state space model

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors ICLR 2024 On Feature Learning in Structured State Space Models NeurIPS 2024 Online Variational Sequential Monte Carlo ICML 2024 Outlier-robust Kalman Filtering through Generalised Bayes ICML 2024 Parallelizing Linear Transformers with the Delta Rule over Sequence Length NeurIPS 2024 Physics-Informed Variational State-Space Gaussian Processes NeurIPS 2024 PIDformer: Transformer Meets Control Theory ICML 2024 PointMamba: A Simple State Space Model for Point Cloud Analysis NeurIPS 2024 Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics NeurIPS 2024 Probabilistic Time Series Modeling with Decomposable Denoising Diffusion Model ICML 2024 Protein-Nucleic Acid Complex Modeling with Frame Averaging Transformer NeurIPS 2024 Provable Benefits of Complex Parameterizations for Structured State Space Models NeurIPS 2024 QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model NeurIPS 2024 Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM EMNLP 2024 RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection Interspeech 2024 Recurrent Distance Filtering for Graph Representation Learning ICML 2024 Recurrent neural networks: vanishing and exploding gradients are not the end of the story NeurIPS 2024 Repeat After Me: Transformers are Better than State Space Models at Copying ICML 2024 Rethinking Token Reduction for State Space Models EMNLP 2024 RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation NeurIPS 2024 Robustifying State-space Models for Long Sequences via Approximate Diagonalization ICLR 2024 Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts NeurIPS 2024 Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading NeurIPS 2024 Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling EMNLP 2024 Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences ICML 2024