Introduces MMBU benchmark for VLMs in biomedicine and demonstrates that established benchmarks mask perception deficiencies in evaluated models.
Octomed: Data recipes for state-of-the-art multimodal medical reasoning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
OpenMedReason supplies a large open corpus of multimodal medical reasoning examples extracted from scientific articles, paired with a benchmark that measures perception, knowledge, and rationale quality, yielding 20% VQA gains after supervised fine-tuning.
ClinSeekAgent automates active multimodal evidence seeking for clinical reasoning, improving LLM performance on raw EHR and CXR tasks while enabling distillation into smaller models.
PathoSage is a three-stage framework using Structured Evidence Deliberation and a Beta-Bernoulli experience system to improve patch-level pathology reasoning by mitigating hallucinations and tool conflicts.
citing papers explorer
-
MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models
Introduces MMBU benchmark for VLMs in biomedicine and demonstrates that established benchmarks mask perception deficiencies in evaluated models.
-
OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models
OpenMedReason supplies a large open corpus of multimodal medical reasoning examples extracted from scientific articles, paired with a benchmark that measures perception, knowledge, and rationale quality, yielding 20% VQA gains after supervised fine-tuning.
-
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
ClinSeekAgent automates active multimodal evidence seeking for clinical reasoning, improving LLM performance on raw EHR and CXR tasks while enabling distillation into smaller models.
-
PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow
PathoSage is a three-stage framework using Structured Evidence Deliberation and a Beta-Bernoulli experience system to improve patch-level pathology reasoning by mitigating hallucinations and tool conflicts.