arXiv subjects

Suraj Joshi

Publications and source records attributed to Suraj Joshi.

4 recordsLinked to original sources

arXiv2026

Terahertz Phase Inversion via Field-Free Spin-Orbit Torque Switching in an Antenna-Integrated Spintronic Heterostructure

We demonstrate microsecond-timescale electrical control of the terahertz (THz) emission phase in broadband field-free spintronic THz emitters, enabling megahertz-rate phase inversion while overcoming the kilohertz limitations of conventional mechanical and field-driven approaches. Our device integrates an H-dipole antenna with a spintronic heterostructure exhibiting uniaxial magnetic anisotropy, enabling deterministic spin-orbit torque induced in-plane magnetization switching without external magnetic fields. The corresponding THz phase inversion is directly observed in the time domain signal, by applying $1\,\mu \mathrm{s}$ electrical pulses on the bias striplines of the H-dipole. This field-free operation reduces system complexity while significantly extending modulation bandwidth. Our results establish electrically programmable spintronic THz emitters that could be used to develop a compact and scalable platform for integrated on-chip THz devices and ultrafast applications, including phase-sensitive spectroscopy and near-field imaging, where high-speed and precise control of THz waveforms is essential.

cond-mat.mtrl-sci↗

arXiv2025

RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation

Visual augmentation has become a crucial technique for enhancing the visual robustness of imitation learning. However, existing methods are often limited by prerequisites such as camera calibration or the need for controlled environments (e.g., green screen setups). In this work, we introduce RoboEngine, the first plug-and-play visual robot data augmentation toolkit. For the first time, users can effortlessly generate physics- and task-aware robot scenes with just a few lines of code. To achieve this, we present a novel robot scene segmentation dataset, a generalizable high-quality robot segmentation model, and a fine-tuned background generation model, which together form the core components of the out-of-the-box toolkit. Using RoboEngine, we demonstrate the ability to generalize robot manipulation tasks across six entirely new scenes, based solely on demonstrations collected from a single scene, achieving a more than 200% performance improvement compared to the no-augmentation baseline. All datasets, model weights, and the toolkit are released https://roboengine.github.io/

cs.RO↗

arXiv2023

An Efficient Compact Blazed Grating Antenna for Optical Phased Arrays

Phased arrays are vital in communication systems and have received significant interest in the field of optoelectronics and photonics, enabling a wide range of applications such as LiDAR, holography, wireless communication, etc. In this work, we present a blazed grating antenna that is optimized to have upward radiation efficiency as high as 80% with a compact footprint of 3.5 {\mu}m \times 2 {\mu}m at an operational wavelength of 1.55 {\mu}m. Our numerical investigations demonstrate that this antenna in a 64 \times 64 phased array configuration is capable of producing desired far-field radiation patterns. Additionally, our antenna possesses a low side lobe level of -9.7 dB and a negligible reflection efficiency of under 1%, making it an attractive candidate for integrated optical phased arrays.

physics.optics↗

arXiv2023

Brain Tumor Detection using Swin Transformers

The first MRI scan was done in the year 1978 by researchers at EML Laboratories. As per an estimate, approximately 251,329 people died due to primary cancerous brain and CNS (Central Nervous System) Tumors in the year 2020. It has been recommended by various medical professionals that brain tumor detection at an early stage would help in saving many lives. Whenever radiologists deal with a brain MRI they try to diagnose it with the histological subtype which is quite subjective and here comes the major issue. Upon that, in developing countries like India, where there is 1 doctor for every 1151 people, the need for efficient diagnosis to help radiologists and doctors come into picture. In our approach, we aim to solve the problem using swin transformers and deep learning to detect, classify, locate and provide the size of the tumor in the particular MRI scan which would assist the doctors and radiologists in increasing their efficiency. At the end, the medics would be able to download the predictions and measures in a PDF (Portable Document Format). Keywords: brain tumor, transformers, classification, medical, deep learning, detection

eess.IV↗