7 papers
Bridging Spherical Black-Box Optimizers
Johannes Ackermann, Stefano Peluchetti
When gradient information is unavailable, black-box optimization (BBO) methods provide a practical alternative. While Evolution Strategies (ES), Consensus-Based Optimization (CBO),…
KamonBench: A Grammar-Based Dataset for Evaluating Compositional Factor Recovery in Vision-Language Models
Richard Sproat, Stefano Peluchetti
Kamon (family crests) are an important part of Japanese culture and a natural test case for compositional visual recognition: each crest combines a small number of symbolic choices…
Latent-Augmented Discrete Diffusion Models
Dario Shariatian, Alain Durmus, Umut Simsekli +1
Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored rev…
Sparser, Faster, Lighter Transformer Language Models
Edoardo Cetin, Stefano Peluchetti, Emilio Castillo +3
Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging uns…
Binomial flows: Denoising and flow matching for discrete ordinal data
Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti
Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, thi…
Function-Space MCMC for Bayesian Wide Neural Networks
Lucia Pezzetti, Stefano Favaro, Stefano Peluchetti
Bayesian Neural Networks represent a fascinating confluence of deep learning and probabilistic reasoning, offering a compelling framework for understanding uncertainty in complex p…