Paper-Conference

Chain-of-Thought Is Not Explainability

F. Barez, T.-Y. Wu, I. Arcuschin, M. Lan, V. Wang, N. Siegel, N. Collignon, C. Neo, I. Lee, A. Paren, J. Yan, A. Bibi, D. Fornasiere, R. Trager, Y. Elazar, Y. Bengio

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors

M. Chaudhary, F. Barez

Code Review Bench: An Automated Benchmark for Evaluating the Software Factory

A. Zhang, N.F. Oozeer, A. Zverianskii, D. Ng, T. Pejovic, A. García, J. Clyne, R. Setia, A. Utture, E.J. Ginsberg, S.K. Upadhyay, F. Barez

Pretraining Curricula Enable Selective Fine-tuning

K.J. Sandbrink, M. Whitefield, S.A. Bruijns, J. Rubruck, L.T. Hunt, F. Barez, C. Summerfield

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

C. Li, P. Lu, X. Pan, F. Barez, M. Yang

Interpretability Can Be Actionable

H. Orgad, F. Barez, T. Haklay, I. Lee, M. Mosbach, A. Reusch, N. Saphra, Et Al.

Old Habits Die Hard: How Conversational History Geometrically Traps LLMs

A. Simhi, F. Barez, M. Tutek, Y. Belinkov, S. B. Cohen

Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics

S. Biderman, M. A. Khan, N. Mireshghallah, C. Arnett, F. Barez, N. Saphra

Position: There Are Futures That Benchmark-Driven AI Cannot See

S. Lotfi, A. Iranmanesh, L. Naghashyar, A. Shirali, F. Nateghi Haredasht, S. Koyejo, P. Torr, Y. S. Lee, F. Barez, J. Lehman, P. Norvig, A. Narayanan

Position: Token Taxes Can Mitigate AI's Economic Risks

L. Irwin, T.-Y. Wu, F. Barez