ModelsSelected

Google 发布 Gemini Robotics 2.5 与 AlphaGenome 2 两个领域模型

Why we picked it

机器人圈和生信圈可以同时关注这条。Gemini Robotics 2.5 在奔驰产线跑到 96% 成功率,比多数还在实验室演示的 VLA 模型更接近工业落地;AlphaGenome 2 免重训就能接 scRNA-seq,做单细胞分析的研究者上手成本低。

Google DeepMind 一口气发布两个垂直领域模型。Gemini Robotics 2.5 是覆盖双臂和人形机器人的全身视觉-语言-动作(VLA)模型,在奔驰生产线的套件装配任务中达到 96% 成功率,并与 Apptronik 的 Apollo 2 人形机器人深度配合。

Image · Philipp Schmid
Body

AlphaGenome 2 则是单细胞 DNA 模型,训练数据涵盖超过 1.07 亿个细胞档案、横跨 68 种组织。它支持直接输入 scRNA-seq 数据而无需重新训练,这让研究人员能把转录组信息快速接入基因组预测流程。

两个模型代表 Google 在机器人控制和生命科学两条垂直线的推进:前者用真实产线数据验证工业落地能力,后者扩展了 DeepMind 在计算生物学领域继 AlphaFold 之后的布局。

Original · Philipp Schmid

We also shipped two domain models: 🤖 Gemini Robotics 2.5: whole-body Vision-Language-Action model across arms and humanoids hitting 96% kitting success on Mercedes-Benz lines with Apptronik Apollo 2 deepmind.google/blog/gemini-ro… T 🧬 AlphaGenome 2: single-cell DNA model trained on 107M+ cell profiles across 68 tissues with scRNA-seq input without retrainin deepmind.google/science/alphag… xX📊 3 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Gemini Robotics, AlphaGenome, Google DeepMind, VLA.

Source attribution: curated from Philipp Schmid (@_philschmid).