Thursday, February 24
4:00-5:00 p.m. | Student Poster Session | Zoom (See Below)
- UTCS Graduate Students share their research.
- Please note: All students with Zoom links are available for all or most of the Poster Session. If a student is not available, please feel free to check out their research!
- Need Help? Please come see us at the GradFest Help Desk
Posters
Title: Adversarial Intrinsic Motivation for Reinforcement Learning
Keywords: Reinforcement learning, directed exploration
By: Ishan Durugkar - Peter Stone (Advisor)
Title: FINE WRINKLING ON COARSELY-MESHED THIN SHELLS
Keywords: Physical simulation, geometry desgin
By: Zhen Chen - Etienne Vouga (Advisor)
Title: Neural Program Generation Modulo Static Analysis
Keywords: Deep Learning, ML4Code
By: Yeming Wen - Swarat Chauduri (Advisor)
Title: Connecting Attributions and QA Model Behavior on Realistic Counterfactuals
Keywords: Interpretability, QA
By: Xi Ye - Greg Durrett (Advisor)
Title: Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks
Keywords: robot learning; manipulation; reinforcement learning
By: Soroush Nasiriany - Yuke Zhu (Advisor)
Title: A new data structure for double exponential compression - CFLOBDD
Keywords: Decision Diagrams; quantum simulation
By: Meghana Aparna Sistla - Swarat Chaudhuri (Advisor)
Title: Building State and Action Abstractions for Robot Manipulation
Keywords: general-purpose robots, imitation learning, planning
By: Yifeng Zhu - Yuke Zhu & Peter Stone (Advisors)
Title: Safe Neurosymbolic Learning with Differentiable Symbolic Execution
Keywords: Program Synthesis, Safe Learning, Neurosymbolic Programming
By: Chenxi Yang - Swarat Chaudhuri (Advisor)
Title: Neurosymbolic Reinforcement Learning with Formally Verified Exploration
Keywords: Reinforcement Learning, Formal Methods, Machine Learning Safety
By: Gregory Anderson - Swarat Chaudhuri & Isil Dillig (Advisors)
Title: Expected Value of Communication in Ad Hoc Teamwork
Keywords: Multiagent Systems, Ad Hoc Teamwork
By: William Macke - Peter Stone (Advisor)
Title: Conflict-averse Gradient Descent for Multitask Learning
Keywords: multitask learning, optimization
By: Bo Liu - Peter Stone & Qiang Liu (Advisors)
Title: Program Synthesis from Pixels
Keywords: Computer Vision, Machine Learning, Program Synthesis, Neurosymbolic Learning
By: Atharva Sehgal - Swarat Chaudhuri (Advisor)
Title: Efficient Rank-Ordered Search of Giga-pixel Images with Multi-Agent RL
Keywords: Reinforcement Learning, Computer Vision
By: Rochan Avlur - Chandrajit Bajaj (Advisor)
Title: CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge
Keywords: NLP
By: Yasumasa Onoe - Greg Durrett & Eunsol Choi (Advisors)
Title: Synthesis Guided Reinforcement Learning
Keywords: Program Synthesis, Reinforcement Learning, Deep Learning
By: Josh Hoffman - Swarat Chaudhuri & Joydeep Biswas (Advisors)
Inverse Stackelberg Game Design for Robust Adversarial Learning
Keywords: Stackelberg Games, Robust Adversarial Learning, Object Detection
By: Xiaohan Zuo - Chandrajit Bajaj (Advisor)
Title: Tracking Pancreas Shape Morphology in Type 1 Diabetes Progression
Keywords: topology, T1D, morphology, geometry, pancreas
By: Yorick Sanders - Chandrajit Bajaj (Advisor)
Title: Web Question Answering using Neurosymbolic Program Synthesis
Keywords: Program synthesis
By: Jocelyn Chen - Isil Dillig (Advisor)
Title: APPLR: Adaptive Planner Parameter Learning from Reinforcement
Keywords: Autonomous navigation, reinforcement learning
By: Zifan Xu - Peter Stone (Advisor)
Title: Optimal Stochastic Pontryagin
Keywords: Protein Folding, Optimal Control, Deep reinforcement learning
By: Conrad Li - Chandrajit Bajaj (Advisor)
