相关论文: Improving Environment Novelty Quantification for E…
Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce, and existing synthesis methods suffer from significant…
This paper introduces "GAIDE: Generative AI for Instructional Development and Education," a novel framework for using Generative AI (GenAI) to enhance educational content creation. GAIDE stands out by offering a practical approach for…
Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics. However, existing methods are typically trained and tested on standard datasets, overlooking the impact of various…
Recent advancements in virtual reality (VR) technology have enabled the creation of immersive learning environments that provide engineering students with hands-on, interactive experiences. This paper presents a novel framework for virtual…
Ensemble learning has gain attention in resent deep learning research as a way to further boost the accuracy and generalizability of deep neural network (DNN) models. Recent ensemble training method explores different training algorithms or…
We formulate a unifying framework for unsupervised continual learning (UCL), which disentangles learning objectives that are specific to the present and the past data, encompassing stability, plasticity, and cross-task consolidation. The…
Unsupervised continual learning remains a relatively uncharted territory in the existing literature because the vast majority of existing works call for unlimited access of ground truth incurring expensive labelling cost. Another issue lies…
Modern neural network performance typically improves as model size increases. A recent line of research on the Neural Tangent Kernel (NTK) of over-parameterized networks indicates that the improvement with size increase is a product of a…
Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones, while maintaining stable performance across all possible class sequences. In real-world settings, the order in…
This paper addresses the challenges of training end-to-end autonomous driving agents using Reinforcement Learning (RL). RL agents are typically trained in a fixed set of scenarios and nominal behavior of surrounding road users in…
Delivering high-quality content is crucial for effective reading comprehension and successful learning. Ensuring educational materials are interpreted as intended by their authors is a persistent challenge, especially with the added…
Distantly-Supervised Named Entity Recognition (DS-NER) is widely used in real-world scenarios. It can effectively alleviate the burden of annotation by matching entities in existing knowledge bases with snippets in the text but suffer from…
Recent advances in instruction-based image editing have shown remarkable progress. However, existing methods remain limited to relatively simple editing operations, hindering real-world applications that require complex and compositional…
When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a…
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal. Goal-directed RL has seen large gains in…
We study the problem of invariant learning when the environment labels are unknown. We focus on the invariant representation notion when the Bayes optimal conditional label distribution is the same across different environments. Previous…
The aim of this work is to develop an approach that enables Unmanned Aerial System (UAS) to efficiently learn to navigate in large-scale urban environments and transfer their acquired expertise to novel environments. To achieve this, we…
In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training.…
Edge computing offers significant advantages for realtime data processing tasks, such as object recognition, by reducing network latency and bandwidth usage. However, edge environments are susceptible to various types of fault. A remediator…
This work proposes a novel framework, Uncertainty-Guided Cross Attention Ensemble Mean Teacher (UG-CEMT), for achieving state-of-the-art performance in semi-supervised medical image segmentation. UG-CEMT leverages the strengths of…