Zobrazeno 1 - 10
of 31 785
pro vyhledávání: '"Coskun A."'
Autor:
Hu, Dongting, Chen, Jierun, Huang, Xijie, Coskun, Huseyin, Sahni, Arpit, Gupta, Aarush, Goyal, Anujraaj, Lahiri, Dishani, Singh, Rajesh, Idelbayev, Yerlan, Cao, Junli, Li, Yanyu, Cheng, Kwang-Ting, Chan, S. -H. Gary, Gong, Mingming, Tulyakov, Sergey, Kag, Anil, Xu, Yanwu, Ren, Jian
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to address all of these challenges by developing an extremely small and f
Externí odkaz:
http://arxiv.org/abs/2412.09619
Autor:
Coskun, Izzet, Gündüz, Abuzer
In this paper, we study the existence of a dense orbit for the diagonal $\PGL(n)$ action on self-products of partial flag varieties. We determine when there exists a dense orbit for flag varieties of the form $F(k_1, \dots, k_r; n)^m$ when $k_i = i$
Externí odkaz:
http://arxiv.org/abs/2412.04870
Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe that smaller ViTs are intrinsically the sub-networks of a larger ViT w
Externí odkaz:
http://arxiv.org/abs/2412.04786
Markov chains are simple yet powerful mathematical structures to model temporally dependent processes. They generally assume stationary data, i.e., fixed transition probabilities between observations/states. However, live, real-world processes, like
Externí odkaz:
http://arxiv.org/abs/2411.17528
Autor:
Kag, Anil, Coskun, Huseyin, Chen, Jierun, Cao, Junli, Menapace, Willi, Siarohin, Aliaksandr, Tulyakov, Sergey, Ren, Jian
Neural network architecture design requires making many crucial decisions. The common desiderata is that similar decisions, with little modifications, can be reused in a variety of tasks and applications. To satisfy that, architectures must provide p
Externí odkaz:
http://arxiv.org/abs/2411.04967
Autor:
Pope, Simon A., Roth, Diane J., Bansal, Aakash, Mousa, Mostafa, Rezanejad, Ashkan, Forte, Antonio E., Nash, Geoff. R., Singleton, Lawrence, Langfeldt, Felix, Cheer, Jordan, Henthorn, Stephen, Hooper, Ian R., Hendry, Euan, Powell, Alex W., Souslov, Anton, Plum, Eric, Sun, Kai, de Groot, C. H., Muskens, Otto L., Shields, Joe, De Galarreta, Carlota Ruiz, Wright, C. David, Kocabas, Coskun, Ergoktas, M. Said, Xiao, Jianling, Schulz, Sebastian A., Di Falco, Andrea, Krasavin, Alexey V., Zayats, Anatoly V., Galiffi, Emanuele
Active metamaterials are engineered structures that possess novel properties that can be changed after the point of manufacture. Their novel properties arise predominantly from their physical structure, as opposed to their chemical composition and ca
Externí odkaz:
http://arxiv.org/abs/2411.09711
Direct Preference Optimization (DPO) has emerged as a powerful approach to align text-to-image (T2I) models with human feedback. Unfortunately, successful application of DPO to T2I models requires a huge amount of resources to collect and label large
Externí odkaz:
http://arxiv.org/abs/2410.18013
The Brill-Noether theory of curves plays a fundamental role in the theory of curves and their moduli and has been intensively studied since the 19th century. In contrast, Brill-Noether theory for higher dimensional varieties is less understood. It is
Externí odkaz:
http://arxiv.org/abs/2409.18008
Spectral Graph Convolutional Networks (GCNs) have gained popularity in graph machine learning applications due, in part, to their flexibility in specification of network propagation rules. These propagation rules are often constructed as polynomial f
Externí odkaz:
http://arxiv.org/abs/2409.04813
Autor:
Martin, Joshua, Feldman, Catherine, Siegmann, Eva, Curtis, Tony, Carlson, David, Coskun, Firat, Wood, Daniel, Gonzalez, Raul, Harrison, Robert J., Calder, Alan C.
Publikováno v:
Practice and Experience in Advanced Research Computing 2024 Article no.8
Astrophysical simulations are computation, memory, and thus energy intensive, thereby requiring new hardware advances for progress. Stony Brook University recently expanded its computing cluster "SeaWulf" with an addition of 94 new nodes featuring In
Externí odkaz:
http://arxiv.org/abs/2408.16084