The paper introduces Set-Distance Rewards (SDR), a permutation-invariant reward signal that effectively guides the generation of unordered radiology reports, significantly outperforming standard train…

This paper introduces MedReCo and MedReCo-VLM, a framework that enables entity-aware cross-image reasoning for medical imaging, allowing AI to compare current scans with prior studies and analogous ca…

The paper addresses 'Template Collapse' in 3D CT report generation—where models generate generic reports—by proposing CLarGen, a decoupled framework that significantly improves clinical accuracy and d…

C-MIG is a novel retrieval-augmented generation framework that uses multi-view information gain to improve clinical diagnosis reasoning by providing richer, more nuanced reward signals than existing m…

The paper demonstrates that clinical vision-language models (VLMs) pose a significant privacy risk by allowing de-identified images to be re-linked to original reports, and proposes a targeted differe…

The paper introduces EASE, a method that enhances multimodal Reinforcement Learning with Verifiable Rewards (RLVR) by providing spatial attention supervision anchored to visual evidence, significantly…

IRDS introduces a novel data selection method that uses a verifier-coupled sparse autoencoder framework to efficiently select high-quality Reinforcement Learning with Verifiable Rewards (RLVR) trainin…

The paper introduces AutoMedBench, a novel workflow-aware benchmark that evaluates autonomous medical-AI agents across a five-stage research process, revealing that agents struggle most with validatio…

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reali…

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

The paper introduces a simple, token-efficient vision-language model for generating comprehensive pathology synoptic reports from multiple whole-slide images (WSIs), achieving high performance while s…

The paper introduces CERA, a novel contrastive retrieval framework that improves RAG factuality and interpretability by using subjectivity-based hard negative selection and an auxiliary attention alig…

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

CRITIC-R1 introduces a structured critic framework that treats RAG critique as an explicit error diagnosis problem using reinforcement learning, significantly improving answer quality over strong RAG…

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals…

This paper demonstrates that patient-facing RAG chatbots frequently expose sensitive system configurations, knowledge base details, and conversation history through client-server communication, posing…

This paper identifies prediction bias, a failure mode of entropy minimization in test-time adaptation, and proposes Distribution Shift Bias Reduction (DSBR) to stabilize adaptation and prevent model c…

The paper introduces Ryze, an automated system that synthesizes evidence-enriched Question-Answering (QA) pairs from raw biomedical papers, resulting in a specialized VLM (BioVLM-8B) that significantl…

The paper introduces Factual Density (FD*), a novel retrieval signal that measures the proportion of verified facts, demonstrating that optimizing RAG retrieval based on this density significantly imp…

EchoRL proposes a lightweight module to exploit valuable learning signals from advantage-degenerated rollouts in Reinforcement Learning with Verifiable Rewards (RLVR), significantly improving LLM post…