AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment

Jinjian Wu, Jiaqi Tang, Wei Wei, Yingying Yan, Jianmin Chen, Botong Geng, Lei Zhang, Qifeng Chen

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add tool-generated visual evidence to SFT (ablation)IQA-T1 SFT · Average of 7 IQA datasetsPLCC: 0.705 -> 0.756Improved
add tool-generated visual evidence to SFT (ablation)IQA-T1 SFT · Average of 7 IQA datasetsSRCC: 0.680 -> 0.738Improved
add tool usage reward in RL (ablation)IQA-T1 · Average of 7 IQA datasetsPLCC: 0.756 -> 0.790Improved
add repetition penalty in RL (ablation)IQA-T1 · Average of 7 IQA datasetsPLCC: 0.756 -> 0.789Improved
add repetition penalty to model with tool usage reward (ablation)IQA-T1 · Average of 7 IQA datasetsPLCC: 0.790 -> 0.795Improved
add tool usage reward to model with repetition penalty (ablation)IQA-T1 · Average of 7 IQA datasetsSRCC: 0.775 -> 0.784Improved
dynamic tool invocation instead of all 15 tools (ablation)IQA-T1 · KonIQPLCC: 0.865 -> 0.942Improved
dynamic tool invocation instead of fixed 3 tools (ablation)IQA-T1 · KonIQPLCC: 0.895 -> 0.942Improved
dynamic tool invocation instead of random 3 tools (ablation)IQA-T1 · KonIQPLCC: 0.871 -> 0.942Improved
add tool evidence to base Qwen3-VL-4B (ablation)Qwen3-VL-4B · KonIQPLCC: 0.785 -> 0.942Improved
dynamic tool invocation instead of all tools (ablation)IQA-T1 · KonIQavg inference time (s): 6.06 -> 5.09Improved
use Qwen3-VL-4B backbone instead of Qwen3-VL-2B (ablation)IQA-T1 · KonIQPLCC: 0.929 -> 0.942Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy