activity
20242026
collaborators

5 papers

cs.CL2026

Selective Rotary Position Embedding

Sajad Movahedi, Timur Carstensen, Arshia Afzal +3

Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (\textit{RoPE}) encode positions through \textit{fixed-angle} rotations…

cs.AI2026

Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers

Sajad Movahedi, Vera Milovanović, Shlomo Libo Feigin +5

Looped architectures provide an inductive bias toward learning step-by-step procedures for tasks that require compositional reasoning. The number of effective layers reached by loo…

cs.LG2025

Fixed-Point RNNs: Interpolating from Diagonal to Dense

Sajad Movahedi, Felix Sarnthein, Nicola Muca Cirone +1

Linear recurrent neural networks (RNNs) and state-space models (SSMs) such as Mamba have become promising alternatives to softmax-attention as sequence mixing layers in Transformer…

cs.LG2025

Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture

Sajad Movahedi, Antonio Orvieto, Seyed-Mohsen Moosavi-Dezfooli

In this paper, we propose the , which argues that the input space curvature of a neural network remains invariant under transformati…

cs.IR2024

QEQR: An Exploration of Query Expansion Methods for Question Retrieval in CQA Services

Yasin Ghafourian, Sajad Movahedi, Azadeh Shakery

CQA services are valuable sources of knowledge that can be used to find answers to users' information needs. In these services, question retrieval aims to help users with their inf…