6 papers · 1 filter
Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
Amirhossein Afsharrad, Ruida Zhou, Luca Viano +2
Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal prefere…
LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
Borna Khodabandeh, Amirabbas Afzali, Amirhossein Afsharrad +4
Visual encoders have become fundamental components in modern computer vision pipelines. However, ensuring robustness against adversarial perturbations remains a critical challenge.…
One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise
Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi +1
Large Language Models (LLMs) have made significant strides in generating human-like responses, largely due to preference alignment techniques. However, these methods often assume u…
Cooperative Multi-Agent Constrained Stochastic Linear Bandits
Amirhossein Afsharrad, Parisa Oftadeh, Ahmadreza Moradipari +1
In this study, we explore a collaborative multi-agent stochastic linear bandit setting involving a network of agents that communicate locally to minimize their collective regre…
Markov Decision Processes with Noisy State Observation
Amirhossein Afsharrad, Sanjay Lall
This paper addresses the challenge of a particular class of noisy state observations in Markov Decision Processes (MDPs), a common issue in various real-world applications. We focu…
Convex Methods for Constrained Linear Bandits
Amirhossein Afsharrad, Ahmadreza Moradipari, Sanjay Lall
Recently, bandit optimization has received significant attention in real-world safety-critical systems that involve repeated interactions with humans. While there exist various alg…