Related papers: Visual Adversarial Imitation Learning using Variat…

Observing a human demonstrator manipulate objects provides a rich, scalable and inexpensive source of data for learning robotic policies. However, transferring skills from human videos to a robotic manipulator poses several challenges, not…

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…

We consider the problem of visual imitation learning without human supervision (e.g. kinesthetic teaching or teleoperation), nor access to an interactive reinforcement learning (RL) training environment. We present a geometric perspective…

We investigate the visual cross-embodiment imitation setting, in which agents learn policies from videos of other agents (such as humans) demonstrating the same task, but with stark differences in their embodiments -- shape, actions,…

As Vision-Language Models (VLMs) become increasingly integrated into decision-making systems, it is essential to understand how visual inputs influence their behavior. This paper investigates the effects of visual priming on VLMs'…

Visuomotor robot policies, increasingly pre-trained on large-scale datasets, promise significant advancements across robotics domains. However, aligning these policies with end-user preferences remains a challenge, particularly when the…

A major challenge in the field of education is providing review schedules that present learned items at appropriate intervals to each student so that memory is retained over time. In recent years, attempts have been made to formulate item…

Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…

Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with suboptimal offline behaviors and inaccurate value estimation…

The Visibility-based Persistent Monitoring (VPM) problem seeks to find a set of trajectories (or controllers) for robots to persistently monitor a changing environment. Each robot has a sensor, such as a camera, with a limited field-of-view…

Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection. Existing adversarial perturbations-based methods mainly focus on the de-identification against…

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert…

Despite remarkable progress in recent years, Vision Language Models (VLMs) remain prone to overconfidence and hallucinations on tasks such as Visual Question Answering (VQA) and Visual Reasoning. Bayesian methods can potentially improve…

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge. Although continual learning has been widely studied in computer vision, its application to Vision+Language tasks is not…

Imitation from observation is the framework of learning tasks by observing demonstrated state-only trajectories. Recently, adversarial approaches have achieved significant performance improvements over other methods for imitating complex…

Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a…

Today's robots attempt to learn new tasks by imitating human examples. These robots watch the human complete the task, and then try to match the actions taken by the human expert. However, this standard approach to visual imitation learning…

Adversarial learning can learn fairer and less biased models of language than standard methods. However, current adversarial techniques only partially mitigate model bias, added to which their training procedures are often unstable. In this…

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new…