activity
20202025
most citedSite Split of Antiferromagnetic -Mn Revealed by Mn Nuclear Magnetic Resonance

6 citations · 18 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV2025

GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting

Madhav Agarwal, Mingtian Zhang, Laura Sevilla-Lara +1

Speech-driven talking heads have recently emerged and enable interactive avatars. However, real-world applications are limited, as current methods achieve high visual fidelity but…

cs.CR2025

Q-RAN: Quantum-Resilient O-RAN Architecture

Vipin Rathi, Lakshya Chopra, Madhav Agarwal +6

The telecommunications industry faces a dual transformation: the architectural shift toward Open Radio Access Networks (O-RAN) and the emerging threat from quantum computing. O-RAN…

cs.CV2022★ 4 cited

Compressing Video Calls using Synthetic Talking Heads

Madhav Agarwal, Anchit Gupta, Rudrabha Mukhopadhyay +2

We leverage the modern advancements in talking head generation to propose an end-to-end system for talking head video compression. Our algorithm transmits pivot frames intermittent…

cond-mat.str-el2022★ 6 cited

Site Split of Antiferromagnetic -Mn Revealed by Mn Nuclear Magnetic Resonance

Masahiro Manago, Gaku Motoyama, Shijo Nishigori +8

The magnetic structure of antiferromagnetic -Mn has been unclarified for almost 70 years since its magnetism was discovered. We measured the zero-field nuclear magnetic resonanc…

cs.AI2022★ 3 cited

Making AI 'Smart': Bridging AI and Cognitive Science

Madhav Agarwal, Siddhant Bansal

The last two decades have seen tremendous advances in Artificial Intelligence. The exponential growth in terms of computation capabilities has given us hope of developing humans li…

cs.CV2020★ 5 cited

CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images

Madhav Agarwal, Ajoy Mondal, C. V. Jawahar

Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainabl…