PulseAugur
中
实时 13:26:04
English(EN) InfiMed2: A Generalist Medical Multimodal Foundation Model from Contextual Evidence and Stability-Aware Supervision

InfiMed2模型在医疗基准测试中达到SOTA,超越Qwen3.5-9B

研究人员推出了一系列新的医疗多模态基础模型InfiMed2,有4B和27B参数两种尺寸。这些模型采用阶段感知数据处理设计,利用包含临床知识和生物医学视觉证据的55.68B token语料库。训练流程包括适配视觉编码器、构建广泛的医学知识以及专注于基于证据的数据混合。在监督微调方面,InfiMed2采用答案稳定性和正确性约束选择等技术来生成更具信息量的解释。经过强化学习进一步优化的4B模型在五个基准测试中的平均准确率为66.73%,优于Qwen3.5-9B模型;而27B模型达到了73.72%,为该领域的开放权重模型树立了新标杆。 AI

影响 为开放权重医疗多模态模型树立了新标杆,有望加速人工智能驱动的医疗保健领域的研究和开发。

排序理由 该条目描述了一篇详细介绍新型AI模型开发和性能的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

InfiMed2模型在医疗基准测试中达到SOTA,超越Qwen3.5-9B

本文如何被排名

Signal score
7 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该条目描述了一篇详细介绍新型AI模型开发和性能的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Guanghao Zhu, Zeyu Liu, Zhitian Hou, Pengkai Wang, Zhijie Sang, Shuo Cai, Yang Yu, Yuanyi Wang, Yanggan Gu, Congkai Xie, Jianmin Wu, Hongxia Yang ·

    InfiMed2:一种来自上下文证据和稳定性感知监督的通用医疗多模态基础模型

    arXiv:2609.34798v2 Announce Type: replace Abstract: Recent medical multimodal models have benefited from larger corpora, broader modality coverage, and stronger reasoning-oriented training, yet effective data design across continued pretraining (CPT) and post-training remains cha…