10 accepted papers
Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and pr…
Offline Zero-Shot Reinforcement Learning requires an agent to solve unseen tasks using only a fixed offline dataset without explicit rewards. A central challenge is learning representations that capture both high-level long-term planning and low-level physical dynamics. We propose a novel framework,
Inherently, robotic manipulation tasks are history-dependent: leveraging past context could be beneficial. However, most existing Vision-Language-Action models (VLAs) have been designed without considering this aspect, i.e., they rely solely on the current observation, ignoring preceding context. In…
The recent theoretical analysis of deep neural networks in their infinite-width limits has deepened our understanding of initialisation, feature learning, and training of those networks, and brought new practical techniques for finding appropriate hyperparameters, learning network weights, and perfo…
In multi-goal reinforcement learning with a sparse binary reward, training agents is particularly challenging, due to a lack of successful experiences. To solve this problem, hindsight experience replay (HER) generates successful experiences even from unsuccessful ones. However, generating successfu…
Optical character recognition(OCR) is the technology to identify text characters embedded within images. Conventional OCR models exhibit performance degradation when performing with noisy images. To solve this problem, we propose a novel model, which combines computer vision using optical sensor wit…
Targetless IMU-LiDAR extrinsic calibration methods are gaining significant attention as the importance of the IMU-LiDAR fusion system increases. Notably, existing calibration methods derive calibration parameters under the assumption that the methods require full motion in all axes. When IMU and LiD
We present a novel sound source localization method that leverages microphone pair training, designed to deliver robust performance in various real-world environments. Existing deep learning (DL)-based approaches face scalability issues when dealing with various types of microphone arrays. To addres
Recently introduced dialogue systems have demonstrated high usability. However, they still fall short of reflecting real-world conversation scenarios. Current dialogue systems exhibit an inability to replicate the dynamic, continuous, long-term interactions involving multiple partners. This shortfal…
Efficient exploration for an agent is challenging in reinforcement learning (RL). In this paper, a novel actor-critic framework namely virtual action actor-critic (VAAC), is proposed to address the challenge of efficient exploration in RL. This work is inspired by humans' ability to imagine the pote…