Phu Pham

I am a Ph.D. student in Computer Science at Purdue University, advised by Prof. Aniket Bera. My research focuses on computer vision and graphics, machine translation, reinforcement learning and robotics. My recent work includes 3D reconstruction from 2D images using diffusion models and neural radiance fields, DNN based predictive models for spatial and spectral data, transformer-based multimodal machine translation and multiagent path planning.

Before pursuing the Ph.D., I gained extensive experience in the industry as a full-stack software engineer in Finland. I worked for several startups and accumulated over 5 years of experience in software development.

Previously, I completed my Master’s degree in Big data and large-scale computing with a minor in Machine learning and data mining from Aalto University, advised by Dr. Jorma Laaksonen. I also did my undergrad in Information Technology at Metropolia University of Applied Sciences.

Publications

Crowd-Aware Multi-Agent Pathfinding With Boosted Curriculum Reinforcement Learning

Phu Pham, and Aniket Bera

2023
DREAM: Decentralized Reinforcement Learning for Exploration and Efficient Energy Management in Multi-Robot Systems

Dipam Patel, Phu Pham, Kshitij Tiwari, and 1 more author

2023
DroNeRF: Real-time Multi-agent Drone Pose Optimization for Computing Neural Radiance Fields

Dipam Patel, Phu Pham, and Aniket Bera

2023
TAIGA: A Novel Dataset for Multitask Learning of Continuous and Categorical Forest Variables From Hyperspectral Imagery

Matti Mõttus, Phu Pham, Eelis Halme, and 3 more authors

IEEE Transactions on Geoscience and Remote Sensing, 2022
RAIST: Learning Risk Aware Traffic Interactions via Spatio-Temporal Graph Convolutional Networks

Videsh Suman, Phu Pham, and Aniket Bera

CoRR, 2020
SeekNet: Improved Human Instance Segmentation via Reinforcement Learning Based Optimized Robot Relocation

Venkatraman Narayanan, Bala Manoghar, Rama RV, and 2 more authors

CoRR, 2020
Deep learning methods for modelling forest biomass and structures from hyperspectral imagery

Phu Pham

2019
The MeMAD Submission to the WMT18 Multimodal Translation Task

Stig-Arne Grönroos, Benoit Huet, Mikko Kurimo, and 8 more authors

In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, Oct 2018

Abs

This paper describes the MeMAD project entry to the WMT Multimodal Machine Translation Shared Task. We propose adapting the Transformer neural machine translation (NMT) architecture to a multi-modal setting. In this paper, we also describe the preliminary experiments with text-only translation systems leading us up to this choice. We have the top scoring system for both English-to-German and English-to-French, according to the automatic metrics for flickr18. Our experiments show that the effect of the visual features in our system is small. Our largest gains come from the quality of the underlying text-only NMT system. We find that appropriate use of additional data is effective.