7 papers
Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval
Sana Ayromlou, Purvi Sehgal, Pradyumna Narayana
Foundation-model agents in multi-step, open-ended environments frequently suffer from compounding errors, where early mistakes contaminate long-horizon trajectories. While Multi-Ag…
MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
Masoumeh Shafieinejad, Xi He, Mahshid Alinoori +6
Synthetic data is often perceived as a silver-bullet solution to data anonymization and privacy-preserving data publishing. Drawn from generative models like diffusion models, synt…
Adaptive Latent-Space Constraints in Personalized Federated Learning
Sana Ayromlou, Fatemeh Tavakoli, D. B. Emerson
Federated learning (FL) is an effective and widely used approach to training deep learning models on decentralized datasets held by distinct clients. FL also strengthens both secur…
Can Generative Models Improve Self-Supervised Representation Learning?
Sana Ayromlou, Vahid Reza Khazaie, Fereshteh Forghani +1
The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the exi…
Federated Impression for Learning with Distributed Heterogeneous Data
Atrin Arya, Sana Ayromlou, Armin Saadat +2
Standard deep learning-based classification approaches may not always be practical in real-world clinical applications, as they require a centralized collection of all samples. Fed…
A Comprehensive View of Personalized Federated Learning on Heterogeneous Clinical Datasets
Fatemeh Tavakoli, D. B. Emerson, Sana Ayromlou +5
Federated learning (FL) is increasingly being recognized as a key approach to overcoming the data silos that so frequently obstruct the training and deployment of machine-learning…