12 papers
Conformal Policy Control
Drew Prinster, Clara Fannjiang, Ji Won Park +4
An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm and must be taken offline, curtailing…
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Gina Wong, Drew Prinster, Suchi Saria +2
Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important for understanding and trusting reported probabilities. Recent wo…
Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution
Shravan Chaudhari, Yoav Wald, Suchi Saria
As we deploy machine learning systems in the real world, a core challenge is to maintain a model that is performant even as the data shifts. Such shifts can take many forms: new cl…
MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling
Hsing-Huan Chung, Shijun Li, Yoav Wald +3
Multimodal irregular time series (MITS) consist of asynchronous and irregularly sampled observations from heterogeneous numerical and textual channels. In healthcare, for example,…
FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
Xing Han, Shravan Chaudhari, Tanvi Ranade +2
Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at des…
On the Invariance and Generality of Neural Scaling Laws
Xing Han, Ziyin Liu, Suchi Saria +1
Neural scaling laws establish a predictable relationship between model performance and data or compute, offering crucial guidance for resource allocation in new domains and tasks.…