collaborators

5 papers

cs.LG2025

Steering Pretrained Drafters during Speculative Decoding

Frédéric Berdoz, Peer Rheinboldt, Roger Wattenhofer

Speculative decoding accelerates language model inference by separating generation into fast drafting and parallel verification. Its main limitation is drafter-verifier misalignmen…

cs.SD2025

High-Fidelity Speech Enhancement via Discrete Audio Tokens

Luca A. Lanzendörfer, Frédéric Berdoz, Antonis Asonitis +1

Recent autoregressive transformer-based speech enhancement (SE) methods have shown promising results by leveraging advanced semantic understanding and contextual modeling of speech…

cs.CV2025

Text-to-Scene with Large Reasoning Models

Frédéric Berdoz, Luca A. Lanzendörfer, Nick Tuninga +1

Prompt-driven scene synthesis allows users to generate complete 3D environments from textual descriptions. Current text-to-scene methods often struggle with complex geometries and…

cs.CY2025

Recommender Systems for Democracy: Toward Adversarial Robustness in Voting Advice Applications

Frédéric Berdoz, Dustin Brunner, Yann Vonlanthen +1

Voting advice applications (VAAs) help millions of voters understand which political parties or candidates best align with their views. This paper explores the potential risks thes…

cs.AI2024

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies

Frédéric Berdoz, Roger Wattenhofer

While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objecti…