No article text was recorded for this version.
hybrid state-space attention architecture
Version 2 of 2206 papers265 conceptsfrozen 2026-10-04
Papers in this version
- Blog: How Effective are State Space Models for Machine Translation?
- Blog: MambAttention: Mamba With Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
- Blog: MLSA4Rec: Mamba Combined with Low-Rank Decomposed Self-Attention for Sequential Recommendation
- Blog: TextMamba: Scene Text Detector with Mamba
- Blog: TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
- Blog: Zamba: A Compact 7B SSM Hybrid Model
- Blog: Multiscale Byte Language Models - A Hierarchical Architecture for Causal Million-Length Sequence Modeling
- Blog: Taipan: Efficient and Expressive State Space Language Models with Selective Attention
- Blog: Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- Blog: HyMaTE: A Hybrid Mamba and Transformer Model for EHR Representation Learning
- Blog: VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining
- Blog: TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
- Blog: LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture
- Blog: A Survey on Small Language Models
- Blog: Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis
- Blog: Distillation-free Scaling of Large SSMs for Images and Videos
- Blog: Hungry Hungry Hippos: Towards Language Modeling with State Space Models
- Blog: Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks
- Blog: The Zamba2 Suite: Technical Report
- Blog: MambaVision: A Hybrid Mamba-Transformer Vision Backbone
- Blog: Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling
- Blog: A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness
- Blog: LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory
- Blog: Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging
- Blog: Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention
- Blog: State Spaces Aren't Enough: Machine Translation Needs Attention
- Blog: Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling
- Blog: State-Space Model Meets Linear Attention: A Hybrid Architecture for Internal Wave Segmentation
- Blog: Hungry Hungry Hippos: Towards Language Modeling with State Space Models
- Blog: MSAmba: Exploring Multimodal Sentiment Analysis with State Space Models
- Blog: Application of Structured State Space Models to High energy physics with locality sensitive hashing
- Blog: Harnessing Temporal Causality for Advanced Temporal Action Detection
- Blog: Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
- Blog: QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
- Blog: Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
- Blog: STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation
- Blog: A deep reinforcement learning approach for solving the Traveling Salesman Problem with Drone
- Blog: Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
- Blog: Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
- Blog: GeneGench: Systematic Evaluation of Genomic Foundation Models and Beyond
- Blog: Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models
- Blog: TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable Platforms
- Blog: HydraRNA: a hybrid architecture based full-length RNA language model
- Blog: Efficient Hybrid Long Sequence Modeling with State Space Augmented Transformers
- Blog: Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance
- Blog: Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling
- Blog: Interdomain Attention: Beyond Token-Level Key-Value Memory
- Blog: Test-Time Adaptation on Recommender System with Data-Centric Graph Transformation
- Blog: MambaGesture: Enhancing Co-Speech Gesture Generation with Mamba and Disentangled Multi-Modality Fusion
- Blog: LFTramba: Comprehensive Information Learning for Light Field Image Super-Resolution via A Hybrid Transformer-Mamba Framework
- Blog: Jamba: Hybrid Transformer-Mamba Language Models
- Blog: Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancement
- Blog: Hybrid Mamba-Transformer Decoder for Error-Correcting Codes
- Blog: IsoPLM: Isolating the Impacts of Architecture on Protein Language Models
- Blog: Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation
- Blog: Long-Form Speech Generation with Spoken Language Models
- Blog: Zamba: A Compact 7B SSM Hybrid Model
- Blog: MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling
- Blog: Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
- Blog: GMSR:Gradient-Guided Mamba for Spectral Reconstruction from RGB Images
Showing 60 of 206 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_hybrid_state_space_attention_architectur_fb91ad75,
title = {hybrid state-space attention architecture},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hybrid-state-space-attention-architecture/rdr_fb91ad75ffe74f58b744b4453de534d8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_hybrid_state_space_attention_architectur_fb91ad75_v2,
title = {hybrid state-space attention architecture},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hybrid-state-space-attention-architecture/rdr_fb91ad75ffe74f58b744b4453de534d8/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}