CV

Research Engineer

Apple

• Designed an auto-improvement pipeline to improve the performance of long-horizon agents on human interaction understanding tasks.
• Owned agent development infrastructure, integrating simulation and evaluation workflows.
• Defined evaluation protocols and scoring rubrics to assess the quality and behavior of multimodal agents and guide model improvements.

Research Intern

Google Beam (Hosts: Jungyeon Park, Srinivas Kaza)

• Designed a novel transformer architecture for scaling novel view synthesis using diffusion-generated views (ICCV 2025; patent application filed).
• Achieved state-of-the-art novel view synthesis on Re10K, ACID, and DL3DV, and improved cross-dataset generalization using synthetic training data.

Research Intern

Deep Imagination Research, NVIDIA (Mentors: J.P. Lewis, Ming-Yu Liu)

• Built a zero-shot pipeline to segment 3D mesh parts and estimate materials and physical properties using multi-view foundation-model features and multimodal reasoning (U.S. Patent Application 19/024,394).

Research Intern

Adobe Inc (Mentor: Yuqian Zhou)

• Developed Control2Control for training-free image editing from sketches, poses, and layouts.
• Designed a novel attention transfer method for identity-preserving editing using human-drawn control signals.

Research Intern

Mitsubishi Electric Research Labs (Mentors: Tim Marks, Anoop Cherian)

• Developed Steered Diffusion, an energy-based approach for zero-shot conditioning of diffusion models through inference-time guidance (ICCV 2023).

Scale-Wise VAR is Secretly Discrete Diffusion

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), accepted

Amandeep Kumar*, Nithin Gopalakrishnan Nair*, Vishal M. Patel. * Equal contribution.

PETALface: Parameter Efficient Transfer Learning for Low-Resolution Face Recognition

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Oral

Kartik Narayan, Nithin Gopalakrishnan Nair, Jennifer Xu, Rama Chellappa, Vishal M. Patel.

GenDeg: Diffusion-Based Degradation Synthesis for Generalizable All-in-One Image Restoration

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Sudarshan Rajagopalan, Nithin Gopalakrishnan Nair, Jay N. Paranjape, Vishal M. Patel.

Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data

IEEE/CVF International Conference on Computer Vision (ICCV)

Nithin Gopalakrishnan Nair*, Srinivas Kaza*, Xuan Luo, Vishal M. Patel, Stephen Lombardi, Jungyeon Park. * Equal contribution.

CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Yasiru Ranasinghe, Nithin Gopalakrishnan Nair, Wele Gedara Chaminda Bandara, Vishal M. Patel.

MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models

European Conference on Computer Vision (ECCV)

Nithin Gopalakrishnan Nair, Jeya Maria Jose Valanarasu, Vishal M. Patel.

Unite and Conquer: Plug&Play Multi-Modal Synthesis Using Diffusion Models

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Nithin Gopalakrishnan Nair, Wele Gedara Chaminda Bandara, Vishal M. Patel.

Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis

IEEE/CVF International Conference on Computer Vision (ICCV)

Nithin Gopalakrishnan Nair, Anoop Cherian, Suhas Lohit, Ye Wang, Toshiaki Koike-Akino, Vishal M. Patel, Tim K. Marks.

Ph.D.

Johns Hopkins University

Electrical and Computer Engineering

• Advisor: Prof. Vishal M. Patel
• GPA: 3.96/4.0

B.Tech and M.Tech Dual Degree

Indian Institute of Technology Madras

Electrical Engineering

• CGPA: 9.0/10.0

All India Rank 454 in IIT-JEE Advanced 2015

IIT-JEE

From 1.5 million candidates

State Rank 4 in KEAM 2015

KEAM

From over 200,000 candidates

Top 0.1% in AISSCE 2015

Central Board of Secondary Education, India

Awarded certificate for exceptional performance

Kishore Vaigyanik Protsahan Yojana (KVPY) Scholarship 2014

Government of India

Given to top 1000 from 300,000 candidates to pursue study in Sciences

All India Topper in NPTEL Analog Electronic Systems

NPTEL

Top scorer nationwide