ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution

cs.AI, cs.LG, eess.SP, q-bio.QM

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: Project: https://pork-pay.github.io/ECG-RSI/; GitHub: https://github.com/pork-pay/ECG-RSI

Code: https://github.com/pork-pay/ECG-RSI

Project page: https://pork-pay.github.io/ECG-RSI

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Teach Multimodal LLMs to Comprehend Electrocardiographic Images
• GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
• ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
• ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases
• DiffuSETS: 12-lead ECG Generation Conditioned on Clinical Text Reports and Patient-Specific Information
• MedGemma Technical Report
• Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
• anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task Understanding
• Q-Heart: ECG Question Answering via Knowledge-Informed Multimodal LLMs
• ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning
• ELF: A Family of Encoder-Free ECG-Language Models
• MEETI: A Multimodal ECG Dataset from MIMIC-IV-ECG with Signals, Images, Features and Interpretations
• ECG-Expert-QA: A Benchmark for Evaluating Medical Large Language Models in Heart Disease Diagnosis
• Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework
• MS-ECG-FM: Towards a More Universal Electrocardiogram Foundation Model for Health Monitoring using Multi-source Contrastive Learning
• ECG Mirage: Revealing and Mitigating the Underutilisation of ECGs in Vision-Language Models for Clinical Prediction
• ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
• How Well Do Multimodal Models Reason on ECG Signals?
• Diffusion-based Conditional ECG Generation with Structured State Space Models
• SSSD-ECG-nle: New Label Embeddings with Structured State-Space Models for ECG generation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems