MolSC: Leveraging Substituent Contributions to Enhance Fine-grained Molecular Understanding in LLMs
We propose MolSC, a method that leverages substituent contributions to enhance fine-grained molecular understanding in large language models.
Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment
We propose a substructure-aware alignment approach to bridge the gap between molecular and textual representations.
Zero-shot Commonsense Reasoning over Machine Imagination
We explore zero-shot commonsense reasoning by leveraging machine-generated visual imagination to supplement text-based reasoning.
MolTRES: Improving Chemical Language Representation Learning for Molecular Property Prediction
MolTRES improves chemical language representation learning for more accurate molecular property prediction.
jun-hyung-park
Moleco: Molecular Contrastive Learning with Chemical Language Models for Molecular Property Prediction
We propose Moleco, a molecular contrastive learning framework using chemical language models for molecular property prediction.
jun-hyung-park
DIVE: Towards Descriptive and Diverse Visual Commonsense Reasoning
DIVE is a framework that promotes descriptive and diverse visual commonsense reasoning beyond surface-level visual cues.
jun-hyung-park
Perceptual-IQ: Visual Commonsense Reasoning about Perceptual Imagination
We introduce Perceptual-IQ, a benchmark for visual commonsense reasoning that evaluates models on perceptual imagination.
hyogyun-an
KOAS: Korean Text Offensiveness Analysis System
KOAS is a Korean text offensiveness analysis system that detects and classifies offensive language in Korean text.
san-hee-park