3 papers
cs.CL2026
MACRO: Markov Chain Routing of Transformer Layers
Paweł Batorski, Abtin Pourhadi, Akylgali Aitaza +2
Standard Large Language Models (LLMs) execute layers sequentially. Dynamic layer routing, i.e. search for a different execution path through layers involving layer repetitions, ski…
cs.CL2026
Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?
Pawel Batorski, Abtin Pourhadi, Jerzy Sarosiek +2
Large language models are highly sensitive to prompts, but this sensitivity is usually studied through task-relevant instructions, demonstrations, or reasoning cues. In this paper,…
cs.CV2026
Normalized Matching Transformer
Abtin Pourhadi, Paul Swoboda
We introduce the Normalized Matching Transformer (NMT), a deep learning approach for efficient and accurate sparse semantic keypoint matching between image pairs. NMT consists of a…