相关论文: CtrlFormer: Learning Transferable State Representa…

Transformer based knowledge tracing model is an extensively studied problem in the field of computer-aided education. By integrating temporal features into the encoder-decoder structure, transformers can processes the exercise information…

Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire. In this work, we propose a reinforcement learning-based method for automatically adjusting the…

Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task. As prior arts can not handle it ideally, we propose a novel transformer, SnowFormer, which explores efficient cross-attentions…

Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity…

Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, high inference…

This paper identifies and addresses the problems with naively combining (reinforcement) learning-based controllers and state estimators for robotic in-hand manipulation. Specifically, we tackle the challenging task of purely tactile,…

Story Visualization is an advanced task of computed vision that targets sequential image synthesis, where the generated samples need to be realistic, faithful to their conditioning and sequentially consistent. Our work proposes a novel…

Transformer-based models for transfer learning have the potential to achieve high prediction accuracies on text-based supervised learning tasks with relatively few training data instances. These models are thus likely to benefit social…

Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an efficient representation space that is invariant under…

Designing mechanical mechanisms to trace specific paths is a classic yet notoriously difficult engineering problem, characterized by a vast and complex search space of discrete topologies and continuous parameters. We introduce MechaFormer,…

In order to understand the in-context learning phenomenon, recent works have adopted a stylized experimental framework and demonstrated that Transformers can learn gradient-based learning algorithms for various classes of real-valued…

Modern machine learning systems rely on large datasets to attain broad generalization, and this often poses a challenge in robot learning, where each robotic platform and task might have only a small dataset. By training a single policy…

The integration of large language models (LLMs) with control systems has demonstrated significant potential in various settings, such as task completion with a robotic manipulator. A main reason for this success is the ability of LLMs to…

While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they…

Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…

When it comes to wild conditions, Facial Expression Recognition is often challenged with low-quality data and imbalanced, ambiguous labels. This field has much benefited from CNN based approaches; however, CNN models have structural…

Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some…

Skill assessment from video entails rating the quality of a person's physical performance and explaining what could be done better. Today's models specialize for an individual sport, and suffer from the high cost and scarcity of…

Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with…

While robot learning has demonstrated promising results for enabling robots to automatically acquire new skills, a critical challenge in deploying learning-based systems is scale: acquiring enough data for the robot to effectively…