Simulating interactions between deformable bodies is vital in fields like material science, mechanical design, and robotics. While learning-based methods with Graph Neural Networks (GNNs) are...

Continuous control of non-stationary environments is a major challenge for deep reinforcement learning algorithms. The time-dependency of the state transition dynamics aggravates the notorious...

We examine the extent to which sublinear-sample property testing and estimation applies to settings where samples are independently but not identically distributed. Specifically, we consider the...

Spatiotemporal point processes (STPPs) are probabilistic models for events occurring in continuous space and time. Real-world event data often exhibits intricate dependencies and heterogeneous...

We introduce a deep neural operator framework aimed at object detection in remotely sensed Synthetic Aperture Radar (SAR) images. Recent research highlights the impressive performance of the...

Sorting is one of the most fundamental algorithms in computer science. Recently, Learned Sorts, which use machine learning to improve sorting speed, have attracted attention. While existing studies...

Image-text models excel at image-level tasks but struggle with detailed visual understanding. While these models provide strong visual-language alignment, segmentation models like SAM2 offer...

Next-token prediction is conventionally done using decoder-only Transformers with causal attention, as this approach allows for efficient reuse of keys and values. What if we were not...

Score-based diffusion models (SBDMs) are powerful amortized samplers for Boltzmann distributions; however, imperfect score estimates bias downstream Monte Carlo estimates. Classical importance...

We introduce FairAlign, a new method to reduce bias and improve group fairness in deepfake detection by aligning conditional distributions of embeddings in a high-dimensional kernel space. Our...

In many real-world settings, regulations and economic incentives permit the sharing of models but not data across institutional boundaries. In such scenarios, practitioners might hope to adapt...

The utility of reinforcement learning is limited by the alignment of reward functions with the interests of human stakeholders. One promising method for alignment is to learn the reward function...

Learning Markov decision processes (MDP) in an adversarial environment has been a challenging problem. The problem becomes even more challenging with function approximation since the underlying...

The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot learning. Inspired by...

We study the unbalanced optimal transport (UOT) problem, where the marginal constraints are enforced using Maximum Mean Discrepancy (MMD) regularization. Our work is motivated by the observation...

As general purpose vision models get increasingly effective at a wide set of tasks, it is imperative that they be consistent across the tasks they support. Inconsistent AI models are considered...

Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets. Different classes of self-supervised learning offer...

We investigate the fundamental optimization question of minimizing a \emph{target} function $f(x)$, whose gradients are expensive to compute or have limited availability, given access to some...

We introduce Voyager, the first LLM-powered embodied lifelong learning agent in an open-ended world that continuously explores, acquires diverse skills, and makes novel discoveries without human...

This paper studies how to achieve variance-aware regrets for online decision-making in the presence of heavy-tailed rewards with only finite variances. For linear stochastic bandits, we address...