Johns Hopkins researchers, including several affiliated with the Johns Hopkins Data Science and AI Institute, will present their research during the upcoming 2025 International Conference on Learning Representations (ICLR), to be held Thursday, April 24 through Monday, April 28 in Singapore.
The International Conference on Learning Representations is dedicated to advancing representation learning, which is a branch of artificial intelligence and is often called deep learning. The annual event brings together professionals with a range of backgrounds across all aspects of deep learning including AI, statistics and data science, machine vision, computational biology, speech recognition, text understanding, gaming and robotics.
Johns Hopkins researchers will present the following:
Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
Dimitris Oikonomou, Nicolas Loizou
Generative World Explorer
Taiming Lu, Tianmin Shu, Alan Yuille, Daniel Khashabi, Jieneng Chen
Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
Jingyu Zhang, Ahmed Elgohary, Ahmed Magooda, Daniel Khashabi, Benjamin Van Durme
Sharpness Aware Minimization: General Analysis and Improved Rates
Dimitris Oikonomou, Nicolas Loizou
ELBOing Stein: Variational Bayes with Stein Mixture Inference
Ola Rønning, Eric Nalisnick, Christophe Ley, Padhraic Smyth, Thomas Hamelryck
Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence
Dharmesh Tailor, Alvaro Correia, Eric Nalisnick, Christos Louizos
X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
Haoran Xu, Kenton Murray, Philipp Koehn, Hieu Hoang, Akiko Eriguchi, Huda Khayrallah
CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations
Noga Mudrik, Ryan Ly, Oliver Ruebel, and Adam S. Charles
Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
Xingrui Wang, Wufei Ma, Angtian Wang, Shuo Chen, Adam Kortylewski, Alan Yuille
COMBO: Compositional World Models for Embodied Multi-Agent Cooperation
Hongxin Zhang, Zeyuan Wang, Qiushi Lyu, Zheyuan Zhang, Sunli Chen, Tianmin Shu, Yilun Du, Behzad Dariush, Kwonjoon Lee, Chuang Gan
A simple diffusion transformer on unified video, 3D, and game field generation
Kangfu Mei, Mo Zhou, and Vishal M. Patel
PIN: Prolate spheroidal wave function-based implicit neural representations
Dhananjaya Jayasundara, Heng Zhao, Demetrio Labate, Vishal M. Patel
Syntactic and semantic control of large language models via sequential Monte Carlo
João Loula, Benjamin LeBrun, Li Du, Ben Lipkin, Clemente Pasti, Gabriel Grand, Tianyu Liu, Yahya Emara, Marjorie Freedman, Jason Eisner, Ryan Cotterell, Vikash Mansinghka, Alexander K. Lew, Tim Vieira, and Timothy J. O’Donnell
Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering
Xingrui Wang, Wufei Ma, Angtian Wang, Shuo Chen, Adam Kortylewski, Alan Yuille
