9 papers
Energy-Regularized Spatial Masking: A Novel Approach to Enhancing Robustness and Interpretability in Vision Models
Tom Devynck, Bilal Faye, Djamel Bouchaffra +3
Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant comput…
Adaptive Head Budgeting for Efficient Multi-Head Attention
Bilal Faye, Abdoulaye Mbaye, Hanane Azzag +1
Multi-head attention enables Transformers to capture diverse representations, but all attention heads are typically activated for every input, regardless of task complexity. For co…
Value-Free Policy Optimization via Reward Partitioning
Bilal Faye, Hanane Azzag, Mustapha Lebbah
Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by di…
Coalition Free Energy and Adaptive Precision in Multi-Agent Cooperation
Djamel Bouchaffra, Faycal Ykhlef, Mustapha Lebbah +1
Cooperative multi-agent systems require robust mechanisms for credit assignment under uncertainty. Here we introduce a variational framework, termed the Game-Theoretic Free Energy…
A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics
Djamel Bouchaffra, Faycal Ykhlef, Mustapha Lebbah +1
Collective intelligence emerges across biological, physical, and artificial systems without central coordination, yet a unifying principle governing such behaviour remains elusive.…
NeuroGame Transformer: Gibbs-Inspired Attention Driven by Game Theory and Statistical Physics
Djamel Bouchaffra, Faycal Ykhlef, Hanene Azzag +2
Standard attention mechanisms in transformers are limited by their pairwise formulation, which hinders the modeling of higher-order dependencies among tokens. We introduce the Neur…