Talks & Presentations

Agentic AI in Industry: Context, Autonomy, and What Works

Guest Lecture, Fusemachines AI Fellowship 2026

Online · Kathmandu, Nepal

A practical look at how AI agents are used in industry: the agent landscape, context engineering, autonomy and human oversight, and what actually works in production, for AI fellows in Nepal.

Multimodal Search in Chemical Documents and Reactions

48th International ACM SIGIR Conference (SIGIR 2025), Demo & Poster Session

Padua, Italy

Demo of ReactionMiner, which searches reaction descriptions in PDF documents using text and chemical structures (SMILES/SMARTS). Presented in person by co-author Patrick Philippy.

Parsing of Math Formulas and Chemical Diagrams using Graph-Based Representation and Attention Models

Ph.D. Dissertation Defense, Rochester Institute of Technology

Rochester, NY

ChemScraper: Pipeline for Parsing Raster and Vector Molecule Diagrams from PDFs

MMLI Research Symposium 2025, “AI Scientists? What Would It Take?!”

NCSA, University of Illinois Urbana-Champaign

ChemScraper: Step-by-Step Video Tutorial

AlphaSynthesis tools, Molecule Maker Lab Institute (prepared for the NSF site visit)

YouTube

Reaction Extraction from PDF: ChemScraper and ReactionMiner Integration

Molecule Maker's Playhouse (inaugural MMLI all-institute meeting), Thrust 1: AI-Enabled Synthesis Planning

Champaign, IL

Parsing of Math Formulas and Chemical Diagrams using Graph-Based Representation and Attention Models

Ph.D. Dissertation Proposal Defense, Rochester Institute of Technology

Rochester, NY

ChemScraper: Leveraging PDF Graphics Instructions for Molecular Diagram Parsing

18th International Conference on Document Analysis and Recognition (ICDAR 2024), Oral Presentation

Athens, Greece

Intro to AI: Exploring Fundamentals, Research, and Career Opportunities

AI Webinar, PANA Academy

Online · Kathmandu, Nepal

An introduction to AI, machine learning, NLP and computer vision, how AI research works, and career paths in AI.

ChemScraper: Extracting and Parsing Molecular Diagrams from PDFs and Images

MMLI NSF Site Visit, Poster Session

University of Illinois Urbana-Champaign

Integration of ReactionMiner and ChemScraper: Mining Chemical Reactions from Literature

MMLI All-Institute Meeting, Cross-Thrust Talk (Thrust 1 & Thrust 4)

University of Illinois Urbana-Champaign (hybrid)

ChemScraper: Extracting Molecule Diagrams from PDF Vector Images and Raster Images with CDXML (ChemDraw) and SMILES Output

MMLI All-Institute Retreat 2023

University of Illinois Urbana-Champaign

Line-of-Sight with Graph Attention and Task Interaction (LGATI) for Math Formulas

17th International Conference on Document Analysis and Recognition (ICDAR 2023), Poster Session & Doctoral Consortium

San José, CA

ChemScraper: Extracting Molecule Diagrams from PDF Vector Images with Page-Level CDXML (ChemDraw) and SMILES Output

NSF Annual Review Meeting, Molecule Maker Lab Institute

University of Illinois Urbana-Champaign

Line-of-Sight with Graph Attention Parser (LGAP) for Math Formulas

Research Idea Ring (RIR), Department of Computer Science, RIT

Rochester, NY

Reconstructing the Structure of Molecular Diagrams in PDF Documents using a CNN-Attention-Based Parsing Model

MMLI All-Institute Retreat 2022

University of Illinois Urbana-Champaign

Bayesian Decision Theory

Guest Lecture, Introduction to Machine Learning (undergraduate, ~40 students), RIT

Rochester, NY

A Fast and Interpretable Context-aware Parser for Isolated Formulas and Chemical Diagrams

Research Idea Ring (RIR), Department of Computer Science, RIT

Rochester, NY

A Math Formula Extraction and Evaluation Framework for PDF Documents

16th International Conference on Document Analysis and Recognition (ICDAR 2021)

Lausanne, Switzerland (virtual)

Mathematical Formula Recognition

Ph.D. Research Potential Assessment (RPA), Rochester Institute of Technology

Rochester, NY