10 papers
MIST: Mutual Information Estimation Via Supervised Training
German Gritsai, Megan Richards, Maxime Méloux +2
We propose a fully data-driven approach to designing mutual information (MI) estimators. Since any MI estimator is a function of the observed sample from two random variables, we p…
Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling
Divyam Madaan, Sumit Chopra, Kyunghyun Cho
Despite the recent success of Multimodal Large Language Models (MLLMs), existing approaches predominantly assume the availability of multiple modalities during training and inferen…
Paradox of De-identification: A Critique of HIPAA Safe Harbour in the Age of LLMs
Lavender Y. Jiang, Xujin Chris Liu, Kyunghyun Cho +1
Privacy is a human right that sustains patient-provider trust. Clinical notes capture a patient's private vulnerability and individuality, which are used for care coordination and…
Group Contrastive Learning for Weakly Paired Multimodal Data
Aditya Gorla, Hugues Van Assel, Jan-Christian Huetter +4
We present GROOVE, a semi-supervised multi-modal representation learning approach for high-content perturbation data where samples across modalities are weakly paired through share…
Meta-Statistical Learning: Supervised Learning of Statistical Estimators
Maxime Peyrard, Kyunghyun Cho
Statistical inference, a central tool of science, revolves around the study and the usage of statistical estimators: functions that map finite samples to predictions about unknown…
Training Dynamics of Learning 3D-Rotational Equivariance
Max W. Shen, Ewa Nowara, Michael Maser +1
While data augmentation is widely used to train symmetry-agnostic models, it remains unclear how quickly and effectively they learn to respect symmetries. We investigate this by de…