8 papers
Wireless Physical-Layer Foundation Models: Architectures, Learning Paradigms, Applications, and Deployment
Mohammad Cheraghinia, Davide Buffelli, Liu Li +6
Foundation models, i.e., large neural networks pretrained on broad unlabeled data and adapted to many downstream tasks, have reshaped natural language processing and computer visio…
A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback
Joseph Lazzaro, Davide Buffelli, Da-shan Shiu +1
Preference feedback, in the form of pairwise comparisons rather than scalar scores, has seen increasing use in applications such as human-, laboratory-, and expert-in-the-loop desi…
Cross-Tokenizer LLM Distillation through a Byte-Level Interface
Avyav Kumar Singh, Yen-Chen Wu, Alexandru Cioba +2
Cross-tokenizer distillation (CTD), the transfer of knowledge from a teacher to a student language model when the two use different tokenizers, remains a largely unsolved problem.…
Towards a Foundation Model for Communication Systems
Davide Buffelli, Sowmen Das, Yu-Wei Lin +5
Artificial Intelligence (AI) has demonstrated unprecedented performance across various domains, and its application to communication systems is an active area of research. While cu…
Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity
Chan-Jan Hsu, Davide Buffelli, Jamie McGowan +4
Recent advances in large language models (LLMs) have demonstrated the power of reasoning through self-generated chains of thought. Multiple reasoning agents can collaborate to rais…
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
Davide Buffelli, Jamie McGowan, Wangkun Xu +4
Second-order optimization has been shown to accelerate the training of deep neural networks in many applications, often yielding faster progress per iteration on the training loss…
Deep Equilibrium Algorithmic Reasoning
Dobrik Georgiev, JJ Wilson, Davide Buffelli +1
Neural Algorithmic Reasoning (NAR) research has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. However, most previous approaches have a…
The Deep Equilibrium Algorithmic Reasoner
Dobrik Georgiev, Pietro Liò, Davide Buffelli
Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. Doing so, however, has always used a rec…