Topology-driven pre-training for robust molecular property prediction modelsAldo Guzmán-SáenzSanjoy Deyet al.2023ACS Fall 2023
Seeing the unseen: leveraging vision models to extract digital fingerprints of complex liquidsGianmarco GabrieliMatteo Manicaet al.2023ACS Fall 2023
TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series ForecastingVijay EkambaramArindam Jatiet al.2023KDD 2023
Hierarchical Proxy Modeling for Improved HPO in Time Series ForecastingArindam JatiVijay Ekambaramet al.2023KDD 2023
The Information Pathways Hypothesis: Transformers are Dynamic Self-EnsemblesMd Shamim HussainMohammed J. Zakiet al.2023KDD 2023
Integrating Chemical Language and Physicochemical Features for Enhanced Molecular Property Prediction with Multimodal Language ModelsEduardo Almeida SoaresEmilio Ashton Vital Brazilet al.2023KDD 2023
Scope 3 emission estimation using large language modelsAyush JainManikandan Padmanabanet al.2023KDD 2023
Challenges in post-training quantization of Vision TransformersPiotr Sebastian KluskaFlorian Scheideggeret al.2023KDD 2023
Foundations and Applications in Large-scale AI Models: Pre-training, Fine-tuning, and Prompt-based LearningDerek ChengDhaval Patelet al.2023KDD 2023
MaxCorrMGNN: A Multi-Graph Neural Framework for Generalized Multimodal Fusion of Medical Data for Outcome PredictionNiharika DSouzaHongzhi Wanget al.2023ICML 2023