collaborators

5 papers

cs.CL2026

LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding

Matan Rusanovsky, Yoav Miron, Roy Uziel +4

Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel. A diffusion-style block head such as DFlash is an at…

cs.LG2026

Learn from Your Mistakes: Self-Correcting Masked Diffusion Models

Yair Schiff, Omer Belhasin, Roy Uziel +6

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models, enabling parallel token generation while achieving competitive performance. Despite…

cs.CL2026

CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language

Roy Uziel, Omer Belhasin, Itay Levy +4

Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation but often struggle with token dependencies and semantic incoherence due to t…

cs.CV2025

Advancing Image Classification with Discrete Diffusion Classification Modeling

Omer Belhasin, Shelly Golan, Ran El-Yaniv +1

Image classification is a well-studied task in computer vision, and yet it remains challenging under high-uncertainty conditions, such as when input images are corrupted or trainin…

cs.LG2025

Uncertainty-Aware PPG-2-ECG for Enhanced Cardiovascular Diagnosis using Diffusion Models

Omer Belhasin, Idan Kligvasser, George Leifman +7

Analyzing the cardiovascular system condition via Electrocardiography (ECG) is a common and highly effective approach, and it has been practiced and perfected over many decades. EC…