9:00 am - 9:10 am Introduction and Opening remarks
9:10 am - 9:55 am Keynote by Prof. Wei Wang
9:55 am - 10:40 am Keynote by Prof. Marinka Zitnik
10:40 am - 10:55 am Coffee Break / Poster Setup
10:55 am - 11:45 am Poster Session 1 and Student Mentoring Session
Understanding How Paper Writers Use AI-Generated Captions in Figure Caption Writing
Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses
CypEGAT: A Deep Learning Framework Integrating Protein Language Model and Graph Attention Networks for Enhanced CYP450s Substrate Prediction (Visa Issue)
Multi-LLM Collaborative Caption Generation in Scientific Documents
Towards LLM-Driven Multi-Agent Pipeline for Drug Discovery: Neurodegenerative Diseases Case Study (Visa Issue)
DYNA-SKILL: Dynamic Self-Prompting Knowledge Graphs for Improving Logical Reasoning in Language Models
What Would You Ask When You First Saw $a^2+b^2=c^2$? Evaluating LLM on Curiosity-Driven Questioning
Profiling and Analyzing Climate Change Statements in IPCC Reports
11:55 am - 12:25 pm Lunch Break
12:25 pm - 13:15 pm Poster Session 2
Clustering Time Series Data with Gaussian Mixture Embeddings in a Graph Autoencoder Framework
AuditBench: A Benchmark for Large Language Models in Financial Statement Auditing
DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration
Bridged Clustering: Learning across Unsupervised Datasets
LLMs Tackle Meta-Analysis: Automating Scientific Hypothesis Generation with Statistical Rigor
Reflection System for the Abstraction and Reasoning Corpus
ResearchCodeAgent: An LLM Multi-Agent system for automated codification of research methodologies
13:15 pm - 14:00 pm Keynote by Prof. Doug Downey
14:00 pm - 14:45 pm Keynote by Prof. Aviad Levis
14:45 pm - 15:30 pm Keynote by Prof. Jinho Choi
15:30 pm - 15:45 pm Coffee Break
15:45 pm - 16:30 pm Keynote Speaker by Dr. Cong Lu
16:30 pm - 17:00 pm Panel Discussion AI4Research: Frontiers in Methodology, Challenges, and Ethical Considerations
17:00 pm - 18:00 pm Oral paper session (12 min talk + 3 min QA)
Towards Scalable Oversight: Meta-Evaluation of LLMs as Evaluators via Agent Debate (17:00 - 17:15) (Visa Issue)
A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion (17:00- 17:15)
Learning to Generate Research Idea with Dynamic Control (17:15- 17:30)
Empowering AI as Autonomous Researchers: Evaluating LLMs in Generating Novel Research Ideas through Automated Metrics (17:30- 17:45)
AAAR-1.0: Assessing AI's Potential to Assist Research (17:45- 18:00)
18:00pm - 18:10 pm Closing remarks