AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation

Qiang Hu, Yuxuan Luo, Yingjie Guo, Hao Wang, Qimei Wang, Qiang Li, Zhiwei Wang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Bias-aware multi-image robustness · 0 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
mitigate explicit errors without ECD module (ablation)RADAR · MIMIC-CXR (RADAR)14Ma-F1: 0.460 -> 0.452Hurt
add ECD module to explicit-error mitigation (ablation)RADAR + MEE · MIMIC-CXR (RADAR)14Ma-F1: 0.452 -> 0.482Improved
add knowledge-graph verification to latent-risk mitigation (ablation)RADAR + MLR · MIMIC-CXR (RADAR)14Ma-F1: 0.472 -> 0.475Improved
add latent-risk mitigation with verification (ablation)RADAR · MIMIC-CXR (RADAR)14Ma-F1: 0.460 -> 0.475Improved
add dynamic masking (ablation)RADAR + MEE&MLR · MIMIC-CXR (RADAR)14Ma-F1: 0.466 -> 0.490Improved
use linguistically-aligned report instead of raw GT report (ablation)RADAR + MEE&MLR · MIMIC-CXR (RADAR)14Ma-F1: 0.482 -> 0.490; BLEU-1 0.526 -> 0.522Mixed
combine explicit-error and latent-risk mitigation (ablation)RADAR · MIMIC-CXR (RADAR)14Ma-F1: 0.482 -> 0.490Improved
use M2DPO instead of standard DPO (ablation)R2GenGPT · MIMIC-CXR14Ma-F1: 0.420 -> 0.437Improved
use M2DPO instead of SimPO (ablation)R2GenGPT · MIMIC-CXR14Ma-F1: 0.425 -> 0.437Improved
use M2DPO instead of standard DPO (ablation)R2GenGPT · In-house endoscopy2F1: 0.832 -> 0.852Improved
mitigate latent risks (ablation)RADAR · MIMIC-CXRmean uncertainty score of correct entities: 0.514 -> 0.282Improved
apply DPO-Clin instead of MMedPOR2GenGPT · IU X-Ray14Ma-F1: 0.332 -> 0.350Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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