1 citations · 1 across the 17 of their papers we have counts for
18 papers
Geometric Iterative Retrieval for Neural Audio Codec Resynthesis
Leo Schmidt-Traub, Frédéric Berdoz, Luca A. Lanzendörfer +1
Neural audio codecs based on Residual Vector Quantization (RVQ) have become the dominant discrete representation for token-based general audio generation, yet resynthesizing high-q…
Post-Training Speech Enhancement Language Models with Perceptual Rewards
Frédéric Berdoz, Luca A. Lanzendörfer, Antonis Asonitis +1
Speech enhancement language models achieve strong results when trained on discrete audio tokens, but their optimization relies on token-level cross-entropy rather than the perceptu…
Data Attribution in Large Language Models via Bidirectional Gradient Optimization
Frédéric Berdoz, Luca A. Lanzendörfer, Kaan Bayraktar +1
Large Language Models (LLMs) are increasingly deployed across diverse applications, raising critical questions for governance, accountability, and data provenance. Understanding wh…
Reasoning Structure of Large Language Models
Frédéric Berdoz, Luca A. Lanzendörfer, Fabian Farestam +1
Large reasoning models (LRMs) are often evaluated using metrics such as final-answer accuracy or token count. However, identical scores on these metrics can hide fundamentally diff…
TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding
Peer Rheinboldt, Frédéric Berdoz, Roger Wattenhofer
One-shot block drafters for speculative decoding generate the full draft in a single forward pass, achieving strong throughput by eliminating sequential token generation. However,…
N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation
Aleksander Lorenc, Frédéric Berdoz, Joël Mathys +1
Improving the inference efficiency of autoregressive transformers typically means reducing FLOPs per token, usually through approximations that degrade model quality. We introduce…
WorldSpeech: A Multilingual Speech Corpus from Around the World
Antonis Asonitis, Luca A. Lanzendörfer, Frédéric Berdoz +1
Automatic speech recognition (ASR) performs well for high-resource languages with abundant paired audio-transcript data, but its accuracy degrades sharply for most languages due to…
Reasoning Boosts Opinion Alignment in LLMs
Frédéric Berdoz, Yann Billeter, Yann Vonlanthen +1
Opinion modeling aims to capture individual or group political preferences, enabling applications such as digital democracies, where models could help shape fairer and more popular…
Can AI Agents Agree?
Frédéric Berdoz, Leonardo Rugli, Roger Wattenhofer
Large language models are increasingly deployed as cooperating agents, yet their behavior in adversarial consensus settings has not been systematically studied. We evaluate LLM-bas…
Subliminal Signals in Preference Labels
Isotta Magistrali, Frédéric Berdoz, Sam Dauncey +1
As AI systems approach superhuman capabilities, scalable oversight increasingly relies on LLM-as-a-judge frameworks where models evaluate and guide each other's training. A core as…
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…
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…
Alignment-Aware Decoding
Frédéric Berdoz, Luca A. Lanzendörfer, René Caky +1
Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and effective method for improving a…
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…
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…
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…
Scalable Collaborative Learning via Representation Sharing
Frédéric Berdoz, Abhishek Singh, Martin Jaggi +1
Privacy-preserving machine learning has become a key conundrum for multi-party artificial intelligence. Federated learning (FL) and Split Learning (SL) are two frameworks that enab…
Fundamentals of Task-Agnostic Data Valuation
Mohammad Mohammadi Amiri, Frederic Berdoz, Ramesh Raskar
We study valuing the data of a data owner/seller for a data seeker/buyer. Data valuation is often carried out for a specific task assuming a particular utility metric, such as test…