【Official】以 AI × 机器人驱动研发创新，探索未来分子发现 Driving R&D Innovation with AI × Robotics for Future Molecule Discovery by XtalPi|muShanghai Pass Needed
Events calendar has moved to Sola. Visit the link below for the latest events and RSVP.
Weekly pass is required for events at Ali Hongqiao Center. Monthly pass is sold out — thank you for the overwhelming support!
muShanghai 活动日历已迁移至 Sola，请前往以下链接查看最新活动并报名。
如活动地点在阿里虹桥中心，须持有周票入场。谢谢大家的厚爱，月票已售罄！
Events & RSVP: https://app.sola.day/event/mushanghai
Tickets: https://p.baominggongju.com/detail?eid=6a09d97aeda89afdb6daadbe&referer=odVL41ECtJ_QzoCogQn0W-4qROpQ
如果未来的药物与材料研发不再主要依赖盲目“试错”，而是由 AI 预测、机器人实验、数据反馈共同驱动，科学发现会变成什么样？
晶泰科技正在回答这个问题。
这场分享将从晶泰科技的技术实践出发，讨论 AI、量子物理、超级智能体以及机器人实验平台如何重塑分子发现的流程：从靶点理解、分子生成、虚拟筛选，到自动化合成、实验验证与数据回流，研发不再只是线性的人工推进，而逐渐变成一个可以持续学习、持续迭代的闭环系统。
晶泰科技成立于 2015 年，由 MIT 背景的物理学家创立，长期聚焦以 AI 与机器人技术推动生命科学和新材料研发的智能化、数字化转型。它的技术体系把量子物理、AI、云计算和大规模自动化实验平台结合起来，服务于药物发现、新材料、化学自动化、现代化中医药、新能源、农业科学等多个方向。
当 AI 不只会“预测”，机器人不只会“执行”，而是共同构成一个可学习的研发系统时，未来分子发现的速度、尺度和成功率会如何改变？
为什么这场值得来
它不是一场泛泛而谈的 AI 科普。 这场分享会围绕真实研发场景展开，讨论 AI 与机器人如何进入药物和材料发现的核心流程。
它关心的不只是模型，而是完整闭环。 分子发现真正困难的地方，不只是生成一个候选结构，而是如何让设计、合成、测试、反馈形成可持续迭代的系统。
它连接生命科学与未来材料。 同一套“AI × Robotics”的研发范式，正在从小分子药物延展到抗体、材料、能源、化工等更广阔领域。
它来自一线产业实践。 晶泰科技已经与全球多家药企、科研机构和产业伙伴开展合作，并在自动化实验、AI 模型、分子设计与数据驱动研发方面积累了大量经验。
你会看到什么
AI 如何进入分子发现。 从分子生成、性质预测、虚拟筛选到候选物优化，AI 如何帮助研发团队更快地探索更大的化学空间。
机器人实验室为什么重要。 自动化实验平台如何 24X7 执行高通量实验、产生标准化数据，并减少传统实验流程中的重复劳动与不可控变量。
“干实验室”与“湿实验室”如何闭环。 计算模型提出假设，机器人实验验证假设，实验数据再反哺模型，形成 Design-Make-Test-Analyze 的持续迭代。
未来分子发现的基础设施是什么。 当 AI、超级智能体、量子物理第一性原理、实验机器人、数据工程和领域专家共同工作，研发组织的能力边界会发生什么变化。
从药物到材料的跨行业想象。 分子层面的发现能力如何支持药物研发、新材料、绿色化学、新能源、农业科学和现代化中医药等方向。
分享嘉宾
王明泰
晶泰科技高级副总裁
王明泰长期参与晶泰科技在技术创新、产业合作与生态建设中的实践。他将结合晶泰科技在“AI × Robotics驱动研发范式创新”的产业实践，分享未来分子发现如何从“依靠经验的研发流程”走向“由数据驱动的工程化创新”。
关于晶泰科技
晶泰科技是一家由人工智能与机器人技术驱动的创新技术平台公司，成立于 2015 年，致力于推动生命科学和新材料行业的智能化、数字化转型。
公司将量子物理、AI、云计算和大规模机器人实验平台紧密结合，为全球生物医药和新材料企业提供技术解决方案、服务与产品，帮助加速从想法到候选分子、从实验假设到可验证结果的研发过程。
晶泰科技已于 2024 年在香港联交所上市，股票代码 2228.HK。其技术和业务覆盖小分子药物发现、蛋白与抗体设计、肽类发现、固态研究、自动化实验室解决方案、未来材料和化学自动化等方向。
适合谁来
生命科学与药物研发从业者： 想了解 AI 与自动化实验如何改变早期发现、候选物优化和研发决策。
AI、机器人与自动化方向的研究者 / 工程师： 想看到模型、硬件、实验流程和产业场景如何结合。
材料、化学、新能源与合成生物学相关从业者： 想理解分子发现平台如何从药物研发扩展到更多材料与化学问题。
投资人、创业者与产业合作伙伴： 想观察 AI for Science 从概念走向平台化、基础设施化和商业化的路径。
对未来科学发现感兴趣的跨行业观众： 想用非专业但不浅薄的方式理解 AI × Robotics 为什么可能改变研发范式。
你将带走什么
一个清晰框架： 如何理解 AI、量子物理、机器人实验与数据闭环在分子发现中的分工。
一个产业视角： 为什么未来的研发竞争不只是“谁的模型更强”，也包括谁能持续获得高质量实验数据、构建自动化基础设施并形成闭环能力。
一组真实问题： AI 药物研发如何避免停留在 demo？机器人实验室如何真正提升研发效率？跨学科团队如何协作？
一个未来想象： 分子发现可能从单点工具，变成一套连接科学假设、自动实验、数据生产和产业应用的新型研发操作系统。
现场内容
从传统研发到智能闭环： 为什么药物与材料发现需要新的研发基础设施。
AI × Robotics 的核心逻辑： 模型预测、机器人实验、标准化数据与专家知识如何互相增强。
未来分子发现案例与场景： 从小分子、抗体，到新材料和化学自动化。
产业合作与生态建设： AI for Science 如何在药企、科研机构、材料企业和自动化平台之间形成新的协作方式。
开放 Q&A： 欢迎围绕 AI 药物研发、机器人实验室、未来材料、分子设计、产业落地和跨学科团队建设提问。
报名说明
报名主要用于收集邮箱，以便后续有更新信息时及时通知大家。本活动仅限 muShanghai Pass 持有者参加。
FAQ
我不是药物研发或材料科学专业背景，可以来吗？
可以。这场分享会尽量用清楚的语言解释 AI × Robotics 如何改变分子发现，同时保留足够的技术密度，适合跨行业观众理解。
这是一场销售活动吗？
不是。这是一场围绕 AI、机器人与未来分子发现的主题分享与交流，不构成采购承诺、投资建议、医疗建议或任何产品性能保证。
现场会涉及很深的专业公式或论文细节吗？
不会以公式推导为主。分享重点是研发范式、技术平台、产业实践和未来趋势。如果你来自 AI、生命科学、材料、化学、投资或创业领域，都可以找到相关视角。
为什么主题里用 “future molecule discovery”？
因为未来的分子发现不只发生在药物研发里，也会影响材料、能源、农业、环境与化学工业。AI 与机器人平台提供的是一种更通用的研发能力：更快地产生假设、更高效地验证假设、更系统地积累可复用数据。
What if future drug and materials R&D were no longer driven mainly by blind trial and error, but by AI prediction, robotic experimentation, and data feedback?
XtalPi is answering this question.
This session will start from XtalPi’s technology practice and discuss how AI, quantum physics, super agents, and robotic experimentation platforms are reshaping the process of molecule discovery: from target understanding, molecule generation, and virtual screening to automated synthesis, experimental validation, and data feedback. R&D is no longer only a linear, human-driven process, but is gradually becoming a closed-loop system that can keep learning and iterating.
Founded in 2015 by MIT-trained physicists, XtalPi has long focused on using AI and robotics to drive the intelligent and digital transformation of life sciences and new materials R&D. Its technology system combines quantum physics, AI, cloud computing, and large-scale automated experimentation platforms, serving drug discovery, new materials, chemical automation, modernized traditional Chinese medicine, renewable energy, agricultural science, and other directions.
When AI does not only “predict” and robots do not only “execute,” but together form a learning R&D system, how will the speed, scale, and success rate of future molecule discovery change?
Why this session is worth attending
It is not a generic AI popular science talk. This session will focus on real R&D scenarios and discuss how AI and robotics enter the core processes of drug and materials discovery.
It cares not only about models, but about the full closed loop. The real difficulty of molecule discovery is not only generating a candidate structure, but how to make design, synthesis, testing, and feedback form a continuously iterative system.
It connects life sciences and future materials. The same “AI × Robotics” R&D paradigm is extending from small-molecule drugs to antibodies, materials, energy, chemical engineering, and broader fields.
It comes from frontline industry practice. XtalPi has already collaborated with many global pharmaceutical companies, research institutions, and industry partners, and has accumulated extensive experience in automated experimentation, AI models, molecular design, and data-driven R&D.
What you will see
How AI enters molecule discovery. From molecule generation, property prediction, and virtual screening to candidate optimization, how AI helps R&D teams explore larger chemical spaces faster.
Why robotic laboratories matter. How automated experimentation platforms can run high-throughput experiments 24X7, generate standardized data, and reduce repetitive labor and uncontrolled variables in traditional experimental workflows.
How “dry labs” and “wet labs” form a closed loop. Computational models propose hypotheses, robotic experiments validate hypotheses, and experimental data feeds back into the models, forming continuous Design-Make-Test-Analyze iteration.
What the infrastructure of future molecule discovery is. When AI, super agents, first principles of quantum physics, experimental robots, data engineering, and domain experts work together, how will the capability boundaries of R&D organizations change?
Cross-industry imagination from drugs to materials. How molecule-level discovery capabilities can support drug R&D, new materials, green chemistry, renewable energy, agricultural science, and modernized traditional Chinese medicine.
Speaker
Wang Mingtai
Senior Vice President, XtalPi
Wang Mingtai has long participated in XtalPi’s practice in technology innovation, industry collaboration, and ecosystem building. He will draw on XtalPi’s industry practice in “AI × Robotics-driven R&D paradigm innovation” to share how future molecule discovery is moving from “experience-based R&D processes” toward “data-driven engineering innovation.”
About XtalPi
XtalPi is an innovative technology platform company driven by artificial intelligence and robotics. Founded in 2015, it is committed to driving the intelligent and digital transformation of the life sciences and new materials industries.
The company tightly combines quantum physics, AI, cloud computing, and large-scale robotic experimentation platforms to provide technology solutions, services, and products for biopharmaceutical and new materials companies worldwide, helping accelerate the R&D process from ideas to candidate molecules and from experimental hypotheses to verifiable results.
XtalPi was listed on the Hong Kong Stock Exchange in 2024 under the stock code 2228.HK. Its technology and business cover small-molecule drug discovery, protein and antibody design, peptide discovery, solid-state research, automated laboratory solutions, future materials, and chemical automation.
Who should attend
Life sciences and drug R&D professionals: Those who want to understand how AI and automated experimentation are changing early discovery, candidate optimization, and R&D decision-making.
AI, robotics, and automation researchers / engineers: Those who want to see how models, hardware, experimental workflows, and industry scenarios come together.
Materials, chemistry, renewable energy, and synthetic biology practitioners: Those who want to understand how molecule discovery platforms can expand from drug R&D to more materials and chemistry problems.
Investors, entrepreneurs, and industry partners: Those who want to observe how AI for Science moves from concept toward platformization, infrastructure, and commercialization.
Cross-industry audiences interested in future scientific discovery: Those who want to understand in a non-professional but not shallow way why AI × Robotics may change the R&D paradigm.
What you will take away
A clear framework: How to understand the division of labor among AI, quantum physics, robotic experimentation, and data closed loops in molecule discovery.
An industry perspective: Why future R&D competition is not only about “whose model is stronger,” but also about who can continuously obtain high-quality experimental data, build automated infrastructure, and form closed-loop capabilities.
A set of real questions: How can AI drug R&D avoid staying at the demo stage? How can robotic laboratories truly improve R&D efficiency? How can interdisciplinary teams collaborate?
A future imagination: Molecule discovery may move from point tools into a new R&D operating system that connects scientific hypotheses, automated experiments, data production, and industrial applications.
Live content
From traditional R&D to intelligent closed loops: Why drug and materials discovery need new R&D infrastructure.
The core logic of AI × Robotics: How model prediction, robotic experimentation, standardized data, and expert knowledge reinforce one another.
Future molecule discovery cases and scenarios: From small molecules and antibodies to new materials and chemical automation.
Industry collaboration and ecosystem building: How AI for Science forms new ways of collaboration among pharmaceutical companies, research institutions, materials companies, and automation platforms.
Open Q&A: Questions are welcome around AI drug R&D, robotic laboratories, future materials, molecular design, industrial implementation, and interdisciplinary team building.
Registration note
Registration is mainly used to collect email addresses so that we can notify everyone in time if there are follow-up updates. This event is for muShanghai Pass holders only.
FAQ
Can I come if I do not have a drug R&D or materials science background?
Yes. This session will try to explain how AI × Robotics changes molecule discovery in clear language while retaining enough technical density, making it suitable for cross-industry audiences to understand.
Is this a sales event?
No. This is a thematic sharing and exchange around AI, robotics, and future molecule discovery. It does not constitute a procurement commitment, investment advice, medical advice, or any guarantee of product performance.
Will the session involve very deep professional formulas or paper-level details?
It will not focus on formula derivation. The focus of the sharing is the R&D paradigm, technology platform, industry practice, and future trends. If you come from AI, life sciences, materials, chemistry, investment, or entrepreneurship, you can find relevant perspectives.
Why use “future molecule discovery” in the theme?
Because future molecule discovery does not only happen in drug R&D. It will also affect materials, energy, agriculture, the environment, and the chemical industry. AI and robotics platforms provide a more general R&D capability: generating hypotheses faster, validating hypotheses more efficiently, and systematically accumulating reusable data.