collaborators

7 papers

cs.AI2026

LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation

Gabriele Cesa, Thomas Hehn, Aleix Torres-Camps +4

Parallel LLM test-time scaling techniques (e.g., best-of-) require drawing sequences conditioned on the same input prompt. These methods boost accuracy while exploiting th…

cs.LG2025

A Probabilistic Approach to Pose Synchronization for Multi-Reference Alignment with Applications to MIMO Wireless Communication Systems

Rob Romijnders, Gabriele Cesa, Christos Louizos +2

From molecular imaging to wireless communications, the ability to align and reconstruct signals from multiple misaligned observations is crucial for system performance. We study th…

eess.SP2025

ReQuestNet: A Foundational Learning model for Channel Estimation

Kumar Pratik, Pouriya Sadeghi, Gabriele Cesa +5

In this paper, we present a novel neural architecture for channel estimation (CE) in 5G and beyond, the Recurrent Equivariant UERS Estimation Network (ReQuestNet). It incorporates…

cs.AI2025

Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving

Sara Rajaee, Kumar Pratik, Gabriele Cesa +1

The most promising recent methods for AI reasoning require applying variants of reinforcement learning (RL) either on rolled out trajectories from the LLMs, even for the step-wise…

cs.LG2025

A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs

Lars Veefkind, Gabriele Cesa

Steerable convolutional neural networks (SCNNs) enhance task performance by modelling geometric symmetries through equivariance constraints on weights. Yet, unknown or varying symm…

cs.LG2025

Neural Lattice Reduction: A Self-Supervised Geometric Deep Learning Approach

Giovanni Luca Marchetti, Gabriele Cesa, Pratik Kumar +1

Lattice reduction is a combinatorial optimization problem aimed at finding the most orthogonal basis in a given lattice. The Lenstra-Lenstra-Lovász (LLL) algorithm is the best alg…