collaborators

7 papers

stat.ML2026

Optimal Conformal Prediction under Epistemic Uncertainty

Alireza Javanmardi, Soroush H. Zargarbashi, Santo M. A. R. Thies +3

Conformal prediction (CP) is a widely used frequentist framework to quantify uncertainty by constructing prediction sets with user-specified marginal coverage guarantees. In practi…

cs.LG2026

Reward-Gated On-Policy Distillation

Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3

On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the tea…

cs.LG2026

Test-Time Training Undermines Safety Guardrails

Simone Antonelli, Sadegh Akhondzadeh, Aleksandar Bojchevski

Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval…

cs.LG2025

One Sample is Enough to Make Conformal Prediction Robust

Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski

For any black-box model, conformal prediction (CP) returns prediction sets guaranteed to include the true label with high adjustable probability. Robust CP (RCP) extends the guaran…

cs.LG2025

EvA: Evolutionary Attacks on Graphs

Mohammad Sadegh Akhondzadeh, Soroush H. Zargarbashi, Jimin Cao +1

Even a slight perturbation in the graph structure can cause a significant drop in the accuracy of graph neural networks (GNNs). Most existing attacks leverage gradient information…

cs.LG2025

Robust Conformal Prediction with a Single Binary Certificate

Soroush H. Zargarbashi, Aleksandar Bojchevski

Conformal prediction (CP) converts any model's output to prediction sets with a guarantee to cover the true label with (adjustable) high probability. Robust CP extends this guarant…