AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs

Huan Zheng, Yucheng Zhou, Tianyi Yan, Dubing Chen, Hongbo Lu, Wenlong Liao, Tao He, Pai Peng, Shen Jianbing

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 4 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 hierarchical clinical cognition SFT (ablation)Qwen3-VL-8B · Average (5 GI benchmarks)accuracy: 35.30 -> 66.31Improved
add hierarchical clinical cognition SFT (ablation)Qwen3-VL-2B · Average (5 GI benchmarks)accuracy: 16.05 -> 54.49Improved
add counterfactual-driven GRPO after SFT (ablation)Qwen3-VL-8B (SFT) · Average (5 GI benchmarks)accuracy: 66.31 -> 67.67Improved
add counterfactual-driven GRPO after SFT (ablation)Qwen3-VL-4B (SFT) · Average (5 GI benchmarks)accuracy: 61.98 -> 64.05Improved
add counterfactual-driven GRPO after SFT (ablation)Qwen3-VL-2B (SFT) · Average (5 GI benchmarks)accuracy: 54.49 -> 57.40Improved
add counterfactual-driven GRPO after SFT (ablation)Qwen3-VL-8B (SFT) · Multi-label subset (strict exact match)accuracy: 10.64 -> 13.62Improved
add counterfactual-driven GRPO after SFT (ablation)Qwen3-VL-8B (SFT) · CrohnIPIaccuracy: 62.14 -> 63.11Improved
add counterfactual-driven GRPO after SFT (ablation)Qwen3-VL-8B (SFT) · GastroVisionaccuracy: 76.92 -> 77.21Improved
add counterfactual-driven GRPO after SFT (ablation)Qwen3-VL-4B (SFT) · HyperKvasiraccuracy: 86.10 -> 89.19Improved
use Gaussian blur instead of solid white mask for counterfactuals (ablation)CogAlign · GI benchmarksaccuracyImproved
add clinical cognition reward R_cog (ablation)CogAlign GRPO · GI benchmarksaccuracyImproved
add diagnostic consistency reward R_diag (ablation)CogAlign GRPO · GI benchmarksaccuracyImproved

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