Wednesday, April 2, 2025

Columbia University – Alfred Lerner Hall

Thank you for your submission to Data Science Day 2025, DSI’s flagship annual event. We look forward to exhibiting your research. Please use this page to search for your project name and find your correlating poster or demo number using the exhibitor map. Please also look at the setup and exhibition timeline. FAQ’s regarding registration, what to bring, and other details are included at the bottom of this page.


Exhibitor Map

View Larger Map

Timeline for Wednesday, April 2

Check-In Location: Exhibitor Table, Broadway Lobby, Alfred Lerner Hall (2920 Broadway, New York, NY 10027). Due to public safety policy, please make sure you have your Eventbrite QR code with you when you arrive. All tickets will be checked at the door. 

8:00 AM – 8:45 AM: ARRIVAL & POSTER DROP OFF

  • We encourage exhibitors to arrive early and attend the program, which offers valuable context for the day’s events. The Data Science Day program can be found on the event landing page.
  • To minimize sound disruption, all teams will leave their poster with DSI event staff, who will then take your project to your assigned easel. Please head into the auditorium and take a seat after you arrive.
  • ALL DEMOS should arrive to set up between 8:00 AM – 8:30 AM.
  • Posters located in front of the stage (P56 – P65) will be set up at the start of the poster session at 1:00 PM.

1:00 PM – 4:00 PM: POSTER AND DEMO SESSION

  • Exhibitors must be stationed by their project during the open session time.

4:00 PM – 5:00 PM: RECEPTION

  • Teams are welcome to continue presenting during the event reception, but this is optional.

5:00 PM – 5:15 PM: BREAKDOWN & EXIT


Table-Based Demos

D01 – Table 1: Augmented Reality Visualization of a Cross-Attention Enhanced 3D Optical Coherence Tomography Volume for Ophthalmic Disease Diagnosis

D02 – Table 1: Artificial Intelligence to Detect Spinal Fluid and Spinal Cord on Ultrasound

D03 – Table 2: Trip Genius: A Fully Automated and Agentic Solution for End-to-End Travel Planning and Booking

D04 – Table 2: GoGo Data Lab: Low-cost sensor data collection on the go

D05 – Table 3: The Choice Mapper

D06 – Table 4: Projects from Ali Hirsa

D07 – Table 5: Ora – A Teacher’s Friend for the Now

D08 – Table 5: rklex AI: Effortless AI Orchestration for Customer-Facing Workflows

D09 SPONSOR PROJECTS – Table 6: Reserved for CUIT Research Computing Services; and the SHARP Program

D10 – Table 7: Digital Twin for Pedestrian Safety Warning at a Single Urban Traffic Intersection

D11 – Table 7: DriveGenVLM: Real-World Video Generation for Vision Language Model Based Autonomous Driving – PI to show their poster at the table

D12 – Table 8: Demo: Intelligent 5G “All-G” Networks Designed and Integrated for Global Operations

D13 – Table 8: Demo: A Full-Duplex Link with Adaptive Self-Interference Cancellation

D14 – Table 9: Scaledown Intersection Testbed


Posters

P01: Full-Duplex Self-Interference Cancellation Control Algorithm

P02: SLAMuZero: Plan and Learn to Map for Joint SLAM and Navigation

P03: Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problems

P04: SPONSOR PROJECT: Undergraduate Research Opportunities

P05: Improving Language Models’ Sensory Understanding via Context-Aware Embedding Interpolations

P06: From Rewards to Videos: Self-Supervised Temporal Pretraining for Inverse Reinforcement Learning & Video Generative Models

P07: Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control

P08: Bibarel: Accelerating Agentic Planning Through Dynamic Parallelism and Live Migration

P09: Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization

P10: Active Exploration via Autoregressive Generation of Missing Data

P11: High-Throughput Angle Extraction via Symmetry-Adapted Filters

P12: SGFormer: Improving spacegroupMining model using Transformer for Determining the Space Group of a Structure from Atomic Pair Distribution Function (PDF)

P13: How to Tell Structures Apart: Data-Driven Analysis of Structural Similarity Measures

P14: Graphical Framework for the Representation of Inorganic Synthesis Reactions and Prediction Using Graph Neural Networks

P15: Unveiling Hidden Symbiotic Stars: A VAE Approach to Anomaly Detection

P16: AI-driven automated system for identification of Phytoplankton in the global oceans

P17: ThunderKittens: GPU Primitives for Fast ML Computation

P18: Energy Efficient Scheduling of AI/ML Workloads on MIG with Dynamic Repartitioning

P19: Volcanology Infrastructure for Computational Tools and Resources: Tephra2 Inversion Workflow

P20: SparseQJL: Efficient KV Cache Compression For Accelerating Large Language Models

P21: Embedded Databases for Servers- RootDB

P22: In Situ Correlative Transmission Electron Microscopy for Experimental Study of Grain Growth in Thin Films

P23: On symbolic regression and Taylor series: How neural networks can lead to analytical solutions

P24: Control of Nonstationary Systems with QPLEX

P25: Hacking the LLM Guardrail: Malicious Injection In Enterprise Dataset & Automatic Threat Assessment

P26: Technical Standards for Decentralized Clinical Trials as a Care Option Leveraged with Hospitals at Home

P27: Powering AI the Next Gold Rush

P28: External Validation of Risk Assessment Model MIRAI on Columbia Screening Cohort

P29: Propaganda Generation Capabilities of Large Language Models AND Comments and Community: Dimensions of YouTube Use – PI to rotate projects on the same easel

P30: A Vision-Based Analysis of Congestion Pricing in New York City

P31: Quantifying Data Reliability in Air Quality Monitoring: A Scoring Framework for Spatio-Temporal Datasets

P32: UN-EARTHED: Construction Ecologies of Soil Remediation

P33: Predicting Middle School Academic Achievement Using Teachers’ Perceptions of School Climate

P34: Reducing the Filtering Effect in Public School Admissions: A Bias-aware Analysis for Targeted Interventions

P35: AI Awareness Survey of Educators

P36: Assessing Graduate Student Attitudes toward ChatGPT and its Effectiveness as a Teaching Tool for Real Estate Finance

P37: Text Mining Analysis and Concept Mapping of 60 Philosophical Texts: Perceiving the Purpose of Education from Ancient Greece to the Postmodern Era

P38: Responsible AI for Educational Equity

P39: AdaptLingo: An Adaptive Speech-to-Speech Conversational Agent Tailored to Users’ English Proficiency Levels

P40: Sex & HIV Education Policies: Insights into sate-mandated school curriculums and their impact on social outcomes from 2009 – 2022

P41: A Lagrangian-Informed Long-Term Dispatch Policy for Coupled Hydropower and Photovoltaic Systems

P42: Spacial Temporal Air Quality Profiling of Chennai City

P43: From Experiments to In-Service: Encoding Structural Damage via Speaker Recognition

P44: From Conflict to Consensus: Using AI for participatory spatial design

P45: Customized FinGPT Search Agents Using Foundation Models

P46: FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning AND LLM-Powered Compliance Agents for Small- and Medium-sized Businesses (SMBs) – PI to rotate projects on the same easel

P47: Imagining the Future: Sociotechnical Imaginaries in Artificial Intelligence Development at OpenAI

P48: Who’s Left Unprotected? Predicting Underinsurance with Spatial CNN Analysis

P49: Analysis of the Order Flow Auction under Proposer-Builder Separation

P50: Conformal Uncertainty Quantification of Electricity Price Predictions for Risk-Averse Storage Arbitrage

P51: Is Cross-Validation the Gold Standard to Estimate Out-of-sample Model Performance?

P52: Consistency Checks for Language Model Forecasters

P53: Distributionally Robust Newsvendor on a Metric

P54: Who Ate the Lunch? A Variational Bayes Algorithm for Identifying Refund Hunters

P55: Integrating Ethics into Data-driven AI Research: Scope, Goals, and Relationship-building

P56: Modeling Dynamic Consumer Preferences with Distribution Shift

P57: DIVAN: A Data Aggregation Visualization System that Focuses on Frequent Data

P58: Uncertainty Quantification for LLM-Based Survey Simulations

P59: AI to Measure Peace with App for Behavior Change

P60: The Utility of SaTScan to identify and map nightlife districts across the USA

P61: Leveraging t-SNE Visualization of Professional Networks for Predictive AI in Transdisciplinary Team Collaboration

P62: Moderation Needs of Youtube Creators

P63: Joint modeling for learning decision-making dynamics in behavioral experiments

P64: Automatic DCIS Segmentation in First Post-Contrast DCE-MRI Image using MA-SAM architecture with pre-trained vision transformer backbone

P65: Diffusion Models for Determining Local Atomic Structure from X-ray Absorption Spectra

P66: Mapping visual categorical selectivity across the whole brain using transformer-based encoders and large-scale generative models

P67: OptiRes-DDPM for Portable OCT Image Quality Enhancement Toward Downstream AI-Based Ophthalmic Disease Diagnosis

P68: AI-CNet3D: An Anatomically-Informed Cross-Attention Network with Consistency-Based Multi-Task Fine-Tuning for Enhanced 3D Glaucoma Detection

P69: Assessing the impact of the Augmented Response Technology on Clinician In-Basket Responses

P70: Leveraging data-driven analyses to improve subpopulation robustness of a schizophrenia prediction model

P71: Mitigating Spurious Invariance in Contrastive Learning: A Probabilistic Self-Supervised Learning Framework for Medical Image Analysis

P72: A 3D-Consistent Framework for T2-Weighted Image Generation and Enhancement Using VIPGAN and Projection-Based Optimization

P73: Decentralized Personalization for Federated Medical Image Segmentation via Gossip Contrastive Mutual Learning

P74: Enhancing Brain Age Estimation with a Multimodal 3D CNN Approach Combining Structural MRI and AI-Synthesized Cerebral Blood Volume Data

P75: The Impact of State Space and Dimensionality on Pancreatic Ultrasound Tumor Segmentation

P76: Quantitative Imaging Analysis of Irradiation-Induced Effects on Ribosome Biogenesis

P77: Leveraging AI for Insights into Corporate Emission Reduction and Climate Action AND The Impact of Biomedical Innovation on U.S. Mortality, 1999-2019: Evidence Partly Based on 286 Million Descriptors of 27 Million PubMed Articles – PI to rotate projects on the same easel

P78: Real-Time Structural Damage Detection Using Kolmogorov-Arnolds Neural Networks and Cepstral Features

P79: Using AI-powered experimental design to create patient-centric clinical studies

P80: Patient-centric approaches for antipsychotic medication research : an application of the Desirability of Outcome Ranking (DOOR) and Global Benefit-Risk Score (GBR)

P81: AI-accelerated Personalized Predictive Modeling with Uncertainty for Neonates with Borderline Left Ventricles

P82: Public Perspectives on the Use of AI in Mental Health with Comparison to Utilization for Somatic Health Applications

P83: Accelerating Drug Discovery through the Automatic Population of a Pharmaceutical Ontology using Knowledge Graphs

P84: A Hybrid Self-supervised And Supervised Deep Learning Framework For Accurate Volumetric Breast Density Segmentation From 3D Reconstructed DBT Images

P85: Developing a Novel Approach to Video Analysis Using Multimodal Large Language Models for Fall Risk Assessment: A Pilot Study

P86: Multi-site Pragmatic Cluster Randomized Controlled Trial of the CONCERN Early Warning System

P87: Designing a dynamic user-centric screening app for diverse scenarios

P88: FEST: Enhancing Genetic Risk Prediction through Federated Semi-Supervised Transfer Learning with Inaccurate Electronic Health Record Data

P89: Automating Health Problem Identification and Mapping to the Omaha System Using LLMs

P90: Permanent Proxies for Bimanual Selection and Manipulation in VR

P91: Investigating the Impact of Agricultural Burning on Air Quality in West Bengal​

P92: SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions

P93: Eye-Track-ML: A Machine Learning Pipeline for Automated Frame-by-Frame Coding of Eye-Tracking Videos

P94: Distributed VLMs: Efficient Vision-Language Processing through Cloud-Edge Collaboration

P95: Data-Driven Traffic Simulation for an Intersection in a Metropolis

P96: Evaluating Zero-Shot Image Tagging for Urban Traffic Intersection Scenes

P97: How does the infant brain respond to complexity in various contexts?

P98: Predicting the DNA binding specificity of transcription factor mutants using family-level biophysically interpretable machine learning

P99: A Call for New York Robotics and Research Manufacture Hub – ADI CodeCollab

P100: Equal Access, Unequal Outcomes: Hierarchical Cluster Analysis of Advanced Coursework and Postsecondary Outcomes in North Carolina High Schools

P101: Collective inference of the truth of propositions from crowd probability judgments

P102: Learning from Expert Clinician Gaze: How FOI ViT’s Success Exposes Multimodal Medical AI’s Adaptation Gaps

P103: LifeSpan Index in Different Areas

P104: 6G as a Sensor: Repurposing 140 GHz Wireless Signals for AI-Driven Sensing

P105: Leveraging Satellite Measurements to Build Machine Learning Models for Estimating 20 years of High-Resolution Gridded Daily PM2.5 for Ghana