Zobrazeno 1 - 10
of 3 791
pro vyhledávání: '"Pokhrel, P."'
The new transmission control protocol (TCP) relies on Deep Learning (DL) for prediction and optimization, but requires significant manual effort to design deep neural networks (DNNs) and struggles with generalization in dynamic environments. Inspired
Externí odkaz:
http://arxiv.org/abs/2412.18200
Autor:
Pokhrel, Sagar, Gea-Banacloche, Julio
We consider a model for a quantum battery consisting of a collection of $N$ two-level atoms driven by a classical field and decaying to a common reservoir. In the extensive regime, where the energy $E$ scales as $N$ and the fluctuations $\Delta E/E \
Externí odkaz:
http://arxiv.org/abs/2412.10586
Statistical modeling of claim severity distributions is essential in insurance and risk management, where achieving a balance between robustness and efficiency in parameter estimation is critical against model contaminations. Two \( L \)-estimators,
Externí odkaz:
http://arxiv.org/abs/2412.09830
Autor:
Khanal, Bimarsha, Poudel, Paras, Chapagai, Anish, Regmi, Bijan, Pokhrel, Sitaram, Khanal, Salik Ram
Plant diseases significantly impact our food supply, causing problems for farmers, economies reliant on agriculture, and global food security. Accurate and timely plant disease diagnosis is crucial for effective treatment and minimizing yield losses.
Externí odkaz:
http://arxiv.org/abs/2412.05996
NCDD: Nearest Centroid Distance Deficit for Out-Of-Distribution Detection in Gastrointestinal Vision
Autor:
Pokhrel, Sandesh, Bhandari, Sanjay, Ali, Sharib, Lambrou, Tryphon, Nguyen, Anh, Shrestha, Yash Raj, Watson, Angus, Stoyanov, Danail, Gyawali, Prashnna, Bhattarai, Binod
The integration of deep learning tools in gastrointestinal vision holds the potential for significant advancements in diagnosis, treatment, and overall patient care. A major challenge, however, is these tools' tendency to make overconfident predictio
Externí odkaz:
http://arxiv.org/abs/2412.01590
Autor:
Kundu, Joyjit, Bhattacharjee, Debjyoti, Josephsen, Nathan, Pokhrel, Ankit, De Silva, Udara, Guo, Wenzhe, Van Winckel, Steven, Brebels, Steven, Perumkunnil, Manu, Herr, Quentin, Herr, Anna
Publikováno v:
DATE 2025
Superconducting Digital (SCD) technology offers significant potential for enhancing the performance of next generation large scale compute workloads. By leveraging advanced lithography and a 300 mm platform, SCD devices can reduce energy consumption
Externí odkaz:
http://arxiv.org/abs/2411.08645
Autor:
Pokhrel, Rishi, Dey, Tanay K.
In this work, we holographically study the hydrodynamical properties of strongly coupled $\mathcal{N} = 4$ SYM baryon rich thermal plasma with large number of flavour quarks. Specifically, we study the drag force acting on the moving heavy probe quar
Externí odkaz:
http://arxiv.org/abs/2410.14384
M2P2: A Multi-Modal Passive Perception Dataset for Off-Road Mobility in Extreme Low-Light Conditions
Autor:
Datar, Aniket, Pokhrel, Anuj, Nazeri, Mohammad, Rao, Madhan B., Pan, Chenhui, Zhang, Yufan, Harrison, Andre, Wigness, Maggie, Osteen, Philip R., Ye, Jinwei, Xiao, Xuesu
Long-duration, off-road, autonomous missions require robots to continuously perceive their surroundings regardless of the ambient lighting conditions. Most existing autonomy systems heavily rely on active sensing, e.g., LiDAR, RADAR, and Time-of-Flig
Externí odkaz:
http://arxiv.org/abs/2410.01105
Most traversability estimation techniques divide off-road terrain into traversable (e.g., pavement, gravel, and grass) and non-traversable (e.g., boulders, vegetation, and ditches) regions and then inform subsequent planners to produce trajectories o
Externí odkaz:
http://arxiv.org/abs/2409.17479
We present VertiEncoder, a self-supervised representation learning approach for robot mobility on vertically challenging terrain. Using the same pre-training process, VertiEncoder can handle four different downstream tasks, including forward kinodyna
Externí odkaz:
http://arxiv.org/abs/2409.11570