Wen X.
AI Safety Researcher. Ex-Meta Integrity Tech Lead.
- Role
- Researcher at MATS Research
- Location
- San Francisco, CA, US
- LinkedIn followers
- 500 followers
Experience
Researcher
Jun 2025 — Present · Berkeley, CA, US
Conducting monitorability research with Deepmind mentors David Lindner and Erik Jenner- Findings used by Anthropic in Claude Opus 4.6 safety evaluations and cited by OpenAI’s Monitoring Monitorability paper- CoT obfuscation paper published at NeurIPS FoRLM workshop. Model target low rate action eval paper accepted at ICLR 2026 Trustworthy AI Workshop. Both papers under review at ICML 2026.
Education
Rice University
BS, Computer Science with Applied Math Focus
Find verified contacts for anyone on LinkedIn
Unifers gives sales teams verified emails and direct dials, enriched profiles, and outreach that lands in the inbox.
Free plan included · No credit card required
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.