Xiaomi Technology

顶尖应届-具身大模型算法研究员-机器人事业部

Xiaomi Technology  •  Onsite  •  2 hours ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

顶尖应届-具身大模型算法研究员-机器人事业部

北京

校招

正式

算法类

职位描述

1、设计并实现 VLA / Embodied VLM / World Model 的训练目标、分布式训练方案与数据 recipe,融合互联网图文、视频、3D / 仿真、真机轨迹等多源数据; 2、设计并实现融合视频生成与动作控制的多模态大模型架构,探索大规模数据缩放定律,利用海量互联网视频数据及机器人采集数据,提升模型在零样本场景下的任务泛化能力; 3、研发基于 VLM 的端到端导航与具身 Agent 算法; 4、构建具身大模型的评测基准与真机闭环验证 pipeline; 5、跟踪并复现 SOTA 工作,与训练 / 推理 / 数据 / 硬件团队协同迭代

职位要求

1、CV / ML / 机器人 / AI 相关方向博士,或同等研究能力的硕士; 2、在 VLM / 多模态大模型 / 视频理解 / 3D 视觉 / VLN / Embodied Agent / RL / 视频生成 / 世界模型 任一方向有扎实基础; 3、至少在 CVPR / ICCV / ECCV / NeurIPS / ICML / ICLR / ACL / RSS / CoRL / ICRA / IROS 等顶会以一作发表过相关工作; 4、熟练 PyTorch,熟悉 Transformer、Diffusion、CLIP / SigLIP / Qwen-VL 等主流架构,具备分布式训练 / 大规模数据处理经验者优先; 5、系统思维强,对"什么是真正重要的具身问题"有自己的判断,能独立 own 一个研究方向,具备极强的自驱力,能够从 0 到 1 推动前沿技术在真实物理世界落地。

职位信息

课题名称及内容:

【课题名称】 具身大模型算法研究(VLA / 具身推理 / 世界模型) 【课题内容】 围绕机器人具身基础模型展开研究,覆盖三个方面: 1、VLA 大模型:融合视频生成与动作预测的多模态架构,利用海量互联网视频与机器人采集数据,提升零样本场景下的任务泛化与长程决策能力; 2、 具身推理大模型:构建面向开放环境的具身 VLM 基座,攻克三维场景理解、可供性、第一人称时序理解等问题,并在其上研发在开放环境下长程任务规划与执行的具身智能体系统; 3、具身世界模型:通过视觉/动作编码器、多模态表征学习与离散/连续 tokenizer 等核心模块,建模物理世界的时空动力学,为 VLA 与规划提供可预测、可推演的世界基座。最终目标是构建可作为理解、导航、操作等下游任务统一基座的具身大模型,并在真机场景端到端落地。

投递

Xiaomi Technology

About Xiaomi Technology

Xiaomi Corporation was founded in April 2010 and listed on the Main Board of the Hong Kong Stock Exchange on July 9, 2018 (1810.HK). Xiaomi is a consumer electronics and smart manufacturing company with smartphones and smart hardware connected by an IoT platform at its core.

Embracing our vision of “Make friends with users and be the coolest company in the users’ hearts”, Xiaomi continuously pursues innovations, high-quality user experience and operational efficiency. The company relentlessly builds amazing products with honest prices to let everyone in the world enjoy a better life through innovative technology.

Xiaomi is one of the world's leading smartphone companies. The company has also established the world’s leading consumer AIoT (AI+IoT) platform,reached 558 million smart devices connected to its platform (excluding smartphones,laptops and tablets) as of September 30 2022. Xiaomi products are present in more than 100 countries and regions around the world. In August 2022, Xiaomi was included in the Fortune Global 500 list for the fourth year in a row, ranking 266th. The company is the fastest-rising Chinese technology conglomerate during the four-year period.

Xiaomi is a constituent of the Hang Seng Index, Hang Seng China Enterprises Index, Hang Seng TECH Index and Hang Seng China 50 Index.

Industry
IT & Software
Company Size
10,000+ employees
Headquarters
Beijing, CN
Year Founded
2010
Social Media