Tootfinder

On The Road - To Xi’An 🏮
在路上 - 去西安 🏮
📷 Minolta Hi-Matic AF
🎞️Kentmere Pan 200
#filmphotography #Photography #blackandwhite

Hybrid Physics-ML Framework for Pan-Arctic Permafrost Infrastructure Risk at Record 2.9-Million Observation Scale
Boris Kriuk
https://arxiv.org/abs/2510.02189 https://

Hybrid Physics-ML Framework for Pan-Arctic Permafrost Infrastructure Risk at Record 2.9-Million Observation Scale
Arctic warming threatens over 100 billion in permafrost-dependent infrastructure across Northern territories, yet existing risk assessment frameworks lack spatiotemporal validation, uncertainty quantification, and operational decision-support capabilities. We present a hybrid physics-machine learning framework integrating 2.9 million observations from 171,605 locations (2005-2021) combining permafrost fraction data with climate reanalysis. Our stacked ensemble model (Random Forest + Histogram G…

Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector
Thong Nguyen, Yibin Lei, Jia-Huei Ju, Eugene Yang, Andrew Yates
https://arxiv.org/abs/2510.00671 ht…

Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector
Learned Sparse Retrieval (LSR) combines the efficiency of bi-encoders with the transparency of lexical matching, but existing approaches struggle to scale beyond English. We introduce MILCO, an LSR architecture that maps queries and documents from different languages into a shared English lexical space via a multilingual connector. MILCO is trained with a specialized two-stage regime that combines Sparse Alignment Pretraining with contrastive training to provide representation transparency and …

Fault-Tolerant Decentralized Distributed Asynchronous Federated Learning with Adaptive Termination Detection
Phani Sahasra Akkinepally, Manaswini Piduguralla, Sushant Joshi, Sathya Peri, Sandeep Kulkarni
https://arxiv.org/abs/2509.02186

Fault-Tolerant Decentralized Distributed Asynchronous Federated Learning with Adaptive Termination Detection
Federated Learning (FL) facilitates collaborative model training across distributed clients while ensuring data privacy. Traditionally, FL relies on a centralized server to coordinate learning, which creates bottlenecks and a single point of failure. Decentralized FL architectures eliminate the need for a central server and can operate in either synchronous or asynchronous modes. Synchronous FL requires all clients to compute updates and wait for one another before aggregation, guaranteeing con…

YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
Ranjan Sapkota, Rahul Harsha Cheppally, Ajay Sharda, Manoj Karkee
https://arxiv.org/abs/2509.25164

YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
This study presents Key Architectural Enhancements and Performance Benchmarking of Ultralytics YOLO26 for real-time edge object detection, providing a comprehensive overview of the design principles of YOLO26, technological advances, and deployment readiness. YOLO26, released in September 2025 by Ultralytics, represents the newest and most cutting-edge member of the You Only Look Once (YOLO) family, engineered to push the boundaries of efficiency and accuracy on edge and low-power devices. This…

Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling
Daniel Gallo Fern\'andez
https://arxiv.org/abs/2510.02206 https://arxiv.org/pdf/…

Poolformer: Recurrent Networks with Pooling for Long-Sequence Modeling
Sequence-to-sequence models have become central in Artificial Intelligence, particularly following the introduction of the transformer architecture. While initially developed for Natural Language Processing, these models have demonstrated utility across domains, including Computer Vision. Such models require mechanisms to exchange information along the time dimension, typically using recurrent or self-attention layers. However, self-attention scales quadratically with sequence length, limiting …

A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting
Miha O\v{z}bot, Igor \v{S}krjanc, Vitomir \v{S}truc
https://arxiv.org/abs/2510.00960 https://

A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting
In the complex landscape of multivariate time series forecasting, achieving both accuracy and interpretability remains a significant challenge. This paper introduces the Fuzzy Transformer (Fuzzformer), a novel recurrent neural network architecture combined with multi-head self-attention and fuzzy inference systems to analyze multivariate stock market data and conduct long-term time series forecasting. The method leverages LSTM networks and temporal attention to condense multivariate data into i…

Speech Command Recognition Using LogNNet Reservoir Computing for Embedded Systems
Yuriy Izotov, Andrei Velichko
https://arxiv.org/abs/2509.00862 https://ar…

Speech Command Recognition Using LogNNet Reservoir Computing for Embedded Systems
This paper presents a low-resource speech-command recognizer combining energy-based voice activity detection (VAD), an optimized Mel-Frequency Cepstral Coefficients (MFCC) pipeline, and the LogNNet reservoir-computing classifier. Using four commands from the Speech Commands da-taset downsampled to 8 kHz, we evaluate four MFCC aggregation schemes and find that adaptive binning (64-dimensional feature vector) offers the best accuracy-to-compactness trade-off. The LogNNet classifier with architect…

A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting
Miha O\v{z}bot, Igor \v{S}krjanc, Vitomir \v{S}truc
https://arxiv.org/abs/2510.00960 https://

A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting
In the complex landscape of multivariate time series forecasting, achieving both accuracy and interpretability remains a significant challenge. This paper introduces the Fuzzy Transformer (Fuzzformer), a novel recurrent neural network architecture combined with multi-head self-attention and fuzzy inference systems to analyze multivariate stock market data and conduct long-term time series forecasting. The method leverages LSTM networks and temporal attention to condense multivariate data into i…

Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model
Hyun-kyu Ko, Youbin Kim, Jihyeon Park, Dongheok Park, Gyeongjin Kang, Wonjun Cho, Hyung Yi, Eunbyung Park
https://arxiv.org/abs/2510.00862

Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model
State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated due to their ability to model global context, their quadratic complexity and limited scalability make them less suited for long sequences. Video super-resolution (VSR) methods have traditionally relied on recurrent architectures to propagate features across frames. However, such approaches suffer from well-known issue…