1 citations · 2 across the 6 of their papers we have counts for
6 papers
WaiT for the Signal: Simple Frequency-Aware Flow-Matching
Krunoslav Lehman Pavasovic, Théophane Vallaeys, Stéphane Mallat +4
As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation quality. However, standard flo…
A Differentiable Rank-Based Objective For Better Feature Learning
Krunoslav Lehman Pavasovic, David Lopez-Paz, Giulio Biroli +1
In this paper, we leverage existing statistical methods to better understand feature learning from data. We tackle this by modifying the model-free variable selection method, Featu…
Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms
Krunoslav Lehman Pavasovic, Jakob Verbeek, Giulio Biroli +1
Classifier-Free Guidance (CFG) is a widely adopted technique in diffusion and flow-based generative models, enabling high-quality conditional generation. A key theoretical challeng…
The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models
Anaelia Ovalle, Krunoslav Lehman Pavasovic, Louis Martin +5
Natural-language assistants are designed to provide users with helpful responses while avoiding harmful outputs, largely achieved through alignment to human preferences. Yet there…
Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent
Krunoslav Lehman Pavasovic, Alain Durmus, Umut Simsekli
A recent line of empirical studies has demonstrated that SGD might exhibit a heavy-tailed behavior in practical settings, and the heaviness of the tails might correlate with the ov…
MARS: Meta-Learning as Score Matching in the Function Space
Krunoslav Lehman Pavasovic, Jonas Rothfuss, Andreas Krause
Meta-learning aims to extract useful inductive biases from a set of related datasets. In Bayesian meta-learning, this is typically achieved by constructing a prior distribution ove…