Unified Multimodal Model for Brain MRI Imputation and Understanding
早录MICCAI 2026,提出统一多模态模型同步实现脑MRI数据补全与理解,打通医学影像分析新路径。
arXiv:2606.16484v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) hold great potential for medicine, as they inherit knowledg…
GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal Models
大型多模态模型的提示检索新方法,利用用户反馈动态优化提示,提升生成质量与适应性。
arXiv:2606.12744v1 Announce Type: new Abstract: In-Context Learning (ICL) has become a powerful mechanism for adapting Large Language Models (LLMs) to…
Navigating Gigapixel Pathology Images with Large Multimodal Models
在arXiv上追踪前沿AI病理图像研究,一键访问最新多模态论文
arXiv:2511.19652v2 Announce Type: replace Abstract: Recent advances in large multimodal models have allowed for the development of interactive chat mo…
小米 MiMo Code V0.1.0 探索性 AI 编程助手发布并开源:基于 OpenCode 二次开发,采用 MIT 协议
小米开源探索性AI编程助手MiMo Code v0.1.0,基于OpenCode二次开发,支持多模态模型与语音控制,采用MIT协议。
IT之家 6 月 11 日消息,小米 MiMo 官方今日凌晨正式发布并开源 MiMo Code V0.1.0 —— 一款运行在终端里的探索性 AI 编程助手。 据介绍, MiMo Code 基于开源项目 OpenCode 二次开发,发布并开源,采用 MIT 协议 。它还内置限时免费多模态模型 MiM…
Large Language Models as Modal Models in Linguistics
探讨LLM作为语言学模态模型的新视角,论文从理论层面解析大语言模型的语言学应用价值
arXiv:2606.10467v1 Announce Type: new Abstract: The rapid advancement of large language models (LLMs) has intensified debates about their significance…
PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
生理信号增强胸部X光自编码器,多模态基础模型新突破,被ICML 2026 Workshop接收。
arXiv:2606.01537v1 Announce Type: cross Abstract: Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed mo…
Video Reasoning without Training
无需昂贵训练与冗长思维链,探索视频推理的高效新路径。
arXiv:2510.17045v2 Announce Type: replace-cross Abstract: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning…
BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs
首个针对多模态大模型物理推理的台球基准,测试从静态图预测动态的能力
arXiv:2605.30900v1 Announce Type: new Abstract: Current multimodal models handle static image recognition well, but intuitive physical reasoning remai…
从Token无上限到全员Agent:MiniMax的AI Native组织进化实践
MiniMax从Token无上限到全员Agent,揭秘AI Native组织的进化实践与多模态模型布局
与其焦虑AI,不如加入AI
Archon: A Unified Multimodal Model for Holistic Digital Human Generation
首次提出全预训练的统一多模态模型Archon,融合文本、音频、动作与视觉,实现数字人整体生成。
arXiv:2605.30311v1 Announce Type: cross Abstract: Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic m…
智象未来CEO梅涛:多模态模型Token的毛利率,远高于语言模型
梅涛揭秘多模态模型毛利率远超语言模型,商业路径清晰可见。
文|王欣逸 李嘉星 编辑|周鑫雨 一家Day 1就在做多模态大模型的公司,无法拒绝参与到具身智能和世界模型热潮之中。 2026年,随着Seedance 2.0、GPT Image 2.0等模型的爆火,多模态能力越来越成为行业内绕不开的关键词。5月19日,智象未来首届开放日上,智象未来给出了他们的判断…
How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning
让多模态模型通过“想象”进行视觉思维,大幅提升空间推理能力,新方法开源并实验验证。
arXiv:2605.27310v1 Announce Type: new Abstract: Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason …
网易有道“子曰 4”多模态模型、语音合成模型全量开源
网易有道重磅开源“子曰4”多模态模型与TTS模型,教育场景数理能力达行业顶尖,支持14种语言,单卡即可运行。
IT之家 5 月 22 日消息,网易有道今日宣布,决定将“子曰”大模型 4.0 的核心双引擎 ——“多模态模型”与“语音合成(TTS)模型”, 正式面向全球全量开源 。开发者可以免费下载、部署,并基于此进行二次开发。 此次开源的“子曰 4”多模态模型(27B 参数规模)面向教育场景,支持视觉输入的数…
Reinforcing VLAs in Task-Agnostic World Models
提出在任务无关世界模型中强化VLA的方法,提升模型泛化能力与样本效率。
arXiv:2605.12334v2 Announce Type: replace Abstract: Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world…