I’m Jaswanth Reddy, a computer vision and NLP researcher with a BTech from IIT Tirupati. I grew up riding oxcart through the dusty lanes of my village in India, a small memory that still grounds me in where my journey began
My focus is on building practical, reliable ML models. I’ve worked across 3D vision, tracking, and language technologies.
I began my research journey at VAL(IISc), India’s top-ranked computer vision group on CSRankings 2024. There, I worked on 3D reconstruction and object manipulation using Neural Radiance Fields and Gaussian Splatting.
After IISc, I joined ViSAL Lab, where I develop a memory-based long–short term tracking model for transformer architectures. My work spanned both single and multi-object tracking.
I’m currently at AutoAlign.ai, exploring the next generation of NLP applications. My work centers on safety, trustworthiness, and scalable pipelines for large language models. I’ve built guardrails for sensitive tasks, designed evaluation frameworks, and led the development of datasets and training flows that make LLMs more reliable in real-world use.
I enjoy tackling hard technical challenges and collaborating with teams pushing the frontier of AI. If you’re working on something exciting or just want to talk about vision, language, or ML systems, I’d love to connect.
Latest Updates
DEC 1,2025 Reduce and Refine
NOV 11,2025 Tarka Embedding V1
NOV 8,2025 UniC-Lift accepted at AAAI 2026
MAY 11,2025 Tiny Url
MAY 11,2025 Factcheck in SLM
Reach out to me