Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Stepputtis, Simon"'
Autor:
Wang, Zirui, Zhao, Xinran, Stepputtis, Simon, Kim, Woojun, Wu, Tongshuang, Sycara, Katia, Xie, Yaqi
Understanding and predicting human actions has been a long-standing challenge and is a crucial measure of perception in robotics AI. While significant progress has been made in anticipating the future actions of individual agents, prior work has larg
Externí odkaz:
http://arxiv.org/abs/2411.01455
Autor:
Li, Bowen, Li, Zhaoyu, Du, Qiwei, Luo, Jinqi, Wang, Wenshan, Xie, Yaqi, Stepputtis, Simon, Wang, Chen, Sycara, Katia P., Ravikumar, Pradeep Kumar, Gray, Alexander G., Si, Xujie, Scherer, Sebastian
Recent years have witnessed the rapid development of Neuro-Symbolic (NeSy) AI systems, which integrate symbolic reasoning into deep neural networks. However, most of the existing benchmarks for NeSy AI fail to provide long-horizon reasoning tasks wit
Externí odkaz:
http://arxiv.org/abs/2411.00773
Autor:
Aryan, FNU, Stepputtis, Simon, Bhagat, Sarthak, Campbell, Joseph, Lee, Kwonjoon, Mahjoub, Hossein Nourkhiz, Sycara, Katia
Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons over their
Externí odkaz:
http://arxiv.org/abs/2410.22626
Autor:
Lin, Muhan, Shi, Shuyang, Guo, Yue, Chalaki, Behdad, Tadiparthi, Vaishnav, Pari, Ehsan Moradi, Stepputtis, Simon, Campbell, Joseph, Sycara, Katia
The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning from human
Externí odkaz:
http://arxiv.org/abs/2410.17389
Volume rendering in neural radiance fields is inherently time-consuming due to the large number of MLP calls on the points sampled per ray. Previous works would address this issue by introducing new neural networks or data structures. In this work, W
Externí odkaz:
http://arxiv.org/abs/2410.19831
Test-time adaptation, which enables models to generalize to diverse data with unlabeled test samples, holds significant value in real-world scenarios. Recently, researchers have applied this setting to advanced pre-trained vision-language models (VLM
Externí odkaz:
http://arxiv.org/abs/2410.12790
Autor:
Drolet, Michael, Stepputtis, Simon, Kailas, Siva, Jain, Ajinkya, Peters, Jan, Schaal, Stefan, Amor, Heni Ben
Amidst the wide popularity of imitation learning algorithms in robotics, their properties regarding hyperparameter sensitivity, ease of training, data efficiency, and performance have not been well-studied in high-precision industry-inspired environm
Externí odkaz:
http://arxiv.org/abs/2408.06536
Publikováno v:
2024 IEEE International Conference on Robotics and Automation (ICRA) 2024
This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The approach inv
Externí odkaz:
http://arxiv.org/abs/2406.01377
Autor:
Wan, Zifu, Zhang, Pingping, Wang, Yuhao, Yong, Silong, Stepputtis, Simon, Sycara, Katia, Xie, Yaqi
Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environments. Leveraging additional modalities (X-modality) like thermal and dep
Externí odkaz:
http://arxiv.org/abs/2404.04256
Autor:
Li, Samuel, Bhagat, Sarthak, Campbell, Joseph, Xie, Yaqi, Kim, Woojun, Sycara, Katia, Stepputtis, Simon
Task-oriented grasping of unfamiliar objects is a necessary skill for robots in dynamic in-home environments. Inspired by the human capability to grasp such objects through intuition about their shape and structure, we present a novel zero-shot task-
Externí odkaz:
http://arxiv.org/abs/2403.18062