MATS Winter 2027

The Winter 2027 program will run for 12 weeks, from January 19th to April 10th, in Berkeley, CA and London, UK, with remote options also available. Fellows will receive mentorship from world-class researchers at organizations like Anthropic, Google DeepMind, OpenAI, Redwood Research, and ARC, with the option to apply for a 6–12 month funded extension beyond the main program.

Applications are now closed.

Program phases

Key dates for the application and admissions timeline

1. Applications

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. More information can be found on the apply page.

Winter 2027 Timeline:

2. Main Program
3. Extension Phase
4. Post-program

Winter 2027 Streams

In Stage 1, applicants apply to one or more tracks (broad research areas): Empirical, Theory, Strategy & Forecasting, Policy & Governance, System Security, Biosecurity, and Founding & Field-Building. In Stage 2, advancing applicants choose specific streams within those tracks, each led by one or more mentors with their own research agenda. You can view this list below or as a grid here.

This stream will focus on model motivations and character, open-ended environments, and new forms of misalignment.

Read more
Desired fellow characteristics

This stream will focus on monitoring, stress-testing safety methods, and evals, with a focus on risks from scheming AIs. Examples include (black-box) AI control techniques, white-box monitors (probes etc.), chain-of-thought monitoring/faithfulness, building evaluation environments, and stress-testing mitigations.

Read more
Mentorship structure
Desired fellow characteristics
Project selection process

Founding ambitious AI safety and field-building projects.

Read more
Mentorship structure
Desired fellow characteristics
Project selection process

We work arms-length with policymakers in Congress and the executive branch on timely, practical AI policy issues, while also conducting original research into future-oriented topics that may arise under plausible AI trajectories that have yet to enter the mainstream. High level themes include frontier AI governance, robotics / reindustrialization, and institutional disruption.

Read more
Desired fellow characteristics

At Fourth Eon Biosecurity we're building adaptive, AI-native safeguards across the bioengineering 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 safety and biosecurity, aimed at reinforcing screening and generalizing detection beyond known threat signatures. Projects span mechanistic interpretability of bio foundation models, model evaluations for biosecurity-relevant capabilities, and agentic sequence analysis workflows.

Read more
Mentorship structure
Desired fellow characteristics
Project selection process

In this project, we will explore GPU side-channel attacks to extract information about model usage. A simple example is to observe (via radio, power fluctuations, acoustics, etc.) which experts were used in each forward pass of an MOE model, then use those observations to guess which tokens were produced.

Read more
Mentorship structure
Desired fellow characteristics
Project selection process

本研究流将聚焦生物安全防护措施相关项目。

Read more
Mentorship structure
Desired fellow characteristics
Project selection process

I'm interested in better understanding and controlling how post-training causes alignment-relevant behavior. This is a pretty broad area, and I’m open to many approaches to these problems! Potential areas of study / methods of attack might include model organisms, training run science/ablations, root causing strange behaviors, or studying how best to robustly induce behaviors or values or beliefs into models.

Read more
Desired fellow characteristics

Winter 2027 Mentors

The MATS Program is supported by a diverse and highly respected group of mentors — top-tier researchers, engineers, and thinkers working across AI alignment, governance, interpretability, and security.

Anthropic
,
Research Scientist
Juniper Ventures
,
Founder
University of Oxford
,
Group Leader
IAPS
,
Senior Researcher
Truthful AI
,
Research Lead
AVERI
,
Director of Standards
Eleos
,
Senior Research Lead
Alignment Research Center
,
Technical Advisor
AI Policy Network
,
Head of AI Policy
ACS Research, University of Toronto
,
Senior Researcher
Independent
,
Researcher
UK AISI
,
Research Scientist
Anthropic, University of Toronto
,
Associate Professor
AI Futures Project
,
研究员
Eleos
,
Managing Director
Halcyon Futures
,
Investor & Grantmaker
Thinking Machines
,
Member of Technical Staff
Redwood Research
,
Chief Scientist
Institute for AI Policy and Strategy
,
Research Associate
Anthropic
,
Member of Technical Staff
Foundation for American Innovation
,
Director of Artificial Intelligence & Chief Economist
Anthropic
,
Member of Technical Staff
Transluce
,
Co-Founder, Chief Scientist
Anthropic
,
Member of Technical Staff

Application

What are the key dates for MATS Winter 2027?

The timeline for the MATS Winter 2027 program is:‍

  • ‍Application final deadline: September 6th, 2026
  • Evaluations: September, October and early November
  • Offers sent: Early to mid-November
  • Program dates: January 19th to April 10th. The Winter 2027 Program has a time commitment of 40 hours per week over 12 weeks and takes place in-person in Berkeley, CA and London, UK. Remote or part-time participation is a possibility depending on your circumstances and mentor.‍
  • Extension phase: Possible 6 or 12-month extension for select fellows after the 12-week program, starting in December.
What if I am accepted by multiple streams?

Based on stream rankings of applicants and applicant rankings of streams, a final matching process uses both sides' rankings to send out a single offer.

How long does the application process take?

Stage 1 applications open on August 18th and close on September 6th, end of day anywhere on Earth. Offers go out in early to mid-November, and the program starts on January 19th.

What is a track?
What is a stream?
How many streams and tracks can I apply to?
Are the key dates flexible?
Who is eligible to apply?
Is this program a full-time commitment?
Can I update my application after submitting?
What is the policy on LLM usage?
What should I know about references?

Finances

What does “financial support” concretely entail?

MATS provides a stipend of $1600 per week for participation in the main program ($19,200 for the full 12-week program). Scholars who are participating and performing research for less than 40 hours/week and/or for less than 12 weeks will receive stipends proportional to their level of participation.

Separately from this stipend, MATS will provide scholars with travel to and from Berkeley or London, housing, office space, and lunch and dinner on weekdays.

Do I have to pay taxes on the grant I receive for the MATS Program?

MATS participants may have to pay taxes on their grants based on the rules of the countries in which they are a resident for tax purposes. The grants should be regarded as private grants from a non-profit entity provided to individuals for the purpose of independent research and participation in a US-based educational seminar program.

MATS Program

Is MATS officially affiliated with UC Berkeley? Will I get a student card?
Where does the program take place?
Can I participate remotely?
Can I join the program from outside the US?
What should I expect from my mentor?
What training will the program offer?
What are the main deliverables of the research program?
How can I share feedback with the MATS team?