Zobrazeno 1 - 10
of 29 957
pro vyhledávání: '"Karimi P"'
Autor:
Monsefi, Amin Karimi, Zhou, Mengxi, Monsefi, Nastaran Karimi, Lim, Ser-Nam, Chao, Wei-Lun, Ramnath, Rajiv
We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. Prior work in this direction masks out pre-defined frequencies in the input image and employs a reconstruction loss
Externí odkaz:
http://arxiv.org/abs/2409.10362
Autor:
Holighi, Amirhossein Kheiri, Hajibekandeh, Seyed Sobhan Hosseini, Behbahani, Amirhossein Gholizadeh, Khatibi, Kian, Shabestari, Saina Najafi, Ghoreishi, Ghazal, Dadnavi, Aria, Sadeghi, Saba, Makhsous, Shahriar Karimi, Jamshidi, Matin, Abadi, Mandana Shabanzadeh Nasrolah, Moaiyeri, Mohammad Hossein
This paper presents Auriga Robotics' autonomous vehicle, developed at Shahid Beheshti University's Robotics and Intelligent Automation Lab, as part of the team's entry for the 2024 RoboCup IranOpen competition. The vehicle is a 1:10 scale car equippe
Externí odkaz:
http://arxiv.org/abs/2410.11746
Autor:
Downing, Max, Karimi, Faisal
We investigate the modular properties of Generalised Gibbs Ensembles (GGEs) in two dimensional conformal field theories. These are obtained by inserting higher spin charges in the expressions for the partition function of the theory. We investigate t
Externí odkaz:
http://arxiv.org/abs/2410.06288
We consider deep deterministic policy gradient (DDPG) in the context of reinforcement learning with sparse rewards. To enhance exploration, we introduce a search procedure, \emph{${\epsilon}{t}$-greedy}, which generates exploratory options for explor
Externí odkaz:
http://arxiv.org/abs/2410.05225
Autor:
Dinis, Isaac, Wildi, François, Ségransan, Damien, Gupta, Vaibhav, Karimi, Alireza, Tallon, Michel, Bosc, Isabelle, Langlois, Maud, Loupias, Magali, Bechet, Clémentine, Thiébaut, Eric, Goulas, Charles, Ferreira, Florian, Boccaletti, Anthony, Vidal, Fabrice, Kulcsar, Caroline, Raynaud, Henri-François, Galland, Nicolas, Kasper, Markus, Milli, Julien, Mouillet, David, Schreiber, Laura, Diolaiti, Emiliano, Gratton, Raffaele, Chauvin, Gael
This study introduces a novel frequency-based data-driven controller for adaptive optics, using power spectral density for optimization while ensuring stability criteria. It addresses disturbance rejection, command amplitude constraints and system tr
Externí odkaz:
http://arxiv.org/abs/2410.05123
Autor:
Navard, Pouyan, Monsefi, Amin Karimi, Zhou, Mengxi, Chao, Wei-Lun, Yilmaz, Alper, Ramnath, Rajiv
Recent advances in diffusion models have significantly improved text-to-image (T2I) generation, but they often struggle to balance fine-grained precision with high-level control. Methods like ControlNet and T2I-Adapter excel at following sketches by
Externí odkaz:
http://arxiv.org/abs/2410.01595
Effective summarisation evaluation metrics enable researchers and practitioners to compare different summarisation systems efficiently. Estimating the effectiveness of an automatic evaluation metric, termed meta-evaluation, is a critically important
Externí odkaz:
http://arxiv.org/abs/2409.19507
Autor:
Spooner, Annette, Moridani, Mohammad Karimi, Safarchi, Azadeh, Maher, Salim, Vafaee, Fatemeh, Zekry, Amany, Sowmya, Arcot
The complementary information found in different modalities of patient data can aid in more accurate modelling of a patient's disease state and a better understanding of the underlying biological processes of a disease. However, the analysis of multi
Externí odkaz:
http://arxiv.org/abs/2409.13791
Autor:
Satrya, Christoforus Dimas, Chang, Yu-Cheng, Upadhyay, Rishabh, Makinen, Ilari K., Peltonen, Joonas T., Karimi, Bayan, Pekola, Jukka P.
Superconducting circuits provide a versatile and controllable platform for studies of fundamental quantum phenomena as well as for quantum technology applications. A conventional technique to read out the state of a quantum circuit or to characterize
Externí odkaz:
http://arxiv.org/abs/2409.13417
Autor:
Karimi, Raika, Faez, Faezeh, Zhang, Yingxue, Li, Xing, Chen, Lei, Yuan, Mingxuan, Biparva, Mahdi
Contemporary hardware design benefits from the abstraction provided by high-level logic gates, streamlining the implementation of logic circuits. Logic Synthesis Optimization (LSO) operates at one level of abstraction within the Electronic Design Aut
Externí odkaz:
http://arxiv.org/abs/2409.10653