HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize
cs.LG, cs.AI
Submitted: 2026-01-06
Updated: 2026-10-12
Terminology
Sources
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
- Reasoning Models Don't Always Say What They Think
- Process Reward Models That Think
- Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT
- GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- R-GenIMA: Integrating Neuroimaging and Genetics with Interpretable Multimodal AI for Alzheimer's Disease Progression
- X-ray Made Simple: Lay Radiology Report Generation and Robust Evaluation
- Multimodal Large Language Model driven Radiology Report Generation with Clinical Knowledge Enhancement
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks