works on

From the 1 of 10 linked papers with an AI index.

collaborators

10 papers

stat.ML2026

Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents

Amirmohammad Farzaneh, Osvaldo Simeone

The paper introduces Think Short, Defer Smart (TSDS), a framework for edge-deployed LLM agents that stops on-device reasoning when actions stabilize and defers uncertain actions to…

cs.LG2026

Synthetic Counterfactual Labels for Efficient Conformal Counterfactual Inference

Amirmohammad Farzaneh, Matteo Zecchin, Osvaldo Simeone

This work addresses the problem of constructing reliable prediction intervals for individual counterfactual outcomes. Existing conformal counterfactual inference (CCI) methods prov…

cs.LG2026

Optimized Certainty Equivalent Risk-Controlling Prediction Sets

Jiayi Huang, Amirmohammad Farzaneh, Osvaldo Simeone

In safety-critical applications such as medical image segmentation, prediction systems must provide reliability guarantees that extend beyond conventional expected loss control. Wh…

cs.IT2026

SCAN-BEST: Sub-6GHz-Aided Near-field Beam Selection with Formal Reliability Guarantees

Weicao Deng, Binpu Shi, Min Li +1

As millimeter-wave (mmWave) MIMO systems adopt larger antenna arrays, near-field propagation becomes increasingly prominent, especially for users close to the transmitter. Traditio…

cs.AI2026

Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control

Amirmohammad Farzaneh, Salvatore D'Oro, Osvaldo Simeone

Large language model (LLM)-powered agents can translate high-level user intents into plans and actions in an environment. Yet after observing an outcome, users may wonder: What if…

cs.LG2025

Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offs

Haifeng Wen, Hong Xing, Osvaldo Simeone

For modern artificial intelligence (AI) applications such as large language models (LLMs), the training paradigm has recently shifted to pre-training followed by fine-tuning. Furth…