Related papers: How to Solve Contextual Goal-Oriented Problems wit…

Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-purpose policies from diverse and multi-task offline datasets. Despite notable recent progress, the predominant offline GCRL methods, mainly model-free, face…

Motion forecasting in highly interactive scenarios is a challenging problem in autonomous driving. In such scenarios, we need to accurately predict the joint behavior of interacting agents to ensure the safe and efficient navigation of…

This work studies the problem of object goal navigation which involves navigating to an instance of the given object category in unseen environments. End-to-end learning-based navigation methods struggle at this task as they are ineffective…

In this paper we describe the design and the ideas motivating a new Continual Learning benchmark for Autonomous Driving (CLAD), that focuses on the problems of object classification and object detection. The benchmark utilises SODA10M, a…

We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency. CoDA generalizes beyond standard adapter approaches to enable a new way of balancing speed and accuracy using…

Unsupervised domain adaptation (UDA) refers to a domain adaptation framework in which a learning model is trained based on the labeled samples on the source domain and unlabeled ones in the target domain. The dominant existing methods in…

Multimodal large language models (MLLMs) recently showed strong capacity in integrating data among multiple modalities, empowered by a generalizable attention architecture. Advanced methods predominantly focus on language-centric tuning…

We propose a data augmentation method for offline reinforcement learning, motivated by active positioning problems. Particularly, our approach enables the training of off-policy models from a limited number of suboptimal trajectories. We…

We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision. Map-based memory provides important contextual information for visual navigation, and…

Recent studies have demonstrated that near-data processing (NDP) is an effective technique for improving performance and energy efficiency of data-intensive workloads. However, leveraging NDP in realistic systems with multiple memory…

Online learning algorithms update models via one sample per iteration, thus efficient to process large-scale datasets and useful to detect malicious events for social benefits, such as disease outbreak and traffic congestion on the fly.…

Domain adaptive object detection (DAOD) assumes that both labeled source data and unlabeled target data are available for training, but this assumption does not always hold in real-world scenarios. Thus, source-free DAOD is proposed to…

Convolutional Neural Networks (CNNs) have brought revolutionary advances to many research areas due to their capacity of learning from raw data. However, when those methods are applied to non-controllable environments, many different…

The remarkable success of Deep Learning approaches is often based and demonstrated on large public datasets. However, when applying such approaches to internal, private datasets, one frequently faces challenges arising from structural…

Multilingual task-oriented dialogue (ToD) facilitates access to services and information for many (communities of) speakers. Nevertheless, the potential of this technology is not fully realised, as current datasets for multilingual ToD -…

Real-world application models are commonly deployed in dynamic environments, where the target domain distribution undergoes temporal changes. Continual Test-Time Adaptation (CTTA) has recently emerged as a promising technique to gradually…

Counterfactual data augmentation (CDA) is a method for controlling information or biases in training datasets by generating a complementary dataset with typically opposing biases. Prior work often either relies on hand-crafted rules or…

Recent breakthroughs in scale have enabled the emergence of powerful generative language models, and the ability to fine-tune these models on various tasks by casting them into prompts or instructions. In this landscape, the problem of…

Due to the high cost of collection and labeling, there are relatively few datasets for camouflaged object detection (COD). In particular, for certain specialized categories, the available image dataset is insufficiently populated. Synthetic…

Data generation is recognized as a potent strategy for unsupervised domain adaptation (UDA) pertaining semantic segmentation in adverse weathers. Nevertheless, these adverse weather scenarios encompass multiple possibilities, and…