#StateSpaceModels
LightNews LightNews
ai-bloom.warp-studio.com
Weighted State Souping：クエリ適応型の状態合成で長文脈検索を効率化

キャッシュ状態をクエリに応じて重み付けし長文脈検索を効率化

#StateSpaceModels #長文脈検索 #状態合成 #情報検索
Weighted State Souping：クエリ適応型の状態合成で長文脈検索を効率化
キャッシュ状態をクエリに応じて重み付けし長文脈検索を効率化
ai.warp-studio.com
November 11, 2026 at 6:34 PM
ai-bloom.warp-studio.com
AWSで実現する100ms未満の音声AI：SSMとGPU基盤の設計・運用

SSMとAWS GPU基盤で音声AIの低遅延化を解説

#音声AI #StateSpaceModels #AWS #AmazonSageMaker #GPU推論
AWSで実現する100ms未満の音声AI：SSMとGPU基盤の設計・運用
SSMとAWS GPU基盤で音声AIの低遅延化を解説
ai.warp-studio.com
November 3, 2026 at 9:48 PM
futuregearai.bsky.social
A new incremental, operator-level pruning approach for S4 and S4D structured state space models cuts inference cost while preserving accuracy on resource-constrained devices. It's the first systematic study of structured…

#EdgeAI #ModelCompression #StateSpaceModels
https://arxiv.org/abs/2606.18096
October 9, 2026 at 8:01 PM
alex-andorra.bsky.social
New episode is out!
We covered some of the most practical and under-discussed tools in #Bayesian econometrics:
🔷 #DynamicRegression
🔷 #StateSpaceModels
🔷 Predictively consistent priors
🔷 Bayesian R²
🔷 Whether AI could help us elicit better priors
learnbayesstats.bsky.social Pierre-Simon Laplace @learnbayesstats.bsky.social · Jun 13
Some people think R² doesn’t belong in Bayesian models
👇 David Kohns disagrees, and he has the math to back it

🎙️Ep. 134: @alex-andorra.bsky.social sits down with economist David Kohns to explore how modern Bayesian methods are reshaping time series modelling

🎧 learnbayesstats.com/episode/134-...
June 13, 2025 at 4:23 PM
infoq.com
Tired of #AI search hallucinations?

The root cause often lies in the architecture behind most AI models: the #Transformer.

In this #InfoQ article, Albert Lie explains how #StateSpaceModels (#SSMs) can fix this, and what it could mean for the future of AI search.

Read now: bit.ly/4nojJrZ

#LLMs
June 27, 2025 at 9:57 AM
benjamincwalker.bsky.social
Huge thanks to my incredible co-authors Nicola Cirone, Antonio Orvieto, Cristopher Salvi, and Terry Lyons!

#NeurIPS2024 #MachineLearning #DeepLearning #StateSpaceModels

🧵6/6
November 23, 2024 at 9:04 AM
winbuzzer.com
winbuzzer.com/2026/03/18/o...

New Mamba-3 AI Model Beats Transformers by 4%, Runs 7x Faster

#AI #AIModels #AIResearch #DeepLearning #MachineLearning #OpenSourceAI #AIInference #AIBenchmarks #Mamba3 #TogetherAI #StateSpaceModels
New Mamba-3 AI Model Beats Transformers by 4%, Runs 7x Faster
Together.ai has released Mamba-3, an open-source state space model that outperforms Transformers by nearly 4% on language modeling and runs up to 7x faster.
winbuzzer.com
March 18, 2026 at 11:48 AM
nikolazubic.bsky.social
I am looking forward to presenting this work in Nashville! Let's connect at CVPR 2025 in person. Would love to chat about dynamic graph modeling, efficient state propagation, and the future of ML Models.

#CVPR2025 #MachineLearning #TimeSeries #StateSpaceModels #DeepLearning #Nashville #Algorithms
April 9, 2025 at 8:01 AM
getnews-me.bsky.social
The article notes that state space models accelerate recommendation engines and large language models improve content quality. Read more: https://getnews.me/state-space-models-accelerate-recommendations-llms-boost-quality/ #statespacemodels #llms #recommendations
State Space Models Accelerate Recommendations, LLMs Boost Quality
October 8, 2025 at 1:11 PM
getnews-me.bsky.social
The paper expands Structured State‑Space Duality to diagonal state matrices, preserving the O(T) recurrence vs O(T²) attention trade‑off when an SSM matches masked attention. https://getnews.me/state-space-duality-expanded-to-diagonal-models-for-faster-sequences/ #statespacemodels #attention
State‑Space Duality Expanded to Diagonal Models for Faster Sequences
October 8, 2025 at 5:57 AM
getnews-me.bsky.social
In‑training compression trims SSM hidden dimensions during training, preserving performance while speeding up optimization; paper submitted Oct 2025. Read more: https://getnews.me/in-training-compression-improves-efficiency-of-state-space-models/ #statespacemodels #modelcompression
In-Training Compression Improves Efficiency of State Space Models
October 6, 2025 at 8:09 AM
getnews-me.bsky.social
D‑LinOSS adds learnable damping to oscillatory state‑space models, improving long‑range. It hits state‑of‑the‑art results on 50 k‑token tasks; paper posted on arXiv May 2025. Read more: https://getnews.me/damped-oscillatory-state-space-models-boost-long-range-learning/ #dlinoss #statespacemodels
Damped Oscillatory State‑Space Models Boost Long‑Range Learning
October 3, 2025 at 7:46 AM
getnews-me.bsky.social
Researchers find that giving state space models the longest memory horizon improves gradient descent, and fixing recurrent weights matches or exceeds adaptive versions. Read more: https://getnews.me/memory-length-drives-learning-in-state-space-models-study-finds/ #statespacemodels #memorylength
Memory Length Drives Learning in State Space Models, Study Finds
October 2, 2025 at 11:25 PM
getnews-me.bsky.social
Task-Dependent Initialization (TDI) aligns an SSM's spectral bias with a dataset's power spectrum, improving accuracy in low-data regimes. Sep 26 2025. Read more: https://getnews.me/aligning-inductive-bias-boosts-data-efficiency-in-state-space-models/ #taskdependentinitialization #statespacemodels
Aligning Inductive Bias Boosts Data Efficiency in State Space Models
September 30, 2025 at 1:42 AM
ai-bloom.warp-studio.com
感情ベクトルにおける機械論的解釈可能性と状態空間モデル（SSM）の最適化

感情ベクトルの解釈とSSM構造の最適化による次世代AIの可能性。

#MechanisticInterpretability #StateSpaceModels #NeuralDynamics #AffectiveComputing
感情ベクトルにおける機械論的解釈可能性と状態空間モデル（SSM）の最適化
感情ベクトルの解釈とSSM構造の最適化による次世代AIの可能性。
ai.warp-studio.com
April 13, 2026 at 7:23 PM
n1o-cortx.bsky.social
Mamba(2) is great but not without flaws. Combining with Attention can aleviate its shortcommings. If you want to learn more about current SSM-Attention Hybrids I compiled a extensive review with cons and pros:
n1o.github.io/posts/ssm-tr...
#AI #Mamba #StateSpaceModels #LLM
Mamba(2) and Transformer Hybrids: An Overview
Abstract Link to heading We have already looked into Mamba and Mamba2. In terms of efficiency, with their linear complexity and the absence of Key-Value cache, they are a significant improvement over ...
n1o.github.io
November 27, 2024 at 9:15 AM
tildalice.bsky.social
🆕 Mamba-2 vs Griffin vs RWKV-6: SSM Architecture Benchmark

#DeepLearning #AI #StateSpaceModels #Mamba2
https://tildalice.io/mamba-2-griffin-rwkv-6-ssm-benchmark/
February 14, 2026 at 9:34 PM
kostastsampourakis.bsky.social
✅ The AGSF is a robust, flexible & theoretically grounded Bayesian filter. Future work: variational proposals, advanced integration, regime/structural break detection. Implemented in JAX 🚀

#MachineLearning #StateSpaceModels #BayesianML
May 26, 2026 at 9:58 PM
recoveringceo.bsky.social
Full write-up in the blog post.

twosmallfish.vc/portfolio-hi...

#EdgeAI #OnDeviceAI #VoiceAI #TimeSeriesAI #Semiconductors #StateSpaceModels #Robotics #Wearables #AR #HealthTech #Automotive #VentureCapital
Portfolio Highlight: ABR's Funding Round - Two Small Fish
Edge AI has been a key pillar of our Advanced Computing Hardware investments and a core part of our thesis for a long time. It is the same arc I wrote about in The Next Data Centre: Your Phone a while...
twosmallfish.vc
January 13, 2026 at 2:25 PM