activity
20242026
collaborators

5 papers

cs.LG2026

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

Ismail Labiad, Mathurin Videau, Matthieu Kowalski +4

Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, exposing gradients during training can leak se…

cs.CL2026

Likelihood-Based Reward Designs for General LLM Reasoning

Ariel Kwiatkowski, Natasha Butt, Ismail Labiad +2

Fine-tuning large language models (LLMs) on reasoning benchmarks via reinforcement learning requires a specific reward function, often binary, for each benchmark. This comes with t…

cs.LG2025

Watermarking Autoregressive Image Generation

Nikola Jovanović, Ismail Labiad, Tomáš Souček +2

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation mod…

cs.CL2025

Soft Tokens, Hard Truths

Natasha Butt, Ariel Kwiatkowski, Ismail Labiad +2

The use of continuous instead of discrete tokens during the Chain-of-Thought (CoT) phase of reasoning LLMs has garnered attention recently, based on the intuition that a continuous…

cs.AI2024

Log-normal Mutations and their Use in Detecting Surreptitious Fake Images

Ismail Labiad, Thomas Bäck, Pierre Fernandez +5

In many cases, adversarial attacks are based on specialized algorithms specifically dedicated to attacking automatic image classifiers. These algorithms perform well, thanks to an…