MATS 2026 年秋季项目
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。研究员将接受顶尖研究人员以及 Anthropic、Google DeepMind、OpenAI、Redwood Research 和 ARC 等机构研究人员的指导，并可申请在主项目结束后继续参加 6 至 12 个月的带资助延长期。本届首次开设创业与领域建设方向和生物安全方向。
Applications are now closed.
Program phases
Key dates for the application and admissions timeline
Applications typically open several months before the program begins. Applicants complete a multi-stage admissions process, beginning with a general application. Depending on the tracks, streams, and mentors they apply to, applicants may also complete additional evaluations such as interviews, work tests, coding assessments, or writing samples before final admissions decisions are made.
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，申请人可选择这些方向下的具体研究流，每个研究流由一位或多位拥有各自研究议程的导师负责。你可以查看网格视图。
Junior grantmaking on Coefficient Giving's Technical AI Safety team ($150M+ in grants in 2025). Fellows will co-lead grant investigations, scope new active grantmaking projects (incl. founding new orgs), and help shape the team's strategy and future RFPs.
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。
The stream focuses on evaluating and/or mitigating catastrophic risk emerging from dangerous scientific capabilities in frontier AI systems, with an emphasis on the challenges that emerge from lab integrations and novel science. Potential research directions include evaluation design, risk mitigations and evaluation science.
Founding ambitious AI safety and field-building projects.
This is the empirical research stream of Eleos AI Research. We’re dedicated to understanding and addressing the potential wellbeing and moral status of AI systems. We are open to fellows working on a broad range of topics, including LLM introspection, LLM preferences, persona vectors, and more, using either white-box or black-box interpretability techniques.
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。
Fourth Eon is developing adaptive, AI-native safeguards across the biotechnology stack, with a focus on function-based DNA synthesis screening. Fellows in this stream will work on technical research projects at the intersection of AI and biosecurity. Projects span topics like mechanistic interpretability of protein foundation models, bio model evaluations for biosecurity-relevant capabilities, and agentic sequence analysis workflows.
We are looking for fellows with a significant background in the biological sciences and/or a founder's perspective to work on and support the Bio Action Plan.