Related papers: Differentiable Semantic Meta-Learning Framework fo…

With the popularity of location-based services, human mobility prediction plays a key role in enhancing personalized navigation, optimizing recommendation systems, and facilitating urban mobility and planning. This involves predicting a…

Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for adapting large pre-trained models to downstream tasks, greatly reducing trainable parameters while grappling with memory challenges during…

Existing aerial robot navigation systems typically plan paths around static and dynamic obstacles, but fail to adapt when a static obstacle suddenly moves. Integrating environmental semantic awareness enables estimation of potential risks…

Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates…

This paper considers robot motion planning under temporal logic constraints in probabilistic maps obtained by semantic simultaneous localization and mapping (SLAM). The uncertainty in a map distribution presents a great challenge for…

Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data analysis and management. TRL aims to convert complicated raw trajectories into low-dimensional representation vectors, which can be applied to various…

Learning to control a safety-critical system with latent dynamics (e.g. for deep brain stimulation) requires taking calculated risks to gain information as efficiently as possible. To address this problem, we present a…

Real-world time series data often present recurrent or repetitive patterns and it is often generated in real time, such as transportation passenger volume, network traffic, system resource consumption, energy usage, and human gait.…

In the field of Learning from Demonstration (LfD), enabling robots to generalize learned manipulation skills to novel scenarios for long-horizon tasks remains challenging. Specifically, it is still difficult for robots to adapt the learned…

Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact conditions. We introduce SafeMind, a differentiable stochastic…

Reasoning about motion and space is a fundamental cognitive capability that is required by multiple real-world applications. While many studies highlight that large multimodal language models (MLMs) struggle to reason about space, they only…

Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited…

Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data. We formalize this challenge as the Distribution Shift…

Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution.…

Anomaly detection (AD) aims to identify defective images and localize their defects (if any). Ideally, AD models should be able to detect defects over many image classes; without relying on hard-coded class names that can be uninformative…

Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions, where tail classes suffer high robust error and unstable decision boundaries. We propose Manifold-Constrained…

Forecasting rare events in multivariate time-series data is challenging due to severe class imbalance, long-range dependencies, and distributional uncertainty. We introduce EVEREST, a transformer-based architecture for probabilistic…

Contact-rich robotic manipulation requires representations that encode local geometry. Vision provides global context but lacks direct measurements of properties such as texture and hardness, whereas touch supplies these cues. Modern…

This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catastrophic forgetting in the context of long-tailed data…

The role of natural language constraints in Safe Multi-agent Reinforcement Learning (MARL) is crucial, yet often overlooked. While Safe MARL has vast potential, especially in fields like robotics and autonomous vehicles, its full potential…