Skip to content

ADHAYAN / RESEARCH

Research

Independent research preprints shared through ADHAYAN.

Contribute

Sign in with Google and submit an application to publish your research here.

CC BY 4.0

Lightweight Prompt Injection Detection: From Centroid-Based Embedding Classification to a Hybrid Guardrail

Preprint · Independent research

Prashanna Tiwari

Prompt injection remains one of the most practical threats to large language model (LLM) applications. This paper presents a lightweight approach to prompt-injection detection, moving from centroid-based embedding...

prompt injectionLLM securityguardrailsembeddingsclassification
PDF · 1.2 MB Code ↗
MIT

Semantic Segmentation for Autonomous Agricultural Robots: A U-Net Approach with Auto-Generated Labels

Preprint · Independent research

Prashanna Tiwari

This paper presents the development of a semantic segmentation pipeline designed for autonomous navigation in agricultural environments. Inspired by the NATERIDA microbots project—an AI-powered exploration robot...

semantic segmentationU-NetGroundingDINOSegment Anythingagricultural roboticsWebots
PDF · 2.3 MB Code ↗
MIT

Autonomous Edge Robotics: A Comparative Analysis of Behavioral Cloning and Deep Q-Networks in Constrained 2D Environments

Preprint · Independent research

Prashanna Tiwari

The development of lightweight, reactive navigation systems for mobile edge robotics is a critical challenge in modern computer science. Traditional pathfinding relies on heavy, map-based computations which are often...

edge roboticsbehavioral cloningdeep Q-networksreinforcement learningobstacle avoidanceresearch draft
PDF · 402 KB Code ↗