Felipe Avelar

Research

Felipe is a co-author of the verification framework paper. His contributions centre on the symbolic-execution side of the framework — the analysis of environment dynamics that lets the framework reason about the policy's effect over time.

He has been with alphabell since 2020 and is based in São Paulo. He is one of the lab's primary contacts for the Latin American academic AI safety community.

Felipe maintains a personal monorepo of symbolic-execution benchmarks that the lebesgue-22 verification work uses extensively.

Background

Ph.D. computer science, USP São Paulo, 2014.

Prior to alphabell: USP; Cantor Initiative; Praxis AI Studies.

Selected publications

• Mar 2025 · ab-verifiable-pol
  Toward Formal Verification of Learned Policies in Bounded Environments
  Aviva Stern, Sun Kyung-min, Felipe Avelar
• Sep 2025 · ab-scalable-overs
  Scalable Oversight for Multi-Step Agent Systems: a Debate-Plus-Trace Approach
  Ifeoma Nwosu-Howard, Hiroshi Tanigawa, Maral Lotfi, Ruth Wernicke
• Sep 2024 · ab-interpretabili
  Interpretability Cell Pairing: how every dual-use capability run gets a watchful sibling
  Karima Belkadi, Hester Vandekerckhove, Yuki Cho
• May 2025 · ab-mechanistic-ci
  Mechanistic Circuit Analysis at Frontier Scale: cells as a unit of interpretability
  Jiang Yifei, Nico Almgren, Karima Belkadi, Hester Vandekerckhove
• Nov 2024 · ab-sandboxed-self
  Sandboxed Self-Modification: a confinement specification and implementation
  Liora Sabatini, Cheung Wai-Lin, Marek Holub

Full publications index →

Recent talks

• Symbolic execution of environment dynamics, OOPSLA 2025