Research

I’m planning to add some notes here to explain some of my more interesting research projects. In the meantime, I’m just putting a number of selected publications here, categorized under some of my broader research categories. For a full list of my publications, see Google Scholar.

---

Post-training and Alignment of Large Language Models

Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback A Afsharrad, R Zhou, L Viano, S Lall, M Ghavamzadeh The Fourteenth International Conference on Learning Representations (ICLR 2026) Paper

One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise A Afzali, A Afsharrad, SS Mousavi, S Lall Reinforcement Learning Journal 2025 Paper

---

ML-Based Control and Optimization

Generalizable Spacecraft Trajectory Generation via Multimodal Learning with Transformers D Celestini, A Afsharrad, D Gammelli, T Guffanti, G Zardini, S Lall, E Capello, S D’Amico, M Pavone 2025 American Control Conference (ACC 2025) Paper

---

Constrained Linear Bandits

Convex Methods for Constrained Linear Bandits A Afsharrad, A Moradipari, S Lall 2024 European Control Conference (ECC 2024) Paper

Cooperative Multi-Agent Constrained Stochastic Linear Bandits A Afsharrad, P Oftadeh, A Moradipari, S Lall 2025 American Control Conference (ACC 2025) Paper

---

Miscellaneous

LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders B Khodabandeh, A Afzali, A Afsharrad, SS Mousavi, S Lall, S Amini, SM Moosavi-Dezfooli The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2024) Paper