Related papers: Augment-Connect-Explore: a Paradigm for Visual Act…

Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are…

The success of deep learning in computer vision is based on availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Creating realistic 3D content is…

Image-based learning methods for autonomous vehicle perception tasks require large quantities of labelled, real data in order to properly train without overfitting, which can often be incredibly costly. While leveraging the power of…

Graph autoencoders (GAEs) are powerful tools in representation learning for graph embedding. However, the performance of GAEs is very dependent on the quality of the graph structure, i.e., of the adjacency matrix. In other words, GAEs would…

Robotic imitation learning has advanced from solving static tasks to addressing dynamic interaction scenarios, but testing and evaluation remain costly and challenging due to the need for real-time interaction with dynamic environments. We…

Learning long-horizon embodied behaviors from synthetic data remains challenging because generated scenes are often physically implausible, language-driven programs frequently "succeed" without satisfying task semantics, and high-level…

Motivated by exploration of communication-constrained underground environments using robot teams, we study the problem of planning for intermittent connectivity in multi-agent systems. We propose a novel concept of information-consistency…

Active learning for object detection is conventionally achieved by applying techniques developed for classification in a way that aggregates individual detections into image-level selection criteria. This is typically coupled with the…

Recently, large language models (LLMs) have demonstrated remarkable potential as an intelligent agent. However, existing researches mainly focus on enhancing the agent's reasoning or decision-making abilities through well-designed prompt…

On-device learning is essential for personalization, privacy, and long-term adaptation in resource-constrained environments. Achieving this requires efficient learning, both fine-tuning existing models and continually acquiring new tasks…

Deep Learning (DL) training platforms are built by interconnecting multiple DL accelerators (e.g., GPU/TPU) via fast, customized interconnects with 100s of gigabytes (GBs) of bandwidth. However, as we identify in this work, driving this…

Standard Adjacency Spectral Embedding (ASE) relies on a global low-rank assumption often incompatible with the sparse, transitive structure of real-world networks, causing local geometric features to be 'smeared'. To address this, we…

Weakly-supervised temporal action localization is a problem of learning an action localization model with only video-level action labeling available. The general framework largely relies on the classification activation, which employs an…

We propose DeepExplorer, a simple and lightweight metric-free exploration method for topological mapping of unknown environments. It performs task and motion planning (TAMP) entirely in image feature space. The task planner is a recurrent…

Autonomous exploration requires a robot to explore an unknown environment while constructing an accurate map using Simultaneous Localization and Mapping (SLAM) techniques. Without prior information, the exploration performance is usually…

Manipulation in confined and cluttered environments remains a significant challenge due to partial observability and complex configuration spaces. Effective manipulation in such environments requires an intelligent exploration strategy to…

Motion planning algorithms often leverage topological information about the environment to improve planner performance. However, these methods often focus only on the environment's connectivity while ignoring other properties such as…

As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each…

We propose CARE (Collision Avoidance via Repulsive Estimation) to improve the robustness of learning-based visual navigation methods. Recently, visual navigation models, particularly foundation models, have demonstrated promising…

Machine learning has gained widespread attention as a powerful tool to identify structure in complex, high-dimensional data. However, these techniques are ostensibly inapplicable for experimental systems where data is scarce or expensive to…