1 citations · 1 across the 20 of their papers we have counts for
21 papers
Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards
Tianyu Liu, Davide Belli, Bence Major +2
Training LLM agents on long-horizon interactive tasks with reinforcement learning typically relies on human-annotated tasks and reliable verification, both expensive to construct f…
When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
Corrado Rainone, Davide Belli, Bence Major +1
The design space of agentic AI inference spans two extremes: frontier large language models (LLMs), typically hosted in the cloud and offering strong performance across a wide rang…
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…
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
Victor Conchello Vendrell, Arnau Padres Masdemont, Niccolò Grillo +3
Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermedia…
Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi
\ac{CoT} prompting improves LLM accuracy on complex tasks but often increases token usage and inference cost. Existing ``Budget Forcing'' methods reduce cost via fine-tuning with h…
LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents
Amin Rakhsha, Thomas Hehn, Pietro Mazzaglia +3
Large language models can perform well on many isolated tasks, yet they continue to struggle on multi-turn, long-horizon agentic problems that require skills such as planning, stat…
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…
Fundamental bounds on efficiency-confidence trade-off for transductive conformal prediction
Arash Behboodi, Alvaro H. C. Correia, Fabio Valerio Massoli +1
Transductive conformal prediction addresses the simultaneous prediction for multiple data points. Given a desired confidence level, the objective is to construct a prediction set t…
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…
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…
On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing
Arash Behboodi, Gabriele Cesa
Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not cle…
Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits
Ashish Khisti, M. Reza Ebrahimi, Hassan Dbouk +3
We consider multi-draft speculative sampling, where the proposal sequences are sampled independently from different draft models. At each step, a token-level draft selection scheme…
Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problems
Gianluigi Silvestri, Fabio Valerio Massoli, Tribhuvanesh Orekondy +2
A promising way to mitigate the expensive process of obtaining a high-dimensional signal is to acquire a limited number of low-dimensional measurements and solve an under-determine…
Variational Learning ISTA
Fabio Valerio Massoli, Christos Louizos, Arash Behboodi
Compressed sensing combines the power of convex optimization techniques with a sparsity-inducing prior on the signal space to solve an underdetermined system of equations. For many…
Simulating, Fast and Slow: Learning Policies for Black-Box Optimization
Fabio Valerio Massoli, Tim Bakker, Thomas Hehn +2
Simulators are vital in science and engineering, as they faithfully model the influence of design parameters on real-world observations. Optimizing design parameters to minimize a…
Differentiable and Learnable Wireless Simulation with Geometric Transformers
Thomas Hehn, Markus Peschl, Tribhuvanesh Orekondy +2
Modelling the propagation of electromagnetic wireless signals is critical for designing modern communication systems. Wireless ray tracing simulators model signal propagation based…
An Information Theoretic Perspective on Conformal Prediction
Alvaro H. C. Correia, Fabio Valerio Massoli, Christos Louizos +1
Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probab…
Vision-Assisted Digital Twin Creation for mmWave Beam Management
Maximilian Arnold, Bence Major, Fabio Valerio Massoli +2
In the context of communication networks, digital twin technology provides a means to replicate the radio frequency (RF) propagation environment as well as the system behaviour, al…
Algebraic Topological Networks via the Persistent Local Homology Sheaf
Gabriele Cesa, Arash Behboodi
In this work, we introduce a novel approach based on algebraic topology to enhance graph convolution and attention modules by incorporating local topological properties of the data…
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 algo…
Transformer-Based Neural Surrogate for Link-Level Path Loss Prediction from Variable-Sized Maps
Thomas M. Hehn, Tribhuvanesh Orekondy, Ori Shental +7
Estimating path loss for a transmitter-receiver location is key to many use-cases including network planning and handover. Machine learning has become a popular tool to predict wir…