5 papers
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…
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…
Watermarking Autoregressive Image Generation
Nikola JovanoviÄ, Ismail Labiad, Tomáš SouÄek +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…
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…
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…