Top Tweets for #StateSpaceModels
6/ Building models is engineering; debugging their learning dynamics is research. Check out the diagnostic framework, code, and convergence metrics on GitHub: https://t.co/yuYlObeB2b
🚀 #MachineLearning #AIResearch #StateSpaceModels #Mamba #DeepLearning
SSA-Mamba just solved this with a Dual-Branch State Space Model that uses Asymmetric Attention.
Full breakdown + PyTorch code: 🔗 https://t.co/0FMFvRO4gS
#SSAMamba #HSI #RemoteSensing #StateSpaceModels #MachineLearning #AITrendBlend
LiDAR detectors just got a major upgrade! 🚗💨
Enter GateMamba: a new backbone that fixes this with three architectural "gates."
Read the full breakdown + PyTorch code: 🔗 https://t.co/8kqdz3iIWe
#StateSpaceModels #MachineLearning #ComputerVision #AutonomousVehicles
On the Expressive Power and Limitations of Multi-Layer SSMs
👥 Nikola Zubić, Qian Li, Yuyi Wang & Davide Scaramuzza
#AIResearch #MachineLearning #StateSpaceModels #DeepLearning
🔗 https://t.co/qTqdLlMpdW

https://t.co/XQttJpiN2R
New Mamba-3 AI Model Beats Transformers by 4%, Runs 7x Faster
#AI #AIModels #AIResearch #DeepLearning #MachineLearning #OpenSourceAI #AIInference #AIBenchmarks #Mamba3 #TogetherAI #StateSpaceModels

Finite Sample Analysis of System Poles for Ho-Kalman Algorithm
#HoKalman #SystemIdentification #FiniteSampleAnalysis #ControlTheory #StateSpaceModels
International Robotics and Automation Awards
Visit Us: https://t.co/tsUXfhL8k8
Nomination:https://t.co/SHfgLi28AO
Single molecule localization microscopy challenge: a biologically inspired benchmark for long-sequence modeling
Preprint: This work introduces the SMLM-C benc…
https://t.co/nE6Plg0c2G #AI #BiologicalImaging #StateSpaceModels #MachineLearning #Preprint #Arxiv #ScienceNews
#mdpisystems Call for reading:
Data-Driven Strategies for #ComplexSystem Forecasts: The Role of Textual Big Data and State-Space Transformers in Decision Support
👉https://t.co/Um4CVe16lJ
from China Agricultural University and @RUCerofChina
#systems #statespacemodels

Mamba : la nouvelle architecture d’IA qui pourrait remplacer les Transformers et les modèles GPT
https://t.co/7nd3JXQp3z
#deepLearning #developpement #science #recherche #arxiv #mamba #architecture #transformers #albertGu #triDao #llm #performance #stateSpaceModels #gpu
📢 Highly Cited in #Forecasting!
📖 Bootstrapping State-Space Models: Distribution-Free Estimation in View of Prediction and Forecasting
✍️ José Francisco Lima et. al.
🔗 https://t.co/F5vgPQe56I
#StateSpaceModels #Bootstrapping #Prediction #TimeSeriesAnalysis

If you do state‑space models in JAX, check it out and say hi!
Docs: https://t.co/CEwiChv6d2
PyPI: https://t.co/Ek0x7zZX2F
#JAX #StateSpaceModels
Full write-up in the blog post.
https://t.co/jQcaechYvj
#EdgeAI #OnDeviceAI #VoiceAI #TimeSeriesAI #Semiconductors #StateSpaceModels #Robotics #Wearables #AR #HealthTech #Automotive #VentureCapital
📘 Must Read in #Forecasting!
📖 Bootstrapping State-Space Models: Distribution-Free Estimation in View of Prediction and Forecasting
🔗 Read the full article: https://t.co/FFlXqN9SSu
#StateSpaceModels #Bootstrapping #TimeSeries

📢 Research Seminar – Tue 28 Oct
🕛 12–13:30📍Auditorium
🎤 Gianni Amisano (FED)
📝 "How to catch a star? Reliability of filtering estimates in linear state space systems" (with Drautzburg & Stella)
#reliability #latentvariable #macroeconomic #stateSpaceModels
📘Open Access Article Published in MDPI Forecasting
"Bootstrapping State-Space Models: Distribution-Free Estimation in View of Prediction and Forecasting"
🔗 Read the full article here: https://t.co/8v6yIxB83z
#OpenAccess #MDPIForecasting #Statistics #StateSpaceModels

"Meet #Mamba, the newest AI model on the block. Outshining Transformer models, it efficiently processes long sequences like a pro! 🐍🧠💻 #AI #MachineLearning #StateSpaceModels"
I wrote a blog on how to set up Mamab SSM on Kaggle
#MambaSSM #Kaggle #StructuredStateSpace #MachineLearning #DeepLearning #AIResearch #GPUComputing #StateSpaceModels #OpenSourceAI #TransformerAlternatives
https://t.co/DTIeI1Vio8
Tired of #AI search hallucinations?
The root cause often lies in the architecture behind most AI models: the #Transformer.
This #InfoQ article explains how #StateSpaceModels (#SSMs) can fix this, & what it could mean for the future of AI search: https://t.co/pOlYSRxJ4j
#LLMs

Tired of #AI search hallucinations?
The root cause often lies in the architecture behind most AI models: the #Transformer.
This #InfoQ article explains how #StateSpaceModels (#SSMs) can fix this, & what it could mean for the future of AI search: https://t.co/pOlYSRxJ4j
#LLMs

Excited to share our #CVPR2025 paper, "GG-SSMs: Graph-Generating State Space Models", to be presented as a Highlight Paper in Nashville this week!
PDF: https://t.co/sBJMOpNr64
Code: https://t.co/iE4WhNGGrG
While #StateSpaceModels (#SSMs) are extremely powerful for sequential data, the one-dimensional processing paradigm severely limits their ability to model non-local interactions in high-dimensional data. Even advanced models like #Mamba, #Vim, and #VMamba, though offering selective scanning, remain constrained by predetermined paths, often failing to efficiently capture the high-dimensional interactions of data dependencies.
Our new Graph-Generating State Space Models (GG-SSMs) directly address this limitation. We introduce a novel framework that dynamically constructs graphs based on inherent feature relationships, adapting to the unique structure of the data itself! By leveraging Chazelle's Minimum Spanning Tree (MST) algorithm, known for its near-linear time complexity, GG-SSMs enable robust feature propagation and efficiently model complex, long-range dependencies without prohibitive computational costs.
Our contributions are as follows:
* Integration of dynamic graph structures directly into the SSM framework, capturing complex spatial and temporal relationships.
* SOTA results across 11 diverse datasets, including ImageNet, optical flow, event-based eye tracking, and time series!
- ImageNet: Sets a new benchmark with 84.9% top-1 accuracy, outperforming prior SSMs by 1%.
- KITTI-15 Optical Flow: Achieves the lowest error rate ever reported at 2.77%.
- Eye Tracking: Improves detection rates by up to 0.33% with fewer parameters on event-based datasets.
- Time Series: Demonstrates superior forecasting accuracy across six real-world datasets.
* MST-based construction ensures linear computational complexity, making GG-SSMs highly scalable and efficient for large-scale applications.
Kudos to @NikolaZubic5 !
Reference:
Nikola Zubić and Davide Scaramuzza,
GG-SSMs: Graph-Generating State Space Models,
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2025.,
PDF: https://t.co/sBJMOpNr64
Code: https://t.co/iE4WhNGGrG
Highlight Presentation.
@ERC_Research @uzh_ifi @UZH_en @UZH_Science
#GraphNeuralNetworks #ComputerVision #MachineLearning #AIResearch #DeepLearning #OpticalFlow #TimeSeries

Last Seen Hashtags on Sotwe
HOTWIFE
Seen from Netherlands
タイガーウルフ
Seen from United States
prototype1006
Seen from United States
momson() + filter:native_video
Seen from United States
ソングオブバラード
Seen from Russia
สาวพยาบาลใสๆวัย41นะจ๊ะ
Seen from United Kingdom
supportUSpressing
Seen from Spain
朝海凪咲
Seen from Netherlands
spanking punishment
Seen from Turkey
freeazovstaldefenders
Seen from Chile
Most Popular Users

Elon Musk 
@elonmusk
240.1M followers

Barack Obama 
@barackobama
119.3M followers

Donald J. Trump 
@realdonaldtrump
111.6M followers

Cristiano Ronaldo 
@cristiano
108.7M followers

Narendra Modi 
@narendramodi
106.9M followers

Rihanna 
@rihanna
97.2M followers

NASA 
@nasa
92.1M followers

Justin Bieber 
@justinbieber
90.5M followers

KATY PERRY 
@katyperry
86.7M followers

Taylor Swift 
@taylorswift13
80.5M followers

Lady Gaga 
@ladygaga
72.1M followers

Kim Kardashian 
@kimkardashian
69.3M followers

YouTube 
@youtube
68.6M followers

Virat Kohli 
@imvkohli
68.4M followers

Bill Gates 
@billgates
63.3M followers

The Ellen Show
@theellenshow
62.5M followers

CNN 
@cnn
61.9M followers

Neymar Jr 
@neymarjr
60.9M followers

X 
@x
60.9M followers

CNN Breaking News 
@cnnbrk
59.9M followers















