publications

2025

1. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

   Gheorghe Comanici, Eric Bieber, Mike Schaekermann, and 3432 more authors

   2025

2024

1. Agricultural Landscape Understanding At Country-Scale

   Radhika Dua, Nikita Saxena, Aditi Agarwal, and 32 more authors

   2024
2. Monitoring Changes In Agricultural Field Boundaries Using Spatiotemporal Remote Sensing Data

   Nikita Saxena, Abigail Annkah, Ishan Deshpande, and 2 more authors

   In EGU General Assembly Conference Abstracts, Apr 2024

   DOI
3. Multi-Fidelity Active Learning with GFlowNets

   Alex Hernandez-Garcia^*, Nikita Saxena^*, Moksh Jain, and 2 more authors

   Apr 2024

2021

1. Learning to Detect: A Semi Supervised Multi-relational Graph Convolutional Network for Uncovering Key Actors on Hackforums

   Nikita Saxena, and Vinti Agarwal

   In 2021 IEEE International Conference on Big Data (Big Data), Apr 2021

   DOI Code
2. Efficient downscaling of satellite oceanographic data with convolutional neural networks

   Nikita Saxena

   SIGSPATIAL Special, Jan 2021

   Abs DOI

   Space-borne satellite radiometers measure Sea Surface Temperature (SST), which is pivotal to studies of air-sea interactions and ocean features. Under clear sky conditions, high resolution measurements are obtainable. But under cloudy conditions, data analysis is constrained to the available low resolution measurements. We assess the efficiency of Deep Learning (DL) architectures, particularly Convolutional Neural Networks (CNN) to downscale oceanographic data from low spatial resolution (SR) to high SR. With a focus on SST Fields of Bay of Bengal, this study proves that Very Deep Super Resolution CNN can successfully reconstruct SST observations from 15 km SR to 5km SR, and 5km SR to 1km SR. This outcome calls attention to the significance of DL models explicitly trained for the reconstruction of high SR SST fields by using low SR data. Inference on DL models can act as a substitute to the existing computationally expensive downscaling technique: Dynamical Downsampling. The complete code is available on this Github Repository.

3. Towards Designing and Exploiting Generative Networks for Neutrino Physics Experiments using Liquid Argon Time Projection Chamber

   Nikita Saxena, Paul Lutkus, Taritree Wongjirad, and 1 more author

   Jan 2021

   Slides