AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution

Chunzheng Zhu, Jiaqi Zeng, Junyu Jiang, Jianxin Lin, Yijun Wang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 16 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
use CCR reinforcement learning instead of SFT (ablation)MedSynapse-V · 5 VQA benchmarks average (8B)average accuracy: 59.2 -> 67.7Improved
add CCR reinforcement learning after MQPM (ablation)MedSynapse-V · 5 VQA benchmarks average (8B)average accuracy: 55.4 -> 67.7Improved
add MQPM warmup before RL (ablation)MedSynapse-V · 5 VQA benchmarks average (8B)average accuracy: 52.9 -> 67.7Improved
add causal counterfactual reward (ablation)MedSynapse-V CCR · 5 VQA benchmarks average (8B)average accuracy: 63.6 -> 67.7Improved
keep anatomical encoder at inference (no IMT removal) (ablation)MedSynapse-V · 5 VQA benchmarks average (8B)average accuracy: 67.7 -> 69.1Mixed
remove encoder via IMT distillation (ablation)MedSynapse-V · Inference efficiencyms/token: 168 -> 102Improved
use MedSAM3 instead of SAM-Med2D as anatomical encoder (ablation)MedSynapse-V · 5 VQA benchmarks average (8B)average accuracy: 63.3 -> 67.7Improved
use pretrained anatomical encoder instead of random init (ablation)MedSynapse-V · 5 VQA benchmarks average (8B)average accuracy: 52.0 -> 67.7Improved
increase diagnostic probe count N beyond 16 (ablation)MedSynapse-V · benchmarksaccuracyHurt
add MedSynapse-V (IMT) to Qwen3-VL-8BQwen3-VL-8B · 7 medical benchmarks (average)accuracy: 48.6 -> 59.6Improved
adapt Coconut latent reasoning to Qwen3-VL-8BQwen3-VL-8B · 7 medical benchmarks (average)accuracy: 48.6 -> 44.5Hurt
adapt IVT-LR latent reasoning to Qwen3-VL-8BQwen3-VL-8B · 7 medical benchmarks (average)accuracy: 48.6 -> 50.5No clear effect

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