I work as a Deep Learning Engineer at Ramblr.ai, where we build AI for the physical world. I focus on automated video annotation flows that help teach AI agents to understand real-world processes, from strawberry harvesting to industrial quality control. On my free time, I enjoy tinkering with Linux systems, experimenting with specialty coffee, hiking, playing the drums, and going down random rabbit holes.
With the recent developments in the field of artificial intelligence, a lot of new use cases are emerging. Developing …
Scene understanding is central to general physical intelligence, and video is a primary modality for …
Show2Instruct enhances LLMs with spatial understanding to validate building plans against …
Semantic scene understanding is crucial aspect of modern day robotic applications. With the recent …
In this work, we take VoteNet, a state-of-the-art deep neural network for object detection, as a …
Extending a Stereo camera Visual Odometry implementation with Optical Flow per the paper by Usenko …
The goal of the project was to conduct experiments and analyze their results on the DCP architecture …
In this project I’ve developed a 3D object detection and tracking pipeline for autonomous …
Implementation of the paper KinectFusion by Microsoft using C++ and CUDA. The goal of the project is …
Implemented vanilla Tracktor with Faster-RCNN using PyTorch. Added a basic motion model and also a …
We extended the paper “Divergence-Free Shape Correspondence by Deformation” and …
Detection of plant diseases via computer vision based systems are being used to identify plant …
Sketches are probabilistic data structures that can provide approximate results within …
This work describes the plant identification system that we submitted to the ExpertLifeCLEF plant …