Nicolas Flammarion

Transformers Learn Latent Mixture Models In-Context via Mirror Descent

On the Adversarial Robustness of Discrete Image Tokenizers

Incremental Learning in Transformers for In-Context Associative Recall

Incremental Learning of Sparse Attention Patterns in Transformers

Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks

Learning Parametric Distributions from Samples and Preferences

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

Long-Context Linear System Identification

Selective Induction Heads: How Transformers Select Causal Structures in Context

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Does Refusal Training in LLMs Generalize to the Past Tense?

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

Simplicity Bias and Optimization Threshold in Two-Layer Networks