Suggest edit — Saeejith Nair

Title

Name

Note

---
sources:
- https://saeejithnair.github.io/
tags:
- homepage
- bio
title: Saeejith Nair
type: person
visibility: public
---

# Saeejith Nair

*First name sounds like "sigh-jith."*

PhD student in Systems Design Engineering at the University of Waterloo's Vision and Image Processing Lab, advised by Alexander Wong and Yuhao Chen, supported by an NSERC CGS-D. Research at the intersection of efficient ML (neural architecture search for NeRFs and vision transformers), embedded systems (on-device latency prediction), and robotics (simulation pipelines for synthetic data, embodied morphologies, dexterous manipulation). Interested in building embodied systems that can efficiently learn to interact with the world in an open-ended manner.

Currently building [[papiers|Papiers]]; the complete inventory lives in [[projects]].

[Email](mailto:smnair@uwaterloo.ca) · [GitHub](https://github.com/saeejithnair) · [Twitter](https://twitter.com/sighjith) · [LinkedIn](https://www.linkedin.com/in/saeejith/) · [Google Scholar](https://scholar.google.com/citations?user=c1h8n9sAAAAJ)

## Publications

- [NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields](https://arxiv.org/abs/2309.14293) — NewInML @ NeurIPS 2023
- [DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence](https://arxiv.org/abs/2312.05171) — CVIS 2023 (oral)
- [NutritionVerse-Synth: An Open Access Synthetically Generated 2D Food Scene Dataset](https://arxiv.org/abs/2312.06192) — NewInML @ NeurIPS 2023
- [TurboViT: Generating Fast Vision Transformers via Generative Architecture Search](https://arxiv.org/abs/2308.11421) — NewInML @ NeurIPS 2023
- [NutritionVerse: Empirical Study of Various Dietary Intake Estimation Approaches](https://dl.acm.org/doi/10.1145/3607828.3617799) — MADiMa @ ACM Multimedia 2023
- [Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning](https://openaccess.thecvf.com/content/CVPR2023W/NAS/html/Wong_Fast_GraspNeXt_A_Fast_Self-Attention_Neural_Network_Architecture_for_Multi-Task_CVPRW_2023_paper.html) — NAS workshop @ CVPR 2023
- [NutritionVerse-3D: A 3D Food Model Dataset for Nutritional Intake Estimation](https://arxiv.org/abs/2304.05619) — WiCV @ CVPR 2023
- [Faster Attention Is What You Need: A Fast Self-Attention Neural Network Backbone Architecture](https://arxiv.org/abs/2208.06980) — All Things Attention @ NeurIPS 2022
- [MAPLE-Edge: A Runtime Latency Predictor for Edge Devices](https://openaccess.thecvf.com/content/CVPR2022W/EVW/html/Nair_MAPLE-Edge_A_Runtime_Latency_Predictor_for_Edge_Devices_CVPRW_2022_paper.html) — Embedded Vision @ CVPR 2022 (oral)
- [Inferring symbols from demonstrations to support vector-symbolic planning in a robotic assembly task](https://hal.inria.fr/hal-03041290) — SMILES @ ICDL 2020

## Previously

Nuro (hardware acceleration, DSP, comms infrastructure — two internships) · BRAIN Lab, UWaterloo (robotic grasping simulation) · Arcturus Networks (embedded video analytics) · Curtiss-Wright (U-Boot firmware) · DRDC (scheduling optimization) · NXP (DMA simulation for vision processors) · Home Depot (React component library)

---

**2026-07-17** (from https://saeejithnair.github.io/): initial import — minimalist markdown mirror of the public homepage.