Zobrazeno 1 - 10
of 2 240
pro vyhledávání: '"P Isler"'
Autor:
Moorthy, Rahul, Isler, Volkan
The capability to learn latent representations plays a key role in the effectiveness of recent machine learning methods. An active frontier in representation learning is understanding representations for combinatorial structures which may not admit w
Externí odkaz:
http://arxiv.org/abs/2410.05530
We study the problem of sampling robot trajectories and introduce the notion of C-Uniformity. As opposed to the standard method of uniformly sampling control inputs (which lead to biased samples of the configuration space), C-Uniform trajectories are
Externí odkaz:
http://arxiv.org/abs/2409.12266
We introduce a new route-finding problem which considers perception and travel costs simultaneously. Specifically, we consider the problem of finding the shortest tour such that all objects of interest can be detected successfully. To represent a via
Externí odkaz:
http://arxiv.org/abs/2407.06366
Autor:
Podjed, Stephanie A., Hickox, Ryan C., Isler, Jedidah C., Böttcher, Markus, Schutte, Hester M.
Publikováno v:
ApJ 968 (2024) 130 (12pp)
Spectropolarimetry is a powerful tool to investigate the central regions of active galactic nuclei (AGNs) as polarization signatures are key to probing magnetic field structure, evolution, and the physics of particle acceleration in jets. Optical lin
Externí odkaz:
http://arxiv.org/abs/2406.17687
We address the problem of stable and robust control of vehicles with lateral error dynamics for the application of lane keeping. Lane departure is the primary reason for half of the fatalities in road accidents, making the development of stable, adap
Externí odkaz:
http://arxiv.org/abs/2405.16358
Autor:
Zhang, Zheyuan, Keles, Elif, Durak, Gorkem, Taktak, Yavuz, Susladkar, Onkar, Gorade, Vandan, Jha, Debesh, Ormeci, Asli C., Medetalibeyoglu, Alpay, Yao, Lanhong, Wang, Bin, Isler, Ilkin Sevgi, Peng, Linkai, Pan, Hongyi, Vendrami, Camila Lopes, Bourhani, Amir, Velichko, Yury, Gong, Boqing, Spampinato, Concetto, Pyrros, Ayis, Tiwari, Pallavi, Klatte, Derk C. F., Engels, Megan, Hoogenboom, Sanne, Bolan, Candice W., Agarunov, Emil, Harfouch, Nassier, Huang, Chenchan, Bruno, Marco J., Schoots, Ivo, Keswani, Rajesh N., Miller, Frank H., Gonda, Tamas, Yazici, Cemal, Tirkes, Temel, Turkbey, Baris, Wallace, Michael B., Bagci, Ulas
Automated volumetric segmentation of the pancreas on cross-sectional imaging is needed for diagnosis and follow-up of pancreatic diseases. While CT-based pancreatic segmentation is more established, MRI-based segmentation methods are understudied, la
Externí odkaz:
http://arxiv.org/abs/2405.12367
Autor:
Gonultas, Burak M., Isler, Volkan
We present a multi-agent reinforcement learning approach to solve a pursuit-evasion game between two players with car-like dynamics and sensing limitations. We develop a curriculum for an existing multi-agent deterministic policy gradient algorithm t
Externí odkaz:
http://arxiv.org/abs/2405.05372
In the robot follow-ahead task, a mobile robot is tasked to maintain its relative position in front of a moving human actor while keeping the actor in sight. To accomplish this task, it is important that the robot understand the full 3D pose of the h
Externí odkaz:
http://arxiv.org/abs/2403.13294
We present a novel technique for modulating the appearance frequency of a few tokens within a dataset for encoding an invisible watermark that can be used to protect ownership rights upon data. We develop optimal as well as fast heuristic algorithms
Externí odkaz:
http://arxiv.org/abs/2312.16547
Autor:
Choi, Hongsuk, Kasahara, Isaac, Engin, Selim, Graule, Moritz, Chavan-Dafle, Nikhil, Isler, Volkan
Recently introduced ControlNet has the ability to steer the text-driven image generation process with geometric input such as human 2D pose, or edge features. While ControlNet provides control over the geometric form of the instances in the generated
Externí odkaz:
http://arxiv.org/abs/2312.09252