Ismail Labiad

2 accepted papers

2026

Soft Tokens, Hard Truths

Natasha Butt, Ariel Kwiatkowski, Ismail Labiad, Julia Kempe, Yann Ollivier

ICLR 2026poster

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 mixture of discrete tokens could simulate a superposition of several reasoning paths simultaneously. Theoretical result…

Cited by 17 Source ↗Scholar ↗

2025

Watermarking Autoregressive Image Generation

Nikola Jovanović, Ismail Labiad, Tomas Soucek, Martin Vechev, Pierre Fernandez

NeurIPS 2025poster

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has attempted to watermark their outputs at the token level. In this w…

Cited by 0 Source ↗code ↗Scholar ↗