[NeurIPS 2025] Source code of "STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data"
Malware classification framework leveraging dynamic API-call sequences. Explores multiple Deep Learning architectures including Frequency-based FFNNs, Recurrent Neural Networks (GRU, BiLSTM) for sequential analysis, and Graph Neural Networks (GraphSAGE, GCN) for structural behavioral modeling. Focuses on feature extraction and sequence embedding.
A viewer whose perception evolves with each image—stateful, memory-carrying VLM reflections across a gallery.
Project Page of [NeurIPS-2025] "STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data"
Sequential forecasting pipeline leveraging Gated Recurrent Units (GRU) to model long-term dependencies in ad performance data. A deep learning baseline comparing RNN architectures against TCNs for temporal dynamics.
Add a description, image, and links to the sequential-modeling topic page so that developers can more easily learn about it.
To associate your repository with the sequential-modeling topic, visit your repo's landing page and select "manage topics."