activity
20242026
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.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.CV2025

Text-to-Image Generation Via Energy-Based CLIP

Roy Ganz, Michael Elad

Joint Energy Models (JEMs), while drawing significant research attention, have not been successfully scaled to real-world, high-resolution datasets. We present CLIP-JEM, a novel ap…

cs.CV2024

Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination

Shelly Golan, Roy Ganz, Michael Elad

The recently introduced Consistency models pose an efficient alternative to diffusion algorithms, enabling rapid and good quality image synthesis. These methods overcome the slowne…