Zobrazeno 1 - 10
of 2 092
pro vyhledávání: '"P A, Sleiman"'
Autor:
Bagajo, Joshua, Schwarke, Clemens, Klemm, Victor, Georgiev, Ignat, Sleiman, Jean-Pierre, Tordesillas, Jesus, Garg, Animesh, Hutter, Marco
Differentiable simulators provide analytic gradients, enabling more sample-efficient learning algorithms and paving the way for data intensive learning tasks such as learning from images. In this work, we demonstrate that locomotion policies trained
Externí odkaz:
http://arxiv.org/abs/2411.02189
Autor:
Ataallah, Kirolos, Shen, Xiaoqian, Abdelrahman, Eslam, Sleiman, Essam, Zhuge, Mingchen, Ding, Jian, Zhu, Deyao, Schmidhuber, Jürgen, Elhoseiny, Mohamed
Most current LLM-based models for video understanding can process videos within minutes. However, they struggle with lengthy videos due to challenges such as "noise and redundancy", as well as "memory and computation" constraints. In this paper, we p
Externí odkaz:
http://arxiv.org/abs/2407.12679
Green hydrogen is essential for producing renewable fuels that are needed in sectors that are hard to electrify directly. Hydrogen production in a grid-connected hybrid renewable energy plant necessitates smart planning to meet long-term hydrogen tra
Externí odkaz:
http://arxiv.org/abs/2404.11995
Autor:
Ataallah, Kirolos, Shen, Xiaoqian, Abdelrahman, Eslam, Sleiman, Essam, Zhu, Deyao, Ding, Jian, Elhoseiny, Mohamed
This paper introduces MiniGPT4-Video, a multimodal Large Language Model (LLM) designed specifically for video understanding. The model is capable of processing both temporal visual and textual data, making it adept at understanding the complexities o
Externí odkaz:
http://arxiv.org/abs/2404.03413
The emergence of differentiable simulators enabling analytic gradient computation has motivated a new wave of learning algorithms that hold the potential to significantly increase sample efficiency over traditional Reinforcement Learning (RL) methods
Externí odkaz:
http://arxiv.org/abs/2404.02887
Scenario-based testing of automated driving functions has become a promising method to reduce time and cost compared to real-world testing. In scenario-based testing automated functions are evaluated in a set of pre-defined scenarios. These scenarios
Externí odkaz:
http://arxiv.org/abs/2404.02046
Augmented Reality (AR) applications necessitates methods of inserting needed objects into scenes captured by cameras in a way that is coherent with the surroundings. Common AR applications require the insertion of predefined 3D objects with known pro
Externí odkaz:
http://arxiv.org/abs/2401.14510
Autor:
Safaoui, Sleiman, Vinod, Abraham P., Chakrabarty, Ankush, Quirynen, Rien, Yoshikawa, Nobuyuki, Di Cairano, Stefano
We consider the problem of safe multi-agent motion planning for drones in uncertain, cluttered workspaces. For this problem, we present a tractable motion planner that builds upon the strengths of reinforcement learning and constrained-control-based
Externí odkaz:
http://arxiv.org/abs/2311.00063
Recently, there has been a lot of progress in reducing the computation of deep models at inference time. These methods can reduce both the computational needs and power usage of deep models. Some of these approaches adaptively scale the compute based
Externí odkaz:
http://arxiv.org/abs/2310.02544
Autor:
Safaoui, Sleiman, Summers, Tyler H.
Safety is a core challenge of autonomous robot motion planning, especially in the presence of dynamic and uncertain obstacles. Many recent results use learning and deep learning-based motion planners and prediction modules to predict multiple possibl
Externí odkaz:
http://arxiv.org/abs/2309.08821