Related papers: CLUTR: Curriculum Learning via Unsupervised Task R…
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system.…
Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability. However, all the pseudo bi-texts generated by BT are treated equally…
Class incremental learning (CIL) aims to enable models to continuously learn new classes without catastrophically forgetting old ones. A promising direction is to learn and use prototypes of classes during incremental updates. Despite…
Unsupervised representation learning algorithms such as word2vec and ELMo improve the accuracy of many supervised NLP models, mainly because they can take advantage of large amounts of unlabeled text. However, the supervised models only…
LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing unlearning methods face significant limitations:…
Unbiased learning to rank (ULTR) aims to mitigate various biases existing in user clicks, such as position bias, trust bias, presentation bias, and learn an effective ranker. In this paper, we introduce our winning approach for the…
We propose a realistic scenario for the unsupervised video learning where neither task boundaries nor labels are provided when learning a succession of tasks. We also provide a non-parametric learning solution for the under-explored problem…
Contrastive learning (CL) continuously achieves significant breakthroughs across multiple domains. However, the most common InfoNCE-based methods suffer from some dilemmas, such as \textit{uniformity-tolerance dilemma} (UTD) and…
A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…
Designing reinforcement learning curricula for agile robots traditionally requires extensive manual tuning of reward functions, environment randomizations, and training configurations. We introduce AURA (Autonomous Upskilling with…
We consider the problem of tabular infinite horizon concave utility reinforcement learning (CURL) with convex constraints. For this, we propose a model-based learning algorithm that also achieves zero constraint violations. Assuming that…
Curriculum learning has been growing in the domain of reinforcement learning as a method of improving training efficiency for various tasks. It involves modifying the difficulty (lessons) of the environment as the agent learns, in order to…
We propose UnCLe, the first standardized benchmark for Unsupervised Continual Learning of a multimodal 3D reconstruction task: Depth completion aims to infer a dense depth map from a pair of synchronized RGB image and sparse depth map. We…
We explore different curriculum learning methods for training convolutional neural networks on the task of deformable pairwise 3D medical image registration. To the best of our knowledge, we are the first to attempt to improve performance…
In recent years, Deep Reinforcement Learning (DRL) has emerged as a promising method for robot collision avoidance. However, such DRL models often come with limitations, such as adapting effectively to structured environments containing…
Labeling LiDAR point clouds is notoriously time-and-energy-consuming, which spurs recent unsupervised 3D representation learning methods to alleviate the labeling burden in LiDAR perception via pretrained weights. Almost all existing work…
Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work, we extend UDRL to the task of learning a…
Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homogeneous solutions. In such environments, the lack of failure…
Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform…
Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from scalability and sparse reward issues. One promising approach…