deep learning models
Deep learning models are a subset of machine learning that utilize neural networks with multiple layers (depth) to learn from data representations, particularly effective in dealing with large and complex datasets such as images and text.
- A Learning-Augmented Dynamic Programming Approach for Orienteering Problem with Time Windows
- Adaptive Time Encoding for Irregular Multivariate Time-Series Classification
- BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
- Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning
- CheMixHub: Datasets and Benchmarks for Chemical Mixture Property Prediction
- On Linear Mode Connectivity of Mixture-of-Experts Architectures
- On Linear Mode Connectivity of Mixture-of-Experts Architectures
- Point Cloud Synthesis Using Inner Product Transforms
- RGB-to-Polarization Estimation: A New Task and Benchmark Study
- Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
- STACI: Spatio-Temporal Aleatoric Conformal Inference
- SmokeViz: A Large-Scale Satellite Dataset for Wildfire Smoke Detection and Segmentation
- TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents