相关论文: Decoupling Exploration and Exploitation for Unsupe…
Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…
Feature selection (FS) is a fundamental challenge in machine learning, particularly for high-dimensional tabular data, where interpretability and computational efficiency are critical. Existing FS methods often cannot automatically detect…
Prompt learning has become the most effective paradigm for adapting large pre-trained vision-language models (VLMs) to downstream tasks. Recently, unsupervised prompt tuning methods, such as UPL and POUF, directly leverage pseudo-labels as…
Deep-learning-based local feature extraction algorithms that combine detection and description have made significant progress in visible image matching. However, the end-to-end training of such frameworks is notoriously unstable due to the…
Motivated by the recent success of end-to-end deep neural models for ranking tasks, we present here a supervised end-to-end neural approach for query performance prediction (QPP). In contrast to unsupervised approaches that rely on various…
Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in…
With the development of deep learning techniques, supervised learning has achieved performances surpassing those of humans. Researchers have designed numerous corresponding models for different data modalities, achieving excellent results…
Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In…
Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data. In the realm of computer vision, pretrained vision transformers…
Unsupervised and self-supervised objectives, such as next token prediction, have enabled pre-training generalist models from large amounts of unlabeled data. In reinforcement learning (RL), however, finding a truly general and scalable…
Learning rich skills under the option framework without supervision of external rewards is at the frontier of reinforcement learning research. Existing works mainly fall into two distinctive categories: variational option discovery that…
Seismic data restoration is a fundamental task in seismic exploration, yet remains challenging under complex and unknown degradations. Traditional model-driven or task-specific learning methods often require retraining for each degradation…
This work explores the application of Federated Learning (FL) to Unsupervised Semantic image Segmentation (USS). Recent USS methods extract pixel-level features using frozen visual foundation models and refine them through self-supervised…
Pretraining NLP models with variants of Masked Language Model (MLM) objectives has recently led to a significant improvements on many tasks. This paper examines the benefits of pretrained models as a function of the number of training…
In reinforcement learning, unsupervised skill discovery aims to learn diverse skills without extrinsic rewards. Previous methods discover skills by maximizing the mutual information (MI) between states and skills. However, such an MI…
Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…
We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations. The reward is the novelty of the surprise rather than the surprise norm. We estimate…
Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question. Even when insights about the environment dynamics are available, reinforcement learning is traditionally used in a tabula rasa setting and must…
Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison:…
In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use…