Nicolas Flammarion

7

Papers

422

Total Citations

Papers (7)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Is In-Context Learning Sufficient for Instruction Following in LLMs?

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

NeurIPS 2025arXiv

Selective induction Heads: How Transformers Select Causal Structures in Context

Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points

Long-Context Linear System Identification

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning