5 papers · 1 filter
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
Ali Falahati, Mohammad Mohammadi Amiri, Kate Larson +1
Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal, the model tends to collapse…
DriftXpress: Faster Drifting Models via Projected RKHS Fields
Ali Falahati, Elliot Creager, Gautam Kamath +1
Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise is to replace the iterative…
The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation
Ali Falahati, Mohammad Mohammadi Amiri, Kate Larson +1
In self-consuming generative models that train on their own outputs, alignment with user preferences becomes a recursive rather than one-time process. We provide the first formal f…
Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics
Momin Abbas, Ali Falahati, Hossein Goli +1
Out-of-distribution (OOD) detection plays a crucial role in ensuring the robustness of machine learning systems deployed in real-world applications. Recent approaches have explored…
Disentangled Structural and Featural Representation for Task-Agnostic Graph Valuation
Ali Falahati, Mohammad Mohammadi Amiri
With the emergence of data marketplaces, the demand for methods to assess the value of data has increased significantly. While numerous techniques have been proposed for this purpo…