7 papers
Flow Duality and Source Geometry for Categorical Generation
Etrit Haxholli
Continuous and discrete flow matching are usually treated as separate constructions. This paper identifies a duality between them: projecting continuous convex-interpolant flows wi…
Guideline2Graph: Profile-Aware Multimodal Parsing for Executable Clinical Decision Graphs
Onur Selim Kilic, Yeti Z. Gurbuz, Cem O. Yaldiz +4
Clinical practice guidelines are long, multimodal documents whose branching recommendations are difficult to convert into executable clinical decision support (CDS), and one-shot p…
Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models
Etrit Haxholli, Yeti Z. Gurbuz, Ogul Can +1
While continuous diffusion models excel in modeling continuous distributions, their application to categorical data has been less effective. Recent work has shown that ratio-matchi…
Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching
Etrit Haxholli, Yeti Z. Gurbuz, Ogul Can +1
Discrete flow matching, a recent framework for modeling categorical data, has shown competitive performance with autoregressive models. However, unlike continuous flow matching, th…
On Tail Decay Rate Estimation of Loss Function Distributions
Etrit Haxholli, Marco Lorenzi
The study of loss function distributions is critical to characterize a model's behaviour on a given machine learning problem. For example, while the quality of a model is commonly…
Enhanced Distribution Modelling via Augmented Architectures For Neural ODE Flows
Etrit Haxholli, Marco Lorenzi
While the neural ODE formulation of normalizing flows such as in FFJORD enables us to calculate the determinants of free form Jacobians in O(D) time, the flexibility of the transfo…