AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis

Jiao Xu, Junwei Liu, Jiangwei Lao, Qi Zhu, Yunpeng Zhao, Congyun Jin, Shinan Liu, Zhihong Lu, Lihe Zhang, Xin Chen, Jian Wang, Ping Wang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 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 MediScope multi-turn multimodal dataset to SFT data (ablation)PulseMind-72B · PulseMind Benchmarkavg win rate (%): 26.4 -> 65.2Improved
add MediScope to SFT data (ablation)PulseMind-72B · MedXpertQA-MMaccuracy: 34.9 -> 36.5Improved
add MediScope to SFT data (ablation)PulseMind-72B · MMMU Health & Medicineaccuracy: 67.3 -> 68.1Improved
add RL stage (CRPO) after SFT (ablation)PulseMind-72B · PulseMind Benchmarkavg win rate (%): 65.2 -> 76.0Improved
add RL stage after SFT (ablation)PulseMind-72B · MedXpertQA-MMaccuracy: 36.5 -> 36.6No clear effect
add RL stage after SFT (ablation)PulseMind-72B · MMMU Health & Medicineaccuracy: 68.1 -> 69.4Improved
use CRPO comparison-based reward instead of GRPO absolute-score reward (ablation)PulseMind-72B · PulseMind Benchmarkavg win rate (%): 54.7 -> 76.0Improved
use CRPO instead of GRPO (ablation)PulseMind-72B · MMMU Health & Medicineaccuracy: 66.7 -> 69.4Improved
use CRPO instead of GRPO (ablation)PulseMind-72B · SLAKEaccuracy: 85.2 -> 85.6No clear effect
use relative (pairwise) scoring instead of absolute scores for GPT judge (ablation)GPT-based evaluator · PulseMind Benchmarkconsistency with experts (%): 51.5% -> 86.1%Improved
use absolute 5-point scoring to rank modelsGPT-based evaluator · PulseMind Benchmarkscore spread: 4.01 to 4.35 averageHurt
use PulseMind-72B instead of Qwen2.5VL-72BPulseMind-72B · VQA-RADaccuracy: 80.3 -> 87.1Improved

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