sequence modeling
A type of modeling focused on data that is ordered or sequential in nature, such as time series or natural language. Techniques like Recurrent Neural Networks (RNNs) and Transformers are commonly used for this purpose.
- Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning
- Generalization Error Analysis for Selective State-Space Models Through the Lens of Attention
- Less is More: an Attention-free Sequence Prediction Modeling for Offline Embodied Learning
- Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection
- Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
- Sequence Modeling with Spectral Mean Flows
- Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
- Tensor Product Attention Is All You Need
- Vector Quantization in the Brain: Grid-like Codes in World Models
- ZeroS: Zero‑Sum Linear Attention for Efficient Transformers
- vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models