List of accepted papers

Oral presentations

Deep Vision-Based Framework for Coastal Flood Prediction Under Climate Change Impacts and Shoreline Adaptations

TDiMS : A Topological Distance based Intra-Molecular Substructure Descriptor for Improved Machine Learning Predictions

Enhancing Ligand Validity and Affinity in Structure-Based Drug Design with Multi-Reward Optimization

Convolutional Deep Operator Networks for Learning Nonlinear Focused Ultrasound Wave Propagation in Heterogeneous Spinal Cord Anatomy

Llama-3-Meditron: An Open-Source Suite of Medical LLMs Based on Llama-3.1

BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity

Poster presentations

Some of our presenters couldn’t attend the workshop in person. They kindly sent us a video or poster presentation of their work. Please find them listed with Video Link or Poster Link in front of the corresponding paper below.

Application of Neural Ordinary Differential Equations for ITER Burning Plasma Dynamics

Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching

Improving Fine-grained Visual Understanding in VLMs through Text-Only Training

Constructing sensible baselines for Integrated Gradients | Video Link

An Agentic Approach to Automatic Creation of P&ID Diagrams from Natural Language Descriptions | Video Link

SmokeNet: Efficient Smoke Segmentation Leveraging Multiscale Convolutions and Multiview Attention Mechanisms

TireDiff: A Diffusion-based Tire Footprint Image Generation Framework for High-fidelity Prototyping | Video Link

Open source Differentiable ODE Solving Infrastructure

Open-source Polymer Generative Pipeline

Open-Source Protein Language Models for Function Prediction and Protein Design

Accelerating Manufacturing Prototyping: A Continual Learning Approach for Imbalanced Sequential Image Generation | Video Link

NeuroSteiner: A Graph Transformer for Wirelength Estimation

Uncertainty separation via ensemble quantile regression Video Link

CircleSeg-XAI Segmentation-Based Target Point Detection Method Using Circular Shape Label

The BACON system for equation discovery from scientific data: Reconciling classical artificial intelligence with modern machine learning approaches

Enhancing AI Capabilities on the Abstraction and Reasoning Corpus: A Path Toward Broad Generalization in Intelligence

Are Large Language Models the Best Estimators of Chemical Reaction Yields?

4S-Classifier: Empowering Conservation through Semi-Supervised Learning for Rare and Endangered Species

Few-shot Metric Domain Adaptation: Practical Learning Strategies for an Automated Plant Disease Diagnosis

ContinuouSP: Generative Model for Crystal Structure Prediction with Invariance and Continuity

LLM-Fusion: A Novel Multimodal Fusion Model for Accelerated Material Discovery

Crystal Structure Generation Using a Diffusion Model Conditioned on X-Ray Diffraction Intensities Without Label Learning

Projective Operator-based Explanations for Multi-Output Prediction Models in Semiconductor Industry

Advancing Distribution System Restoration via an Innovative Physics-Informed Decision Transformer

A Metric for the Balance of Information in Graph Learning

M-MOFormer: Multi-Modal Transformer Framework for Metal-Organic Framework Property Prediction

The influence of Initial Connectivity on Biologically Plausible Learning

DDD: Discriminative Difficulty Distance for plant disease diagnosis

CRISP-DM 2.0 for the Semiconductor Industry and Other Complex Domains

A Deep Learning-Based Tool for Detection and Counting of Chloroplasts in Single-Cell Images

Lattice Protein Folding with Variational Annealing

An Uncertainty-Aware Data-Driven Predictive Controller for Hybrid Power Plants

Novel Interpretable Amino Acid Property-Based Peptide Embeddings for Improved Activity Prediction

Simulating Tabular Datasets through LLMs to Rapidly Explore Hypotheses about Real-World Entities

Uncertainty Analysis in Predicting Molecular Properties Using Chemical Foundation Models

Bridging Particle Physics and AI with the ATHANOR Pipeline

On the Effectiveness of Neural Operators at Zero-Shot Weather Downscaling

Diffeomorphic Latent Neural Operators for Data-Efficient Learning of Solutions to Partial Differential Equations

Effective Defect Detection Using Instance Segmentation for NDI

Uncertainty Quantification Using Graph-based Conformal Prediction for Mesh-based Simulation

Learning coupled Allen-Cahn and Cahn-Hilliard phase-field equations using Physics-informed neural operator(PINO)

Forecasting Fails: Unveiling Evasion Attacks in Weather Prediction Models

Deep Reinforcement Learning for De novo Synthesis of Eye Drops

InceptionSR: Recursive Symbolic Regression for Equation Synthesis

RL-MILP Solver: A Reinforcement Learning Approach for Solving Mixed-Integer Linear Programs with Graph Neural Networks

Everyone attending #AAAI25 is invited for our 4th AAAI @RealAAAI workshop on AI to Accelerate Science and Engineering on Monday, March 3rd. The workshop location is Room 121B. We have an exciting schedule thanks to all the authors presenting their work and our invited speakers.

I will present our paper “Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning”, led in the main conference poster session track 3 during 12:30 PM to 2:15 PM on Saturday, March 1st. Location or Poster Session 3: Exhibit Hall E.

I will also give a talk at AAI New Faculty Highlights program on “Adaptive Experimental Design to Accelerate Scientific Discovery and Engineering Design” in Room 121 B at 9:30 AM on Saturday, March 1st.