SpecKCast forecasts diffusion features in the frequency domain
A training-free Kalman filter on DCT coefficients skips transformer steps, with up to 6x speedup and under 0.05 GiB extra memory.
Stories per day · 30 days
2 RSS
Relatedcomputer-vision1diffusion1feature-caching1inference-acceleration1multi-object-tracking1sort1sports1video-generation1
9 stories, newest first · one card per story
Stories tagged #kalman-filter
ARC-SORT reports 81.82 HOTA on SportsMOT test tracking
The tracker trains nothing, runs about 50 frames per second on a laptop RTX 3060, and its code is not yet released.
Online Learning via Learned Latent Bayesian Tracking
AURA learns a latent state space so deep models adapt online via Kalman filtering under distribution shift.
Statistical Foundations for a Google Play User-Review Sentiment Index: Signal Fusion, Shrinkage, Distributional Validation, and Dynamic Smoothing
Researchers define a Google Play review sentiment index using signal fusion, shrinkage, and Kalman smoothing.
Repairability of Inexact Solvers in Recursive State Estimation with Machine Learning
A certified repair framework evaluates inexact and quantum linear solvers inside Kalman estimation, including a power-grid study.
Fast-varying Natural Frequencies and Damping Ratio Identification for Linear Time-Varying System
Physics-enhanced LSTM-EKF method identifies fast-varying natural frequencies and damping ratios in offshore wind turbines with 0.0012 Hz RMSE.
Tracking the Unseen: An Occlusion-Robust Framework for Target Tracking Under Full and Long-Term Occlusion
Occlusion-robust tracker combining YOLOv11n, Kalman filtering, and appearance Re-ID cuts identity switches and beats OccluTrack by 18.1% MOTA on OVIS.
Kalman Delta Networks: Uncertainty-aware Associative Memory
Kalman Delta Networks add uncertainty tracking to linear-attention associative memory, improving perplexity and downstream accuracy at 750M and 1.3B scales.
Kalman Delta Networks: Uncertainty-aware Associative Memory
Researchers propose Kalman Delta Networks, adding Kalman-filter uncertainty tracking to delta-rule linear attention, improving perplexity and accuracy at 750M and 1.3B parameters.