Oliver Heinimann — accepted AI-conference papers

2026

KernelFusion: Zero-Shot Blind Super-Resolution via Patch Diffusion

Oliver Heinimann, Tal Zimbalist, Assaf Shocher, michal Irani

ICLR 2026poster

Traditional super-resolution (SR) methods assume an "ideal'' downscaling SR-kernel (e.g., bicubic downscaling) between the high-resolution (HR) image and the low-resolution (LR) image. Such methods fail once the LR images are generated differently. Current blind-SR methods aim to remove this assumpt…

Cited by 0 Source ↗Scholar ↗

2025

DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers

Navve Wasserman, Oliver Heinimann, Yuval Golbari, Tal Zimbalist, Eli Schwartz, Michal Irani

EMNLP 2025

Rerankers play a critical role in multimodal Retrieval-Augmented Generation (RAG) by refining ranking of an initial set of retrieved documents. Rerankers are typically trained using hard negative mining, whose goal is to select pages for each query which rank high, but are actually irrelevant. Howev

Cited by 0 Source ↗PDF ↗Scholar ↗