Four Students Receive Honorable Mention in CRA Undergraduate Research Awards

Nadharm Dhiantravan, Joel Goh, Marko Veljanovski, and Garrett Weil made significant contributions to undergraduate research projects

Four Northwestern Computer Science students — Nadharm Dhiantravan, Joel Goh, Marko Veljanovski, and Garrett Weil — received honorable mentions in the Computer Research Association (CRA) 2023-2024 Outstanding Undergraduate Researcher Award competition.

The nationwide award program, sponsored this year by Mitsubishi Electric Research Labs, recognizes undergraduate students who demonstrate exemplary potential in computing research.

“We are incredibly proud of our amazing students doing so well in the CRA undergraduate research competition,” said Samir Khuller, Peter and Adrienne Barris Chair of Computer Science at Northwestern Engineering. “This is a nationwide competition and incredibly hard to get selected with many top universities nominating students.”

Nadharm Dhiantravan

Adviser: Peter Dinda

Dhiantravan is a fourth-year student earning a combined bachelor’s degree and master’s degree in computer science. A member of the Prescience Lab, Dhiantravan is advised by Peter Dinda, professor of computer science and (by courtesy) electrical and computer engineering at Northwestern Engineering.

“I’m honored to have been selected for this recognition,” Dhiantravan said. “Conducting research with the Prescience Lab has been the highlight of my undergraduate experience and I am very thankful for the mentorship that I’ve received from Professor Dinda and the PhD students in the lab.”

Dhiantravan’s research interests lie at the intersection between hardware and software. He focuses primarily on low-level computer systems optimization, studying operating system kernels, virtualization, and memory management.

Dhiantravan is currently working on creating specialized optimizations in kernel routines and subsystems — such as exception handling and memory management — aimed at supporting greater performance for specific user-space applications.

Joel Goh

Adviser: Brenna Argall

Joel GohGoh is a fourth-year student pursuing a bachelor’s degree in biomedical engineering and a master’s degree in computer science at the McCormick School of Engineering. He is a member of the Assistive and Rehabilitation Robotics Laboratory (argallab) at the Shirley Ryan AbilityLab, directed by Brenna Argall, associate professor of computer science and mechanical engineering at Northwestern Engineering, and associate professor of physical medicine and rehabilitation at Northwestern University’s Feinberg School of Medicine.

Goh is particularly interested in the use of human-robot collaboration and shared autonomy to help make medical devices more accessible. His research focuses on improving partial autonomy in powered wheelchairs to help users with obstacle avoidance, navigation, route planning, and spatially constrained maneuvers.

Goh is a research assistant with Project Drive, a three-year, $5 million Phase 2 National Science Foundation Convergence Accelerator project led by Argall, which aims to bring to market the first active driving assistance system for power wheelchairs, increasing access to safe, independent wheelchair operation.

Goh helped develop a new two-prong additive assistance system to improve the robustness and autonomy of the LUCI sensor-based wheelchair driver assistance system. The reactive assistance functionality signals the wheelchair to rotate when it detects an obstacle to aid the user in maneuvering around. The route assistance implements simultaneous localization and mapping with path planning so the wheelchair can compute a safe path and navigate the wheelchair to a desired goal. Goh is currently designing graphical user interface prototypes that will allow users to alter the level of assistive technology.

“This award celebrates the effort that I have put in — from late-night debugging to long bus rides in the winter — to try to push the boundary of knowledge at the intersection of robotics and assistive rehabilitation,” Goh said.

Marko Veljanovski

Adviser: Zach Wood-Doughty

Marko VeljanovskiVeljanovski is a third-year student pursuing a double major in computer science and mathematics. Veljanovski is interested in the field of natural language processing (NLP), with a particular focus on large language models (LLMs). Veljanovski works on a variety of theoretical and applied projects, ranging from the design of causal estimators to improvements in abstractive summarization to creating more efficient LLM transfer learning methods.

“I'm truly honored and grateful to receive an honorable mention in the CRA Outstanding Undergraduate Research Awards,” Veljanovski said. “This recognition is a huge encouragement for my continued pursuit in machine learning research. It's really exciting to know that my efforts are on the right track, and I'm thrilled to be acknowledged by such a respected award.”

Veljanovski was first author on the paper “DoubleLingo: Causal Estimation with Large Language Models,” which focused on the design of a causal estimator model that adjusts for textual confounders. On a novel text RCT dataset, Veljanovski was able to achieve the lowest estimation error compared to other estimators in the literature.

Veljanovski also competed in the University of Toronto’s five-month ProjectX machine learning competition focused on computational efficiency. The five-member Northwestern team designed a more efficient transfer learning technique that can be applied to any large language model. The team obtained a 170-times speedup compared to the default method of fully-finetuning all model parameters and a 10 percent increase in accuracy and model performance against similarly efficient models.

“My involvement with the team proved to be both immensely beneficial and enjoyable. While the significance of the research itself was undeniable, the opportunity to work alongside other like-minded students was equally as important,” Veljanovski said. “Collaboration is a cornerstone of research and learning to effectively work with others is vital for my development as a researcher.”

Veljanovski is advised by Zach Wood-Doughty, assistant professor of instruction in Northwestern Engineering.

Garrett Weil

Adviser: Peter Dinda

Garrett WeilWeil is a fourth-year student in computer science at Northwestern Engineering with a double major in philosophy through Northwestern’s Weinberg College of Arts and Sciences.

A member of Dinda’s Prescience Lab, Weil collaborates closely with Michael Wilkins (PhD '23) on a project to pioneer a high-level programming model for distributed systems using the task-oriented DMPL programming language. Weil and Wilkins aim to alleviate the burden of application developers in high performance computing — who are typically domain experts in fields such as chemistry or physics — while providing comparable performance to existing, more complicated models.

“Doing so also lowers the barrier to entry for new developers in the space and encourages the involvement of other fields,” Weil said.

Weil was second author on the group’s research paper — “Evaluating Functional Memory-Managed Parallel Languages for HPC using the NAS Parallel Benchmarks” — which he presented with Wilkins at the IEEE International Parallel and Distributed Processing Symposium conference last spring.

“I love research because I get to learn from colleagues I admire while spending time trying to answer questions we're not always sure will turn out well,” Weil said. “I know I still have a lot to learn, but being recognized by an organization as significant as the CRA gives me good confidence that I'm on the right track and makes me proud of the work we've done so far.”

Weil is vice president of the Responsible Artificial Intelligence Student Organization (RAISO), Northwestern's student organization dedicated to the ethics, diversity, and social impacts of AI and modern technology. He plans to continue applying the skills he’s acquired through his involvement with the club, research, and academics to work on projects across a range of interests.

“I’m so grateful to Peter and Mike for the opportunities they’ve given me, and to the Prescience Lab for helping me find community at a new school,” said Weil, who is a transfer student to Northwestern.

McCormick News Article