Zobrazeno 1 - 10
of 15 194
pro vyhledávání: '"Oguzhan, A."'
This paper introduces SmartBSP, an advanced self-supervised learning framework for real-time path planning and obstacle avoidance in autonomous robotics navigating through complex environments. The proposed system integrates Proximal Policy Optimizat
Externí odkaz:
http://arxiv.org/abs/2412.02176
Autor:
Ozden, Tarik Can, Kara, Ozgur, Akcin, Oguzhan, Zaman, Kerem, Srivastava, Shashank, Chinchali, Sandeep P., Rehg, James M.
Current image immunization defense techniques against diffusion-based editing embed imperceptible noise in target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming re-optimization for
Externí odkaz:
http://arxiv.org/abs/2411.17957
In recent years, significant progress has been made in collecting large-scale datasets to improve segmentation and autonomous driving models. These large-scale datasets are often dominated by common environmental conditions such as "Clear and Day" we
Externí odkaz:
http://arxiv.org/abs/2411.16776
Autor:
Yigit, Oguzhan, Wilson, Richard C.
The Laplace-Beltrami operator has established itself in the field of non-rigid shape analysis due to its many useful properties such as being invariant under isometric transformation, having a countable eigensystem forming an orthonormal basis, and f
Externí odkaz:
http://arxiv.org/abs/2411.08272
Despite AI advancements, individuals without software or hardware expertise still face barriers in designing wearable electronic devices due to the lack of code-free prototyping tools. To eliminate these barriers, we designed ProtoBot, leveraging lar
Externí odkaz:
http://arxiv.org/abs/2410.08340
We present the first example of an interacting Carroll supersymmetric field theory with both temporal and spatial derivatives, belonging to the Galileon class, where the non-linear field equation remains second-order in derivative. To achieve this, w
Externí odkaz:
http://arxiv.org/abs/2409.15428
This paper introduces the parallel network-based spoofing-aware speaker verification (SASV) system developed by BTU Speech Group for the ASVspoof5 Challenge. The SASV system integrates ASV and CM systems to enhance security against spoofing attacks.
Externí odkaz:
http://arxiv.org/abs/2408.15877
We introduce a novel and extensible benchmark for large language models (LLMs) through grid-based games such as Tic-Tac-Toe, Connect Four, and Gomoku. The open-source game simulation code, available on GitHub, allows LLMs to compete and generates det
Externí odkaz:
http://arxiv.org/abs/2407.07796
Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. We propose a spoofing-robust ASV system optimized directly for the recently introduced architecture-agnostic detection cost function (a-DCF), which allows targeting a de
Externí odkaz:
http://arxiv.org/abs/2407.04034
Advancements in DeepFake (DF) audio models pose a significant threat to voice authentication systems, leading to unauthorized access and the spread of misinformation. We introduce a defense mechanism, SecureSpectra, addressing DF threats by embedding
Externí odkaz:
http://arxiv.org/abs/2407.00913