All Posts

I am not an avid reader, but I enjoy reading self-help or philosophy books to improve my life. This book is more philosophy than self-help. The author Ryan Holiday talks about stoics' writing by giving examples from wars and politics. Why I read this book: I read this book because I was fascinated by stoics' writing and how they lived lives free of worry and stress that we in modern days are overwhelmed by. I could have read the original texts by Marcus Aurelius, Seneca, and

Computer vision is moving fast, but the most interesting trend is not just “bigger models.” The field is shifting toward general-purpose visual systems: models that can segment, detect, track, estimate depth, understand 3D structure, and work across images, videos, and real-world environments with less task-specific training. Recent papers show a clear pattern. Researchers are trying to make computer vision models more flexible, more efficient, and more useful outside control

The robotics landscape is undergoing a fundamental shift. For decades, robots were programmed with rigid, hand-crafted rules — tell it exactly what to do, in exactly what order, and it will do it. But that paradigm is crumbling fast. A new class of AI models — Vision-Language-Action (VLA) models — is enabling robots to understand natural language instructions, perceive their environment visually, and translate that understanding directly into physical action. No rigid scripts

The computer vision landscape has undergone a seismic shift in 2026. As someone working at the intersection of deep learning and robotics, I've witnessed firsthand how Vision Transformers (ViTs) have fundamentally changed how we approach real-time object detection and tracking. DETR-X and the End of Anchor Boxes The latest iteration of Detection Transformers, DETR-X, has finally achieved what YOLO dominated for years: sub-10ms inference on edge devices. Unlike traditional anc