CS Undergraduate Research Symposium 2023

The CS Undergrad Research Symposium is an end-of-term event to showcase the research of senior undergraduate students and network with mentors and other students!

The event will be formatted as a poster session and will take place in the SFU Applied Sciences Building(ASB) Atrium (below the Applied Sciences Office spaces).

There will be prizes, and lunch/refreshments will be served.

Event Schedule

12:30 - 1:00 pm - Welcome + lighting talk (30 sec each)

1:00 - 2:30pm - Poster session + lunch

2:40 - 3:00 - Faculty Talk

3:00 - 3:15 - Awards

The below SFU computing science professors will be presenting their research at the event:

Anders Miltner, Assistant Professor

Title: Type-Directed Program Synthesis

Abstract: Tools like Github's Copilot and OpenAI’s ChatGPT have shown that automatic code generation can help automate many of the tedious aspects of software development. However, there is a key flaw in these automated programming systems — they often write bad code! Not only is this code often not achieve the desired functional properties, it often doesn’t even pass the parsing or type-checking steps of compilation. Nefariously, however, this code often *looks* correct. In this talk, we will show some alternative approaches to code generation that can jensure the correctness of the generated code. We will end by analyzing the compatibility of neural and symbolic approaches, and showing some paths towards efficient generation of correct code.

Biography: Anders Miltner is an Assistant Professor at Simon Fraser University. He received his PhD from Princeton University in 2020, and worked as a Postdoctoral Fellow at UT Austin from 2020 to 2022. Anders has published in multiple top Programming Language venues like POPL, PLDI, ICFP, and OOPSLA. Anders has received distinguished paper awards from POPL and PLDI.

Jason Peng, Assistant Professor

Abstract: Humans are capable of performing awe-inspiring feats of agility by drawing from a vast repertoire of diverse and sophisticated motor skills. This dynamism is in sharp contrast to the narrowly specialized and rigid behaviors commonly exhibited by artificial agents in both simulated and real-world domains. How can we create agents that are able to replicate the agility, versatility, and diversity of human motor behaviors? In this talk, we present motion imitation techniques that enable agents to learn large repertoires of highly dynamic and athletic behaviors by mimicking demonstrations. We begin by presenting a motion imitation framework that enables simulated agents to imitate complex behaviors from reference motion clips, ranging from common locomotion skills such as walking and running, to more athletic behaviors such as acrobatics and martial arts. The agents learn to produce robust and life-like behaviors that are nearly indistinguishable in appearance from motions recorded from real-life actors. We then develop models that can reuse and compose skills learned through motion imitation to tackle challenging downstream tasks. In addition to developing controllers for simulated agents, our approach can also synthesize controllers for robots operating in the real world. We demonstrate the effectiveness of our approach by developing controllers for a large variety of agile locomotion skills for bipedal and quadrupedal robots.

Biography: Jason is an Assistant Professor in the School of Computing Science at SFU, and a part-time Research Scientist at NVIDIA. He received a PhD at UC Berkeley, and an MSc and BSc at UBC. His work leverages machine learning to develop motor control models that enable simulated agents and real-world robots to reproduce the agile and versatile motor skills exhibited by humans and other animals. He has received an Outstanding Doctoral Dissertation Award from ACM SIGGRAPH, and best paper awards at RSS and SCA.