Related papers: FALCON: Future-Aware Learning with Contextual Obje…

Large language models have been widely applied, but can inadvertently encode sensitive or harmful information, raising significant safety concerns. Machine unlearning has emerged to alleviate this concern; however, existing training-time…

Machine-learning algorithms have shown outstanding image recognition or classification performance for computer vision applications. However, the compute and energy requirement for implementing such classifier models for large-scale…

False negatives pose a critical challenge in vision-language pretraining (VLP) due to the many-to-many correspondence between images and texts in large-scale datasets. These false negatives introduce conflicting supervision signals that…

We present a meta-learning framework for learning new visual concepts quickly, from just one or a few examples, guided by multiple naturally occurring data streams: simultaneously looking at images, reading sentences that describe the…

We present FoundAtion-model-guided decoupled LoCO-maNipulation visuomotor policies (FALCON), a framework for loco-manipulation that combines modular diffusion policies with a vision-language foundation model as the coordinator. Our approach…

We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a…

Humanoid loco-manipulation holds transformative potential for daily service and industrial tasks, yet achieving precise, robust whole-body control with 3D end-effector force interaction remains a major challenge. Prior approaches are often…

Current state-of-the-art approaches in Source-Free Object Detection (SFOD) typically rely on Mean-Teacher self-labeling. However, domain shift often reduces the detector's ability to maintain strong object-focused representations, causing…

We present BEVCon, a simple yet effective contrastive learning framework designed to improve Bird's Eye View (BEV) perception in autonomous driving. BEV perception offers a top-down-view representation of the surrounding environment, making…

To navigate safely and efficiently in crowded spaces, robots should not only perceive the current state of the environment but also anticipate future human movements. In this paper, we propose a reinforcement learning architecture, namely…

Latest deep learning methods for object detection provide remarkable performance, but have limits when used in robotic applications. One of the most relevant issues is the long training time, which is due to the large size and imbalance of…

Existing vision-language-action (VLA) models act in 3D real-world but are typically built on 2D encoders, leaving a spatial reasoning gap that limits generalization and adaptability. Recent 3D integration techniques for VLAs either require…

Precise delineation of anatomical and pathological structures within 3D medical volumes is crucial for accurate diagnosis, effective surgical planning, and longitudinal disease monitoring. Despite advancements in AI, clinically viable…

Perception-centric systems are typically implemented with a modular encoder-decoder pipeline: a vision backbone for feature extraction and a separate decoder (or late-fusion module) for task prediction. This raises a central question: is…

Imitation learning enables robots to learn new tasks from human examples. One fundamental limitation while learning from humans is causal confusion. Causal confusion occurs when the robot's observations include both task-relevant and…

Integration of reinforcement learning with unmanned aerial vehicles (UAVs) to achieve autonomous flight has been an active research area in recent years. An important part focuses on obstacle detection and avoidance for UAVs navigating…

Machine learning as a service has been widely deployed to utilize deep neural network models to provide prediction services. However, this raises privacy concerns since clients need to send sensitive information to servers. In this paper,…

Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and…

We present a novel approach for the detection of deepfake videos using a pair of vision transformers pre-trained by a self-supervised masked autoencoding setup. Our method consists of two distinct components, one of which focuses on…

This paper introduces FALCON, a novel Fast Autonomous expLoration framework using COverage path guidaNce, which aims at setting a new performance benchmark in the field of autonomous aerial exploration. Despite recent advancements in the…