Leveraging Periodicity for Robustness with Multi-modal Mood Pattern Models
*Equal Contributors
Data from wearable sensors (e.g., heart rate, step count) can be used to model mood patterns. We characterize feature representations and...
Strategic Linear Contextual Bandits
Motivated by the phenomenon of strategic agents gaming a recommendation system to maximize the number of times they are recommended to users, we...
GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics
Single-cell genomics has significantly advanced our understanding of cellular behavior, catalyzing innovations in treatments and precision medicine. However, single-cell sequencing technologies are inherently...
Learning Elastic Costs to Shape Monge Displacements
Given a source and a target probability measure supported on RdmathbbR^dRd, the Monge problem aims for the most efficient way to map one...
Speech is More Than Words: Do Speech-to-Text Translation Systems Leverage Prosody?
This paper was accepted at the Ninth Conference on Machine Translation (WMT24) at EMNLP 2024.
The prosody of a spoken utterance, including features like...
Multimodal Autoregressive Pre-Training of Large Vision Encoders
*Equal Contributors
A dominant paradigm in large multimodal models is to pair a large language de- coder with a vision encoder. While it is...
Do LLMs Internally “Know” When They Follow Instructions?
This paper was accepted at the Foundation Model Interventions (MINT) Workshop at NeurIPS 2024.
Instruction-following is crucial for building AI agents with large language...
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by randomly concatenating documents of...
Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications
This paper was accepted at the Machine Learning and Compression Workshop at NeurIPS 2024.
Compressing Large Language Models (LLMs) often leads to reduced performance,...
Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
Learning with identical train and test distributions has been extensively investigated both practically and theoretically. Much remains to be understood, however, in statistical...
