Image de couverture de livre

Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hwang, Sukjun, Lahoti, Aakash, Dao, Tri, Gu, Albert
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Chimera: State Space Models Beyond Sequences
par: Lahoti, Aakash, et autres
Publié: (2025)

Mamba: Linear-Time Sequence Modeling with Selective State Spaces
par: Gu, Albert, et autres
Publié: (2023)

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
par: Dao, Tri, et autres
Publié: (2024)

Mamba-3: Improved Sequence Modeling using State Space Principles
par: Lahoti, Aakash, et autres
Publié: (2026)

M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
par: Mishra, Mayank, et autres
Publié: (2026)

Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
par: Hwang, Sukjun, et autres
Publié: (2025)

Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
par: Lahoti, Aakash, et autres
Publié: (2024)

Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
par: Chang, Jinho, et autres
Publié: (2022)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models
par: Do, Nguyen, et autres
Publié: (2025)

The Mamba in the Llama: Distilling and Accelerating Hybrid Models
par: Wang, Junxiong, et autres
Publié: (2024)

MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection
par: Behrouz, Ali, et autres
Publié: (2024)

EchoMamba4Rec: Harmonizing Bidirectional State Space Models with Spectral Filtering for Advanced Sequential Recommendation
par: Wang, Yuda, et autres
Publié: (2024)

Scale-Consistent State-Space Dynamics via Fractal of Stationary Transformations
par: Yu, Geunhyeok, et autres
Publié: (2026)

LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
par: Li, Wenbing, et autres
Publié: (2025)

SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
par: Guo, Wentao, et autres
Publié: (2025)

Distribution Matching via Generalized Consistency Models
par: Shrestha, Sagar, et autres
Publié: (2025)

TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis
par: Wang, Shiyu, et autres
Publié: (2024)

Free Energy Mixer
par: Lu, Jiecheng, et autres
Publié: (2026)

Hydra: A Modular Architecture for Efficient Long-Context Reasoning
par: Chaudhary, Siddharth, et autres
Publié: (2025)

TSKANMixer: Kolmogorov-Arnold Networks with MLP-Mixer Model for Time Series Forecasting
par: Hong, Young-Chae, et autres
Publié: (2025)

FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
par: Shah, Jay, et autres
Publié: (2024)

SDMixer: Sparse Dual-Mixer for Time Series Forecasting
par: Ao, Xiang
Publié: (2026)

Supervised Contrastive Learning based Dual-Mixer Model for Remaining Useful Life Prediction
par: Fu, En, et autres
Publié: (2024)

MELCOT: A Hybrid Learning Architecture with Marginal Preservation for Matrix-Valued Regression
par: Tran, Khang, et autres
Publié: (2025)

TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
par: Wang, Shiyu, et autres
Publié: (2024)

Inducing Group Fairness in Prompt-Based Language Model Decisions
par: Atwood, James, et autres
Publié: (2024)

FFNet: MetaMixer-based Efficient Convolutional Mixer Design
par: Yun, Seokju, et autres
Publié: (2024)

A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis
par: Zhong, Shuhan, et autres
Publié: (2023)

Challenges in Mechanistically Interpreting Model Representations
par: Golechha, Satvik, et autres
Publié: (2024)

Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models
par: Badger, Benjamin L., et autres
Publié: (2026)

DPWMixer: Dual-Path Wavelet Mixer for Long-Term Time Series Forecasting
par: Qianyang, Li, et autres
Publié: (2025)

HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model
par: Ma, Mingqian, et autres
Publié: (2025)

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism
par: Bick, Aviv, et autres
Publié: (2025)

Linear Attention for Efficient Bidirectional Sequence Modeling
par: Afzal, Arshia, et autres
Publié: (2025)

The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models
par: Flamant, Cedric, et autres
Publié: (2026)

Time Series Clustering with General State Space Models via Stochastic Variational Inference
par: Ishizuka, Ryoichi, et autres
Publié: (2024)

JustDense: Just using Dense instead of Sequence Mixer for Time Series analysis
par: Park, TaekHyun, et autres
Publié: (2025)

Detecting Jailbreak Attempts in Clinical Training LLMs Through Automated Linguistic Feature Extraction
par: Nguyen, Tri, et autres
Publié: (2026)

State Space Models over Directed Graphs
par: She, Junzhi, et autres
Publié: (2025)

Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
par: Ekambaram, Vijay, et autres
Publié: (2024)