collaborators

12 papers

cs.CL2026

Masked Language Flow Models

Iskander Azangulov, Kianoosh Ashouritaklimi, Leo Zhang +2

Masked Diffusion Models (MDMs) promise fast, parallel language generation, but their reverse transition factorises across token positions -- an approximation that breaks down in th…

stat.ML2026

Variance-Tilted Diffusion Models for Diverse Sampling

Iskander Azangulov, Leo Zhang, Kianoosh Ashouritaklimi

Diffusion models are typically sampled independently, even when the downstream objective is to obtain a diverse set of candidates. We introduce a variance-weighted batch distributi…

cs.LG2026

Exact Posterior Score Estimation for Solving Linear Inverse Problems

Abbas Mammadov, Ozgur Kara, Kaan Oktay +5

Diffusion and flow-based models learn powerful data priors by training a denoiser to reverse Gaussian corruption. To use this prior to solve a linear inverse problem, one needs to…

stat.ML2026

Matérn Gaussian Processes on Graphs

Viacheslav Borovitskiy, Iskander Azangulov, Alexander Terenin +3

Gaussian processes are a versatile framework for learning unknown functions in a manner that permits one to utilize prior information about their properties. Although many differen…

cs.LG2026

Sampling from Flow Language Models via Marginal-Conditioned Bridges

Iskander Azangulov, Leo Zhang

Flow Language Models (FLMs) are a recently introduced class of language models which adapt continuous flow matching for one-hot encoded token sequences. Their denoisers have a spec…

math.ST2026

Time-sensitive anytime-valid testing

Eugenio Clerico, Tobias Wegel, Iskander Azangulov +1

Anytime-valid tests allow evidence to be checked during data collection: one can either continue testing or stop and reject the null while still controlling type-I error. Yet, in m…