相关论文: SECANT: Self-Expert Cloning for Zero-Shot Generali…

Training vision-based manipulation policies that are robust across diverse visual environments remains an important and unresolved challenge in robot learning. Current approaches often sidestep the problem by relying on invariant…

Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL…

The use of multi-camera views simultaneously has been shown to improve the generalization capabilities and performance of visual policies. However, the hardware cost and design constraints in real-world scenarios can potentially make it…

Generalizing policies to unseen scenarios remains a critical challenge in visual reinforcement learning, where agents often overfit to the specific visual observations of the training environment. In unseen environments, distracting pixels…

The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been…

Supervised learning (SL) and reinforcement learning (RL) are both widely used to train general-purpose agents for complex tasks, yet their generalization capabilities and underlying mechanisms are not yet fully understood. In this paper, we…

Image clustering is an important and open-challenging task in computer vision. Although many methods have been proposed to solve the image clustering task, they only explore images and uncover clusters according to the image features, thus…

Generalizing vision-based reinforcement learning (RL) agents to novel environments remains a difficult and open challenge. Current trends are to collect large-scale datasets or use data augmentation techniques to prevent overfitting and…

Reinforcement Learning (RL) agents are often unable to generalise well to environment variations in the state space that were not observed during training. This issue is especially problematic for image-based RL, where a change in just one…

Vision-and-Language Navigation (VLN) requires an agent to find a specified spot in an unseen environment by following natural language instructions. Dominant methods based on supervised learning clone expert's behaviours and thus perform…

We present Self-Context Adaptation (SeCAt), a self-supervised approach that unlocks few-shot abilities for open-ended classification with small visual language models. Our approach imitates image captions in a self-supervised way based on…

Low-light image enhancement remains a challenging task, particularly in the absence of paired training data. In this study, we present LucentVisionNet, a novel zero-shot learning framework that addresses the limitations of traditional and…

While Vision-Language-Action (VLA) models show strong generalizability in various tasks, real-world deployment of robotic policy still requires large-scale, high-quality human expert demonstrations. However, data collection via human…

Deploying reinforcement learning in the real world remains challenging due to sample inefficiency, sparse rewards, and noisy visual observations. Prior work leverages demonstrations and human feedback to improve learning efficiency and…

Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from related tasks can be…

Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because…

It is a long-standing challenge to enable an intelligent agent to learn in one environment and generalize to an unseen environment without further data collection and finetuning. In this paper, we consider a zero shot generalization problem…

New categories can be discovered by transforming semantic features into synthesized visual features without corresponding training samples in zero-shot image classification. Although significant progress has been made in generating…

Deep Reinforcement Learning (RL) models often fail to generalize when even small changes occur in the environment's observations or task requirements. Addressing these shifts typically requires costly retraining, limiting the reusability of…

User retention is critical in large-scale recommender systems, significantly influencing online platforms' long-term success. Existing methods typically focus on short-term engagement, neglecting the evolving dynamics of user behaviors over…