Date: November 8, 2024
Location: Engineer 2-180 and Baskin Engineer Courtyard
The UCSC AI Graduate Student Research Symposium provides AI students and faculty a platform to share their work, exchange ideas, and foster collaboration. This event welcomes contributions from all stages of research work.
In addition to AI-specific research, students from related fields are encouraged to participate in oral/poster presentations (CSE, NLP, and CM students are highly welcome). Join us for a day of insightful talks, lively discussions, and the opportunity to receive valuable feedback from peers and faculty.
09:00am - 09:30am
Registration & Breakfast
09:30am - 10:45am
Oral Presentations (Chair: Jeffrey Flanigan)
25 minutes each
Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel. Brendan King
Unifying and Applying Neuro-Symbolic: NeSy Reasoning, Modeling Patterns, and Tasks. Connor Pryor
IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues. Diji Yang
10:45am - 11:00am
Break
11:00am - 12:00pm
Panel (Chair: Leilani Gilpin)
Panelist: Biagio Mattia La Rosa
Panelist: Connor Pryor
Panelist: Manolis Nikolakakis
12:00pm - 13:30pm
Lunch Time (Food provided)
13:30pm - 15:10pm
Oral Presentations (Chair: Yi Zhang)
(25 minutes each)
Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA. Qianqi Yan
Improving the faithfulness of LLM-based abstractive summarization with span-level unlikelihood training. Sicong Huang
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond. Minghao Liu
Understanding Neurons in Deep Neural Networks. Biagio La Rosa
15:10pm - 16:30pm
Poster Session (w/ coffee and snack)
Faculty Chair: Yi Zhang (yiz@ucsc.edu)
Student Chair: Diji Yang (dyang39@ucsc.edu)
Sponsor: Lise Getoor (getoor@ucsc.edu)
Administrative Support: Cynthia McCarley (cynmccar@ucsc.edu)
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond
Minghao Liu
Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel
Brendan King
Unifying and Applying Neuro-Symbolic: NeSy Reasoning, Modeling Patterns, and Tasks
Connor Pryor
GPS4LLM - Graph-based Planning System for Large Language Model
Samyak Rajesh Jain
Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA
Qianqi Yan
Improving the faithfulness of LLM-based abstractive summarization with span-level unlikelihood training
Sicong Huang
IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues
Diji Yang
Wildfire Evacuation Simulation for Civil Engineering Research in XR
Samir Ghosh
Advancing Web-Based Visual Question Answering with Efficient Image-Text Alignment
Shubham Gaur
Right this way: Can VLMs Guide Us to See More to Answer Questions?
Li Liu
Explainable AI and Autograders for Education
Aaja Ouellette
UCSC NLP at SemEval-2024 Task 10: Emotion Discovery and Reasoning its Flip in Conversation (EDiReF)
Steven Au
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
Haoqin Tu
Enhancing Mobile "How-to" Queries with Automated Search Results Verification and Reranking
Lei Ding
Future-Guided Learning: A Predictive Approach To Enhance Time-Series Forecasting
Skye Gunasekaran