相关论文: Salience-Invariant Consistent Policy Learning for …

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challenges. A key difficulty is that standard task rewards supervise…

Contrastive Language-Image Pretraining (CLIP) model has exhibited remarkable efficacy in establishing cross-modal connections between texts and images, yielding impressive performance across a broad spectrum of downstream applications…

Vision-Language-Action (VLA) models improve action generation by conditioning policies on rich vision-language information. However, current auto-regressive policies are constrained by three bottlenecks: (1) architectural bias drives models…

Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy. However, the standard curriculum methodology does not…

One of the well-known challenges in computer vision tasks is the visual diversity of images, which could result in an agreement or disagreement between the learned knowledge and the visual content exhibited by the current observation. In…

Prompt learning has emerged as a powerful paradigm for adapting vision-language models such as CLIP to downstream tasks. However, existing methods often overfit to seen data, leading to significant performance degradation when generalizing…

Goal-conditioned reinforcement learning (GCRL) allows agents to learn diverse objectives using a unified policy. The success of GCRL, however, is contingent on the choice of goal representation. In this work, we propose a mask-based goal…

Zero-Shot Learning (ZSL) has received extensive attention and successes in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. Key to ZSL is to transfer knowledge from the seen to the unseen…

Motivated by the efficiency and rapid convergence of pre-trained models for solving downstream tasks, this paper extensively studies the impact of Continual Learning (CL) models as pre-trainers. In both supervised and unsupervised CL, we…

Reasoning from diverse observations is a fundamental capability for generalist robot policies to operate in a wide range of environments. Despite recent advancements, many large-scale robotic policies still remain sensitive to key sources…

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…

Graphical user interface (GUI)-based mobile agents automate digital tasks on mobile devices by interpreting natural-language instructions and interacting with the screen. While recent methods apply reinforcement learning (RL) to train…

Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically forgetting…

Reinforcement Learning (RL) is a well-established framework for sequential decision-making in complex environments. However, state-of-the-art Deep RL (DRL) algorithms typically require large training datasets and often struggle to…

Video Anomaly Detection (VAD) remains a fundamental yet formidable task in the video understanding community, with promising applications in areas such as information forensics and public safety protection. Due to the rarity and diversity…

Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn. Imitating human action is a fundamental problem of PL. However, both supervised learning (SL) and reinforcement…

While classic control theory offers state of the art solutions in many problem scenarios, it is often desired to improve beyond the structure of such solutions and surpass their limitations. To this end, residual policy learning (RPL)…

The ability to continuously acquire new knowledge and skills is crucial for autonomous agents. Existing methods are typically based on either fixed-size models that struggle to learn a large number of diverse behaviors, or growing-size…

Training end-to-end policies from image data to directly predict navigation actions for robotic systems has proven inherently difficult. Existing approaches often suffer from either the sim-to-real gap during policy transfer or a limited…

While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors…