16 papers
From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation
Amal Akli, Melissa Akli, Cedric Richter +2
Large language models are known to be sensitive to prompt formulation. Even minor variations in wording can substantially degrade performance. This sensitivity reveals an opportuni…
CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning
Ayoub Belouadah, Sylvain Kubler, Yves Le Traon
Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as Constrained Markov Decision Processes (CMDPs). Whil…
Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search
Chaimaa Medjadji, Sylvain Kubler, Yves Le Traon +3
Federated Learning (FL) enables collaborative model training without centralizing data. However, real-world deployments must simultaneously address statistical heterogeneity across…
Federated Imputation under Heterogeneous Feature Spaces
Imane Hocine, Chaimaa Medjadji, Sylvain Kubler +2
Federated Learning (FL) enables collaborative training across decentralized clients, but most methods assume aligned feature schemas, an assumption that rarely holds in tabular set…
Centralized vs Decentralized Federated Learning: A trade-off performance analysis
Chaimaa Medjadji, Guilain Leduc, Sylvain Kubler +1
Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed edge devices while preserving data privacy especially with the huge…
From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation
Yu Pan, Yang Hou, Xiongfei Wu +4
Compositional speech-to-speech translation (S2ST) systems built upon speech large language models (SpeechLLMs) have recently shown promising performance. However, existing S2ST sys…