2026 年秋季项目为期 10 周,于 9 月 28 日至 12 月 4 日在美国加州伯克利和英国伦敦开展。学员将由顶尖研究者及来自 Anthropic、Google DeepMind、OpenAI、Redwood Research 和 ARC 等机构的研究人员指导,并可申请在主项目结束后继续参加 6 至 12 个月的资助延期。本届将首次开设“创业与领域建设”和“生物安全”两个研究方向。
目前已截止申请。

申请与招生流程中的关键阶段
申请通常会在项目开始前几个月开放。申请者需完成多阶段招生流程,首先提交通用申请。根据所选研究方向、研究小组和导师,申请者可能还需参加面试、工作测试、编程评估或提交写作样本,之后才会作出最终录取决定。

主项目为期 10 至 12 周,是全职研究项目。学员与一位或多位导师密切合作,独立开展研究,同时参加工作坊、讲座、导师答疑时段,并融入更广泛的 MATS 社群。学员与导师共同确定研究方向,并在项目期间逐步提升独立开展研究的能力。
延伸阶段通常在主项目结束约两周后开始。主项目中展现出较强研究潜力的学员可申请为期 6 至 12 个月的资助延伸项目。延伸阶段的学员在持续获得导师指导和支持的同时,继续推进独立研究,通常在 MATS 办公室或其他获准的研究地点工作。最近几期中,约 80% 申请延伸阶段的学员获得录取。
MATS 致力于帮助研究人员加速发展,走向以下方向:
MATS 校友后来发表了安全研究成果、加入了 Anthropic 和 MIRI 等对齐研究组织,也创办了对齐研究实验室。更多校友信息请点击这里。
第一阶段,申请人可申请一个或多个研究方向:实证研究、理论、战略与预测、政策与治理、系统安全、生物安全,以及创业与领域建设。进入第二阶段后,通过筛选的申请人可选择这些研究方向下的具体研究流,每个研究流由一位或多位导师负责,并围绕各自的研究议题开展工作。你可以在下方查看研究流列表,也可以通过网格视图查看。
Coefficient Giving 技术 AI 安全团队提供初级项目资助机会(2025 年资助总额超过 1.5 亿美元)。学员将共同领导资助项目调查、规划新的主动资助项目(包括创立新组织),并参与制定团队战略和未来的项目征集。
导师会积极提供支持,形式类似常规的经理与团队成员关系:每周至少一次一对一交流,并提供异步指导。
完整的标准请见这份文档。简而言之,我们希望候选人兼具以下能力:
学员将在整个项目期间参与多个项目,并与导师密切合作,共同确定和推进项目。学员拥有的自主空间,将与新加入团队的资助项目负责人相当。
我主要关注两个方向。
安全:
我希望设计并开展对真实 AI 部署的攻击演示,以展示其安全漏洞,推动企业投入资源采用能够解决根本安全问题的对齐技术。
基准测试:
进入后训练扩展时代后,我希望构建基准,衡量现代大语言模型技术究竟能否泛化。
我会根据项目相关兴趣安排一对一或小组会议。会议之外通过 Slack 沟通。
除项目初期外,我更倾向于安排多次短会,而不是一次长会。
遇到研究障碍时,即使不在会议期间,我也会提供帮助。
安全方向:
你应具备较强的安全意识,展现出创造性解决问题的意愿。我希望看到你愿意亲自动手,尝试测试多种不同系统。
基准测试方向:
你应尽可能富有创意,愿意深入细节、努力处理他人觉得枯燥的问题,并对旧金山湾区常见的兴趣话题以外的领域保持兴趣。
导师将与学员讨论项目想法。
这个研究方向评估和/或缓解前沿 AI 系统危险科学能力可能带来的灾难性风险,尤其关注实验室集成和新兴科学带来的挑战。潜在研究方向包括评估方法设计、风险缓解和评估科学。
我们可以每周安排一次一小时的会议,讨论进展、分享结果并提供总体指导。我也会通过 Slack 进行异步沟通。需要针对具体问题讨论,或结对编程、调试时,也可以临时安排通话。我常驻伦敦,按英国时间工作(上午 10 点至晚上 7 点),每年也会数次前往美国波士顿。
必要条件
优先条件
以下情况可能不太适合:
我会与学员共同寻找符合其兴趣的项目,并介绍几个项目想法,协助学员作出选择。我也欢迎学员提出项目建议;如果有合适的想法,我们可以一起把项目范围细化到可执行的程度。
发起有抱负的 AI 安全项目,推动相关领域发展。
最低指导安排为每周两次、每次 30 分钟会议;如有需要,也可以增加指导时间。
我常驻旧金山。如果学员希望有一段时间在 BlueDot 办公室工作,我可以每天与他们协作。
学员随时可以与我快速通话;我也会及时回复 Slack 消息。
我欢迎背景各异的申请者。不过,学员需要愿意投入大量精力、善于沟通,并真心希望 AI 能朝着有益的方向发展。
我最擅长与行动力强、表达和推理清晰且以使命为导向的人合作。
我们会一起设计项目。学员有很大自由度,可以探索最合适的项目形式;我会定期提供充分反馈,并介绍相关人士,帮助完善提案。
前一到两周主要用于确定项目方向,奖学金后续时间则集中于执行。
这是 Eleos AI Research 的实证研究方向,致力于理解并改善 AI 系统可能具有的福祉和道德地位。我们欢迎学员研究各种相关主题,包括 LLM 内省、LLM 偏好、人格向量等,并可采用白盒或黑盒可解释性方法。
通常每周至少会线下见面一小时。两次会议之间,我们会定期通过 Slack 沟通;如果遇到有时效性、妨碍项目推进的问题,我通常也能临时抽空快速通话。
必备条件:
以下条件会带来明显优势,但并非必需:
项目开始时,我们会讨论符合 Eleos 研究重点的项目想法,也会考虑学员希望提出的选题。之后我们会共同选择最符合每位学员目标与技能的项目。
本研究流包含两个大方向的项目,旨在切实支持 SecureBio 当前的检测工作。第一个方向研究 AI 生物工具或通用 AI 工具在大规模宏基因组检测中的实际价值,包括算力成本、测序成本、模型类型与规模,以及工作流程各阶段之间的权衡。第二个方向探索将基因组语言模型用作新颖性检测器,例如使用类似困惑度的指标标记异常序列,并评估这一方法能否以合理成本提供灵敏、可解释的补充,配合传统生物信息学系统使用。
通常我们会每周安排约一小时的固定会议,讨论近期进展和下一步方向。我也会通过 Slack 快速交流想法、检查思路是否合理,并协助解决数据访问等阻碍;学员需要自行负责实现、代码审查和调试等工作。
必备条件:
优先条件:
不太适合的情况:
我会根据 SecureBio Detection 的需求以及与我匹配的学员情况,决定开展两个大方向中的哪一个。在选定方向内,我会根据自己认为对 SecureBio Detection 有帮助、有趣且相关的内容提供指导;学员则有自主权,也需要主动负责具体工作方向的选择。
Fourth Eon 正在开发覆盖生物技术全链条的自适应 AI 原生防护措施,重点关注基于功能的 DNA 合成筛查。本项目的学员将开展 AI 与生物安全交叉领域的技术研究,方向包括蛋白质基础模型的机制可解释性、生物模型对生物安全相关能力的评估,以及智能体驱动的序列分析流程。
通常我会每周与每位学员固定进行一次一对一交流,也会主持每周的研究组会议。此外,我会通过 Slack 保持联系,并可在例行会议之外安排额外通话。
根据我们的《安全与负责任研究框架》,学员需要签署 fellowship 协议,承诺保密,并接受对可能存在双重用途风险的研究进行发表前审查。这是生物安全研究中的常见做法,有助于我们安心合作处理敏感材料。
必备条件:
• 有技术研究经验
• 具备较强的批判性思维和创造性解决问题的能力
• 为敏感研究负责地开展工作,具备相应的诚信与判断力
• 了解生物分子序列、结构与功能的基础知识
• 在以下一个或多个领域具备专长:
生物信息学、计算生物学、结构生物学、生物化学、分子生物物理学、蛋白质工程、生物安全、AI/机器学习或相关领域
• 熟练使用 Python
优先考虑:
• 有测试生物领域 AI 模型的实践经验
• 有构建模型评估或基准测试的经验
• 有机制可解释性方法的经验
• 了解生物安全相关背景和风险
对我们的研究方向感兴趣的学员,可以先思考如何结合自身优势与兴趣开展项目。我会与每位学员一起确定具体课题,使其契合学员的背景、兴趣和我们的整体研究方向,并共同明确项目范围与目标。
我们希望招募在生物科学领域有扎实背景,和/或具备创业者视角的学员,共同推进并支持 Bio Action Plan。
我们希望学员在生物科学领域有扎实背景;具备生物安全专长会是加分项。了解公共卫生和疫情防备也很有帮助。对这些议题感兴趣并有自己的深入见解,会对项目很有帮助。我也希望学员能以创业者的视角思考如何建立和发展组织,让计划真正落地。
A track is a broad research area within MATS. Empirical, Theory, Strategy & Forecasting, Policy & Governance, Systems Security, Founder & Field-Building, and Biosecurity are our current tracks. Each track contains multiple streams. In Stage 1, you apply to tracks.
Streams are organized around a research agenda, led by one or more mentors who guide fellows through related projects. In Stage 2, applicants apply to streams within tracks based on research that interests them.
You may apply to as many tracks as you wish at Stage 1. At Stage 2, depending on which tracks you progress in, you may then apply to as many streams as you wish within those tracks; there is no cap. The process is comparable to applying to PhD supervisors.
We want to be flexible for applicants who have urgent prior commitments. Based on individual circumstances, we may be willing to alter the time commitment of the program and allow fellows to leave early or arrive late. Please inform us of your availability in the application process.
Applicants who will be 18 years or older before the program start date are eligible to apply. Both US and non-US citizens are eligible to apply. All backgrounds and levels of experience are welcome and prior AI safety experience is not required.
Yes. The 12-week program requires fellows to commit 40 hours per week to their MATS research. For exceptionally strong candidates with significant concurrent responsibilities, the time commitment can be reduced to 20 hours per week on a case-by-case review. However, the program maintains an expectation of sustained, high-level engagement, including regular participation in core activities and most organized events. Candidates that require a J1 visa to come to the US are unable to participate part time; they can only work part time if they participate remotely or from the UK.
Yes, upon submitting you will receive a link that lets you edit your response. Please note that you will not be able to edit your response once the application period ends.
LLMs may not be used to write any part of your application unless specific work tests or forms explicitly permit it. MATS monitors for LLM use, and applicants found to have used LLMs may be disqualified.
Depending on the evaluations of the tracks and streams you apply to in Stages 1 and 2, we will contact your references. We will send them a form with our own set of questions, so they will not have to prepare a reference letter.
Although MATS sometimes supports UC Berkeley-based mentors, MATS is an independent program and is not formally part of UC Berkeley. As such, MATS will not be providing student cards to our scholars.
The main program, or Research Phase, takes place in person in Berkeley, CA and London, UK. Historically, most fellows participate from Berkeley. London is typically chosen by fellows who want to co-locate with their mentor or who have a preference to work from the UK instead of US.Will this program be remote or in-person?
The main program, or the Research Phase takes place in Berkeley, CA and London, UK, with the majority of fellows participating from Berkeley. We strongly encourage in-person participation when possible, as a core part of the program experience comes from day-to-day interactions with your cohort and others in the broader AI safety ecosystem.
Decisions about remote participation are made on a case-by-case basis and depend primarily on mentor preferences, many of whom are open to the possibility, especially if you have family or other obligations that make in-person participation difficult. We strongly encourage in-person participation when possible, as a core part of the program experience comes from day-to-day interactions with your cohort and others in the broader AI safety ecosystem.
If you have difficulties in securing a visa to participate from Berkeley, we are likely to be able to support participation from our London office.The 6–12 month extension gives fellows the option to participate from Berkeley, London, or remotely.
MATS is a scientific and educational seminar and independent research program, and provides J1 visas for non-American participants. Participants can also opt to participate from our London office; however, please note that visa support is not available for that option.
During the main program, fellows should expect to meet with their mentor for at least one hour per week, with more frequent communication via Slack. The extent of mentor support will vary depending on the project and the mentor.
Fellows will also receive support from MATS’ Research Management team, who work with mentors by tracking scholar research progress, unblocking scholar research, and assisting with grant applications and deadlines.
Fellows develop as researchers by working with an experienced research mentor, interacting with other fellows, and receiving support from our Research Management team. Research managers meet weekly with most fellows and mentors and help with research strategy, research unblocking, and project coordination.
Other forms of training include workshops on different parts of the research process and seminars on a variety of AI technical safety and governance research.
Throughout the program, each fellow will work on an independent research project with input and guidance from your mentor(s). Depending on which stream you participate in, you may collaborate with other fellows in your stream.
Traditionally, fellows submit a Research Plan midway through the program and present their research at the Fellow Symposium at the end of the program.
We welcome feedback. For feedback for the whole team (visible by all MATS staff), please use this form. For feedback that will only be visible to the Co-Executive Directors, Ryan and Christian, please submit here.
You can contact the MATS Board of Directors using this linked form (responses are only viewable by the Board). Please only use this if you feel your question or concern requires board-level attention.