Cover Image

Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shaj, Vaisakh, Barker, Cameron, Scannell, Aidan, Szecsenyi, Andras, Crowley, Elliot J., Storkey, Amos
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspective
by: Shaj, Vaisakh
Published: (2024)

Approximate Bayesian Class-Conditional Models under Continuous Representation Shift
by: Lee, Thomas L., et al.
Published: (2023)

Hyperparameter Selection in Continual Learning
by: Lee, Thomas L., et al.
Published: (2024)

Forgetting is Everywhere
by: Sanati, Ben, et al.
Published: (2025)

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity
by: Gospodinov, Emiliyan, et al.
Published: (2024)

Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report
by: Mereu, Riccardo, et al.
Published: (2025)

Label Noise: Correcting the Forward-Correction
by: Toner, William, et al.
Published: (2023)

Noisy Early Stopping for Noisy Labels
by: Toner, William, et al.
Published: (2024)

Chunking: Continual Learning is not just about Distribution Shift
by: Lee, Thomas L., et al.
Published: (2023)

Adversarial robustness of VAEs through the lens of local geometry
by: Khan, Asif, et al.
Published: (2022)

Rationality Measurement and Theory for Reinforcement Learning Agents
by: Qian, Kejiang, et al.
Published: (2026)

Efficient Offline Reinforcement Learning: First Imitate, then Improve
by: Jelley, Adam, et al.
Published: (2024)

Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning
by: Nakhaei, Mohammadreza, et al.
Published: (2024)

Adapting Time Series Foundation Models through Data Mixtures
by: Lee, Thomas L., et al.
Published: (2026)

Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning
by: Nakhaei, Mohammadreza, et al.
Published: (2024)

Contextual Latent World Models for Offline Meta Reinforcement Learning
by: Nakheai, Mohammadreza, et al.
Published: (2026)

Aligning Agents like Large Language Models
by: Jelley, Adam, et al.
Published: (2024)

DAM: Towards A Foundation Model for Time Series Forecasting
by: Darlow, Luke, et al.
Published: (2024)

einspace: Searching for Neural Architectures from Fundamental Operations
by: Ericsson, Linus, et al.
Published: (2024)

Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning
by: Zhang, Weipu, et al.
Published: (2025)

Attention-Based Neural-Augmented Kalman Filter for Legged Robot State Estimation
by: Lee, Seokju, et al.
Published: (2026)

[Re] The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Non-Gaussian Observation Models
by: Casco-Rodriguez, Josue, et al.
Published: (2024)

Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering
by: Gupta, Akash, et al.
Published: (2025)

Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning
by: McInroe, Trevor, et al.
Published: (2023)

Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering
by: Abdi, Hossein, et al.
Published: (2025)

Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filter
by: Lu, Tianlu, et al.
Published: (2026)

Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise
by: Long, Bo, et al.
Published: (2026)

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning
by: Wang, Hu, et al.
Published: (2025)

Linear Attention Sequence Parallelism
by: Sun, Weigao, et al.
Published: (2024)

Neural Aided Kalman Filtering for UAV State Estimation in Degraded Sensing Environments
by: Gupta, Akhil, et al.
Published: (2026)

Recursive KalmanNet: Deep Learning-Augmented Kalman Filtering for State Estimation with Consistent Uncertainty Quantification
by: Mortada, Hassan, et al.
Published: (2025)

Discrete Codebook World Models for Continuous Control
by: Scannell, Aidan, et al.
Published: (2025)

iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
by: Scannell, Aidan, et al.
Published: (2024)

Function-space Parameterization of Neural Networks for Sequential Learning
by: Scannell, Aidan, et al.
Published: (2024)

TrackDiffuser: Nearly Model-Free Bayesian Filtering with Diffusion Model
by: He, Yangguang, et al.
Published: (2025)

Probing Dec-POMDP Reasoning in Cooperative MARL
by: Tessera, Kale-ab, et al.
Published: (2026)

Few-Shot Learning with Class Imbalance
by: Ochal, Mateusz, et al.
Published: (2021)

Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data
by: Zhao, Yi, et al.
Published: (2025)

Kalman Bayesian Transformer
by: Jing, Haoming, et al.
Published: (2025)

On Harnessing Idle Compute at the Edge for Foundation Model Training
by: Xue, Leyang, et al.
Published: (2025)