8 papers
LogicVal:A Logic-Formalized Benchmark for Constraint Satisfaction in Text-to-Image Generation
Savitha Sam Abraham, Marjan Alirezaie, Hossein Rahnama
Text-to-Image (T2I) generative models have made significant progress in producing high-fidelity images from natural-language prompts. Alongside this progress, numerous benchmarks h…
Certifying Interventional Agreement Among Observationally Equivalent Causal Models
Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie +1
Observationally equivalent causal models can still disagree about what happens under intervention, because interventions create inputs that never occur in observational data. We in…
Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents
Hafsa Akbar, Daniel Platnick, Marjan Alirezaie +2
LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified, and collective outcomes inhe…
Share No More Than the Request Requires: Federated Disclosure for Perspective-Aware AI
Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie +1
Modern AI systems bring societal risks such as mass surveillance, extreme concentrations of power, and loss of user autonomy---calling into question a model where third-parties col…
Situation Graph Prediction for User Perspective Modeling
Jisung Shin, Daniel Platnick, Marjan Alirezaie +1
Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences. Progress is limited by a data bottleneck: digital footprints a…
Structured Personalization: Modeling Constraints as Matroids for Data-Minimal LLM Agents
Daniel Platnick, Marjan Alirezaie, Hossein Rahnama
Personalizing Large Language Model (LLM) agents requires conditioning them on user-specific data, creating a critical trade-off between task utility and data disclosure. While the…
ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents
Daniel Platnick, Mohamed E. Bengueddache, Marjan Alirezaie +3
Generative agents powered by language models are increasingly deployed for long-horizon tasks. However, as long-term memory context grows over time, they struggle to maintain coher…
Perspective-Aware AI in Extended Reality
Daniel Platnick, Matti Gruener, Marjan Alirezaie +3
AI-enhanced Extended Reality (XR) aims to deliver adaptive, immersive experiences-yet current systems fall short due to shallow user modeling and limited cognitive context. We intr…