Rohit Jayanti

I am a first-year PhD Student at WILLOW, Inria-Paris / ENS-PSL, advised by Prof. Cordelia Schmid. My research interests lie at the intersection of 3D/4D computer vision and dexterous robot learning.

Previously, I was a Master’s student at the Robotics Research Center (RRC), IIIT Hyderabad, advised by Prof. Madhava Krishna where I conducted research on geometric foundation models, open-vocabulary 3D scene understanding, and topological robot navigation.

News

Publications

* equal contribution

PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops

Sarthak Chittawar, Vansh Garg, Aditya Vadali, Krish Pandya, Rohit Jayanti, Sourav Garg, Madhava Krishna
IROS 2026 (Poster 📜)

MASt3R-Nav: WayPixel Navigation in Relative 3D Maps

Vansh Garg, Rohit Jayanti*, Krish Pandya*, Sarthak Chittawar*, Siddharth Tourani, M. Haris Khan, Sourav Garg, Madhava Krishna
ICRA 2026 (Poster 📜)

SegMASt3R: Geometry Grounded Segment Matching

Rohit Jayanti*, Swayam Agrawal*, Vansh Garg*, Siddharth Tourani, M. Haris Khan, Sourav Garg, Madhava Krishna
NeurIPS 2025 (Spotlight 🌟)

QueSTMaps: Queryable Semantic Topological Maps for 3D Scene Understanding

Yash Mehan*, Kumaraditya Gupta*, Rohit Jayanti*, Anirudh Govil, Sourav Garg, Madhava Krishna
IROS 2024 (15min Talk 🎤) CVPR 2024 Workshop on OpenSUN3D ☀️