activity
20242026
collaborators

11 papers

cs.CY2026

The 2026 Singapore Consensus on Global AI Safety Research Priorities

Stephen Casper, Oskar Galeev, Yoshua Bengio +117

Frontier AI capabilities and autonomy are advancing rapidly. A growing number of real-world incidents make a trusted AI ecosystem essential to embracing AI with confidence. The 202…

cs.AI2025

The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features

Jeremias Ferrao, Matthijs van der Lende, Ilija Lichkovski +1

Prevailing alignment methods induce opaque parameter changes, obscuring what models truly learn. To address this, we introduce Feature Steering with Reinforcement Learning (FSRL),…

cs.CL2025

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs

Minh Nhat Nguyen, Andrew Baker, Clement Neo +3

Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. Popular sampling methods like top-p…

cs.LG2025

TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research

Abir Harrasse, Philip Quirke, Clement Neo +3

Mechanistic interpretability research faces a gap between analyzing simple circuits in toy tasks and discovering features in large models. To bridge this gap, we propose text-to-SQ…

cs.CY2025

Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models

Philip Quirke, Narmeen Oozeer, Chaithanya Bandi +8

This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of companies limits innovation and…

cs.LG2025

Understanding Addition and Subtraction in Transformers

Philip Quirke, Clement Neo, Fazl Barez

We use integer addition and subtraction as a controlled, exactly-solvable testbed for what can be said with confidence about the algorithm a low-loss transformer implements - logic…