digest=sha256:4973a44a5700e17c9326da9a71191b2b7bfe8a2e69ac189fcc5da1148a35548d

Observation f8bebeca-6da2-4111-90c0-32295e79e29c · outbound

This paper cites Teaching large language models to regress accurate image quality scores using score distribution.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Teaching large language models to regress accurate image quality scores using score distribution

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.370227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.370227Z digest=sha256:688155f45ae583cb875285975928fa0cee7c62f6c9c6b21ffb3ebd2985bd4ef4

Observation b5a3d067-2f6e-49c6-b001-86c9502c9634 · outbound

This paper cites Descriptive image quality assessment in the wild.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Descriptive image quality assessment in the wild

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.436525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.436525Z digest=sha256:da2ff9c95f1d0cbc4257b61dbe73b0b73458a99d2b3a6ad02ab64016e68d2c40

Observation fee8388c-44d7-42c8-b728-7462e8a7d74f · outbound

This paper cites Depicting beyond scores: Advancing image quality assessment through multi-modal language models.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Depicting beyond scores: Advancing image quality assessment through multi-modal language models

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.514771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.514771Z digest=sha256:5dd4dfe527aea7d8071a808e7a9b5254e7d6a2f0ccaa0c67b488bce2c29f65c7

Observation 8d005e88-8534-41b0-b104-e4dcaa8eaa7c · outbound

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

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.597252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.597252Z digest=sha256:82e40b2b03e7810e04c4789cd5262c8471e945057e37b8d028523efbde262156

Observation c2ed15d8-69cb-4bc6-b934-ec7f14b6e2ad · outbound

This paper cites Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.689598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.689598Z digest=sha256:045399ed639c58a2a8fb57e1187d0e01806f35a031a33c6e75990d1e53bf3810

Observation 9f673720-0fb3-44d4-a5b5-04fb6bbb0b28 · outbound

This paper cites Sf-iqa: Quality and similarity integration for ai generated image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Sf-iqa: Quality and similarity integration for ai generated image quality assessment

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.783373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.783373Z digest=sha256:47f016fd757b00d9082f4874b0aebb7c26c212f910f0777d30894a00c6e3d83f

Observation 60cde204-1f40-4564-a7d7-acc7fe5084fb · outbound

This paper cites Vision-language models for vision tasks: A survey.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Vision-language models for vision tasks: A survey

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.877811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.877811Z digest=sha256:fab4c8b53d053cd7dc5163705d936a6cec2d817fda4024fc0ecdc66b42a772e3

Observation 218b86d8-3bd2-4233-8245-e870f78165aa · outbound

This paper cites Fsim: A feature similarity index for image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Fsim: A feature similarity index for image quality assessment

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:49.967967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:49.967967Z digest=sha256:6e7844d576fd194a5376a69600d32fa616bf7ff1cc1bd79241ef7105212847a1

Observation 8fcc6445-ca6c-401a-873c-8c33f8d2034c · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment The unreasonable effectiveness of deep features as a perceptual metric

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.047021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.047021Z digest=sha256:659961fe5eafdc87aad873a8ee8ab8d1db7d74c75bcba09e63a15372209ab751

Observation 9c840ca8-f8c2-4700-a833-c9b16ee322a7 · outbound

This paper cites Continual learning for blind image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Continual learning for blind image quality assessment

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.115807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.115807Z digest=sha256:a43b19f347496bd64cfd0da10245518565c6d4bafde216d29b0f839e3424966b

Observation f4e6989f-dc4a-48f1-a8a3-9ab41ea3079b · outbound

This paper cites Blind image quality assessment via vision-language correspondence: A multitask learning perspective.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Blind image quality assessment via vision-language correspondence: A multitask learning perspective

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.197326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.197326Z digest=sha256:3409b4f0509114346a58f4ec934e91c535578f09528893ab2b8efd84811b42f8

Observation 7420504c-a95c-4c50-9097-cb00434d0fdc · outbound

This paper cites GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.278097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.278097Z digest=sha256:53b137fa422b3205bdbbabb314b51ca891a4ef03c239739eda4f48c209a5c3a4

Observation bf83dd4e-5a6b-4fe9-b9fc-de3de6805c90 · outbound

This paper cites MM-RLHF: The Next Step Forward in Multimodal LLM Alignment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.342524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.342524Z digest=sha256:057729470e22ae8940dd95565d0f22a97b0be9daba1212203c1cac048299ae8d

Observation 01b6e318-d9eb-41c8-bc34-3804bd53e64d · outbound

This paper cites Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.396698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.396698Z digest=sha256:12500134ac3db6661aa3ca5b4c04af1364d59aaa98512e58cef4571635fa92c4

Observation 971f844c-def0-40ba-bc69-246ae1de1957 · outbound

This paper cites Quality assess- ment in the era of large models: A survey.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Quality assess- ment in the era of large models: A survey

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.461525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.461525Z digest=sha256:22e881263a36bfcfb1ecb8043ec4de9a9b34d84695589921879bb0ab5b3750eb

Observation 48f74f51-9218-4c85-ae43-68b5b80a9b17 · outbound

This paper cites Learning conditional knowledge distillation for degraded-reference image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Learning conditional knowledge distillation for degraded-reference image quality assessment

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.518298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.518298Z digest=sha256:c89b29fe259b9ea07abd1442f805031018d5256427a08884456c6cadfac7db53

Observation 0538431f-5837-4e0e-8a80-357eda3cd126 · outbound

This paper cites Causal-iqa: Towards the generaliza- tion of image quality assessment based on causal inference.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Causal-iqa: Towards the generaliza- tion of image quality assessment based on causal inference

Reference 84

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.578538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.578538Z digest=sha256:b50732aa1b8a9ee23d5143cac059b9756d64e17a262c87ad691513cbdaa84063

Observation 0b094d24-af10-4b2d-81c9-91ae50bd5fba · outbound

This paper cites Quality assessment of image super-resolution: Balancing deterministic and statistical fidelity.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Quality assessment of image super-resolution: Balancing deterministic and statistical fidelity

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:22:56.193636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:50.648544Z digest=sha256:699e543790b732356e57e2ba1c818e203865c05dd2884e02c82da16c1efbbaa3

Observation c632fef1-c9d5-402f-a179-1c7ce16450bd · outbound

This paper cites Metaiqa: Deep meta-learning for no-reference image quality assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Metaiqa: Deep meta-learning for no-reference image quality assessment

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:22:56.177443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:50.704981Z digest=sha256:5f530d9864032cf70b5f7d871f553125e7bba3c77580f689f47e993f4949d468

Observation 0299c436-682e-49cb-ac9c-67d3d93c65e8 · outbound

This paper cites Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.767674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.767674Z digest=sha256:e29cfed88e753ed79a8054b1b1af6e6edddea5091c0114a7da377ee4fcf46745

Observation f8c62296-95c6-4524-83d9-4dbc189d26b1 · outbound

This paper cites An Intelligent Agentic System for Complex Image Restoration Problems.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment An Intelligent Agentic System for Complex Image Restoration Problems

Reference 88

Resolution
unresolved
no resolver link, observed 2026-08-07T11:22:50.842977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:22:50.842977Z digest=sha256:bc68b187c5c74652713249104d9a18bdfa9d21d496afffaf4e039ebc6795c3a0

Observation 01dd35b6-ae01-45e8-a80b-33b58eec141b · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 90

Resolution
parse uncertain
raw_fallback, observed 2026-08-07T11:22:56.162283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:50.905661Z digest=sha256:a6ecde3158356a213a87dfccfc4561f711ee86c719fda7f91d2187026d462e53

Observation 85a8aed2-1eff-4ec9-8a4e-c08cc5a0b3fc · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 91

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:22:56.148197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:50.958760Z digest=sha256:dc22ecaecb9aa8821112c8e326027caf87740b563f4605358136a238af78bb70

Observation 113bc2a6-4f7a-4e5d-81fd-06bfb6a204f8 · outbound

This paper cites compression noise).

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment compression noise)

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:22:56.134529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.024547Z digest=sha256:7cfea69c4280f9b78923e992f3710086e0a6aee6ce77368e8cb69ba003fa017e

Observation 0994ff35-8053-4e9e-971d-fd8c9f0316a1 · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 93

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:22:56.121101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.078963Z digest=sha256:1d7206607987e0efa4e196bce1b151b39ba84f739a269b2f51f2045ed005f575

Observation 15c81ec6-9de5-4f3a-9192-53f663f4eaa9 · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 94

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:22:56.107111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.140099Z digest=sha256:550589d79a1745ae1a7cbbc98b9ea076b0ab626af4b1c13b590cdc0c8b5785e3

Observation d3abd72f-a8d7-4b77-925c-72f6c15c1299 · outbound

This paper cites Special rule: Artistic style may conditionally override low-level flaws, but must not affect final score.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Special rule: Artistic style may conditionally override low-level flaws, but must not affect final score

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:22:56.092917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.212100Z digest=sha256:ed381d4893c1cc371485f0a7f0f594be5f057e673cfd3ff8bca09a464a9a8cba

Observation 444fa779-0074-4722-8861-a9f93712cb04 · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 96

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:22:56.079114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.281254Z digest=sha256:b7ae75ecc6d807c7e8d21ace3bf1dc6044c8f16cacef97aad75f306c455406e3

Observation bbce5382-ea61-44bc-af6f-f2cd01934782 · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 97

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:22:56.064183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.335668Z digest=sha256:05da6ae39cd528fdec969ed732a7247b3efbe1a8e7cec4ae0e42abcf3e2c5c24

Observation d405ed6a-aff4-4862-b580-f1320856053c · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 98

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:22:56.046820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.395970Z digest=sha256:1e34c2e26385ff2ab4722fc2ca2bed6c8ce9d1a7cbef0f84845298ffb27dbb14

Observation 271b3c92-84b0-42bd-9e34-21e2a6d479db · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 99

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:22:56.032136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.448239Z digest=sha256:94d5d8aedf1289cf3a264976f39e2091055d6f28c9502b6fe7b75950d381e601

Observation f0b182cd-756a-48c6-8870-6f0013b67504 · outbound

This paper cites an unresolved cited work.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Unresolved cited work

Reference 100

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:22:56.017428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.535053Z digest=sha256:d563955adb19cb79abf4ecd5f3a7be49d20971c4795c5c3190ceb14dd7dd6500

Observation 5f6bc4a7-78eb-4240-95dc-a7a121a4fd48 · outbound

This paper cites Composition and Style Attributes Guided Image Aesthetic Assessment.

Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment Composition and Style Attributes Guided Image Aesthetic Assessment

Reference 101

Resolution
verified exact
local_arxiv, observed 2026-08-07T11:22:54.660884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T11:22:51.589424Z digest=sha256:641d6ff27d4763c576fd330ea231473467e98586c48c078027a127d588a3a759

Pith citing papers

Observation e76b0625-b3a2-4934-93b2-586efc0f96a1 · inbound

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

Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-03T12:31:11.070908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T12:31:11.070908Z digest=sha256:377ec76f9d252c54e687161ef735f77e7ebde8465077d146d86680ed8096fe9b

Observation 278c1c0a-e0db-4cc1-9c0e-86c543c89510 · inbound

Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing cites this paper.

Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-16T12:47:54.152422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-16T12:44:12.618007Z digest=sha256:326949d3e0b3ab6fa29f27138c45acd9bba28746851971c1dcfd8de5f6c2e1bc

Observation bdbc6dea-8260-4d49-ab1c-ef34fcfbbdd5 · inbound

SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing cites this paper.

SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-05-11T13:16:03.545962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-10T02:10:12.484462Z digest=sha256:13ed2d3fdfaff467adff293502dc920aa2c8d4d7b41e1bd241403dbfc0c23419

Observation ef5c3d0e-d007-4f44-8412-ec5d5c845290 · inbound

MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment cites this paper.

MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-06-30T06:44:19.633385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-30T06:35:49.706047Z digest=sha256:7f90ef0cf0c356b361753b231635975de8d7cc7d33da95a79c6bf6a06ffe2b54

Observation 879b01d2-3c65-4734-ab68-bf766646ac03 · inbound

MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment cites this paper.

MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-07-01T08:45:35.593423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-07-01T07:08:45.796716Z digest=sha256:5ab25bce67d2c8823a8a64a12b18de81f995957a8ae91461ee43b8e23153e442