Zobrazeno 1 - 10
of 1 662
pro vyhledávání: '"Hong An-Wei"'
Autor:
Karnik, Sathwik, Hong, Zhang-Wei, Abhangi, Nishant, Lin, Yen-Chen, Wang, Tsun-Hsuan, Agrawal, Pulkit
Language-conditioned robot models (i.e., robotic foundation models) enable robots to perform a wide range of tasks based on natural language instructions. Despite strong performance on existing benchmarks, evaluating the safety and effectiveness of t
Externí odkaz:
http://arxiv.org/abs/2411.18676
Autor:
Hwang, Jaedong, Cheung, Brian, Hong, Zhang-Wei, Boopathy, Akhilan, Agrawal, Pulkit, Fiete, Ila
Highly performant large-scale pre-trained models promise to also provide a valuable foundation for learning specialized tasks, by fine-tuning the model to the desired task. By starting from a good general-purpose model, the goal is to achieve both sp
Externí odkaz:
http://arxiv.org/abs/2410.21582
Reward shaping is a critical component in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. While shaping rewards have been introduced to provide additional guidance, selecting effective shaping fun
Externí odkaz:
http://arxiv.org/abs/2410.13837
The ability to efficiently explore high-dimensional state spaces is essential for the practical success of deep Reinforcement Learning (RL). This paper introduces a new exploration technique called Random Latent Exploration (RLE), that combines the s
Externí odkaz:
http://arxiv.org/abs/2407.13755
Publikováno v:
Reinforcement Learning Journal, vol. 4, 2024, pp. 1598-1618
Experience replay serves as a key component in the success of online reinforcement learning (RL). Prioritized experience replay (PER) reweights experiences by the temporal difference (TD) error empirically enhancing the performance. However, few work
Externí odkaz:
http://arxiv.org/abs/2407.03995
Generating varied scenarios through simulation is crucial for training and evaluating safety-critical systems, such as autonomous vehicles. Yet, the task of modeling the trajectories of other vehicles to simulate diverse and meaningful close interact
Externí odkaz:
http://arxiv.org/abs/2406.04300
In this work, we introduce a novel method for calculating the 6DoF pose of an object using a single RGB-D image. Unlike existing methods that either directly predict objects' poses or rely on sparse keypoints for pose recovery, our approach addresses
Externí odkaz:
http://arxiv.org/abs/2405.08483
Autor:
Hong, Zong-Wei, Lin, Yu-Chen
The domain of computer vision has experienced significant advancements in facial-landmark detection, becoming increasingly essential across various applications such as augmented reality, facial recognition, and emotion analysis. Unlike object detect
Externí odkaz:
http://arxiv.org/abs/2404.06029
Autor:
Hong, Zhang-Wei, Shenfeld, Idan, Wang, Tsun-Hsuan, Chuang, Yung-Sung, Pareja, Aldo, Glass, James, Srivastava, Akash, Agrawal, Pulkit
Large language models (LLMs) hold great potential for many natural language applications but risk generating incorrect or toxic content. To probe when an LLM generates unwanted content, the current paradigm is to recruit a \textit{red team} of human
Externí odkaz:
http://arxiv.org/abs/2402.19464
The rheology of suspensions of non-Brownian soft spheres is studied across jamming but also across the viscous and inertial regimes using a custom pressure- and volume-imposed rheometer. The study shows that the granular rheology found for suspension
Externí odkaz:
http://arxiv.org/abs/2311.15107