Tootfinder

Alibaba Cloud details a GPU pooling system that it claims reduced the number of Nvidia H20 required by 82% when serving dozens of LLMs of up to 72B parameters (Vincent Chow/South China Morning Post)
https://www.scmp.com/business/article/3329

Alibaba Cloud claims to slash Nvidia GPU use by 82% with new pooling system
The new Aegaeon system can serve dozens of large language models using a fraction of the GPUs previously required, potentially reshaping AI workloads.

ASDFormer: A Transformer with Mixtures of Pooling-Classifier Experts for Robust Autism Diagnosis and Biomarker Discovery
Mohammad Izadi, Mehran Safayani
https://arxiv.org/abs/2508.14005

ASDFormer: A Transformer with Mixtures of Pooling-Classifier Experts for Robust Autism Diagnosis and Biomarker Discovery
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition marked by disruptions in brain connectivity. Functional MRI (fMRI) offers a non-invasive window into large-scale neural dynamics by measuring blood-oxygen-level-dependent (BOLD) signals across the brain. These signals can be modeled as interactions among Regions of Interest (ROIs), which are grouped into functional communities based on their underlying roles in brain function. Emerging evidence suggests that connectivity p…

SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networks
Rodrigue Govan (ISEA), Romane Scherrer (ISEA), Philippe Fournier-Viger (ISEA), Nazha Selmaoui-Folcher (ISEA)
https://arxiv.org/abs/2509.11675

SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networks
This paper introduces SpaPool, a novel pooling method that combines the strengths of both dense and sparse techniques for a graph neural network. SpaPool groups vertices into an adaptive number of clusters, leveraging the benefits of both dense and sparse approaches. It aims to maintain the structural integrity of the graph while reducing its size efficiently. Experimental results on several datasets demonstrate that SpaPool achieves competitive performance compared to existing pooling techniqu…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/6]:
- ASDFormer: A Transformer with Mixtures of Pooling-Classifier Experts for Robust Autism Diagnosis ...
Mohammad Izadi, Mehran Safayani

Synthesizing Evidence: Data-Pooling as a Tool for Treatment Selection in Online Experiments
Zhenkang Peng (Philip), Chengzhang Li (Philip), Ying Rong (Philip), Renyu (Philip), Zhang
https://arxiv.org/abs/2508.10331

Synthesizing Evidence: Data-Pooling as a Tool for Treatment Selection in Online Experiments
Randomized experiments are the gold standard for causal inference but face significant challenges in business applications, including limited traffic allocation, the need for heterogeneous treatment effect estimation, and the complexity of managing overlapping experiments. These factors lead to high variability in treatment effect estimates, making data-driven policy roll out difficult. To address these issues, we introduce the data pooling treatment roll-out (DTR) framework, which enhances pol…

Pooling Probabilistic Forecasts for Cooperative Wind Power Offering
Honglin Wen, Pierre Pinson
https://arxiv.org/abs/2510.12382 https://arxiv.org/pdf/2510.…

Pooling Probabilistic Forecasts for Cooperative Wind Power Offering
Wind power producers can benefit from forming coalitions to participate cooperatively in electricity markets. To support such collaboration, various profit allocation rules rooted in cooperative game theory have been proposed. However, existing approaches overlook the lack of coherence among producers regarding forecast information, which may lead to ambiguity in offering and allocations. In this paper, we introduce a ``reconcile-then-optimize'' framework for cooperative market offerings. This …

Improving Out-of-Domain Audio Deepfake Detection via Layer Selection and Fusion of SSL-Based Countermeasures
Pierre Serrano, Rapha\"el Duroselle, Florian Angulo, Jean-Fran\c{c}ois Bonastre, Olivier Boeffard
https://arxiv.org/abs/2509.12003

Improving Out-of-Domain Audio Deepfake Detection via Layer Selection and Fusion of SSL-Based Countermeasures
Audio deepfake detection systems based on frozen pre-trained self-supervised learning (SSL) encoders show a high level of performance when combined with layer-weighted pooling methods, such as multi-head factorized attentive pooling (MHFA). However, they still struggle to generalize to out-of-domain (OOD) conditions. We tackle this problem by studying the behavior of six different pre-trained SSLs, on four different test corpora. We perform a layer-by-layer analysis to determine which layers co…

SpikePool: Event-driven Spiking Transformer with Pooling Attention
Donghyun Lee, Alex Sima, Yuhang Li, Panos Stinis, Priyadarshini Panda
https://arxiv.org/abs/2510.12102 https:/…

SpikePool: Event-driven Spiking Transformer with Pooling Attention
Building on the success of transformers, Spiking Neural Networks (SNNs) have increasingly been integrated with transformer architectures, leading to spiking transformers that demonstrate promising performance on event-based vision tasks. However, despite these empirical successes, there remains limited understanding of how spiking transformers fundamentally process event-based data. Current approaches primarily focus on architectural modifications without analyzing the underlying signal process…

A Nonparametric Approach to Augmenting a Bayesian VAR with Nonlinear Factors
Todd Clark, Florian Huber, Gary Koop
https://arxiv.org/abs/2508.13972 https://…

A Nonparametric Approach to Augmenting a Bayesian VAR with Nonlinear Factors
This paper proposes a Vector Autoregression augmented with nonlinear factors that are modeled nonparametrically using regression trees. There are four main advantages of our model. First, modeling potential nonlinearities nonparametrically lessens the risk of mis-specification. Second, the use of factor methods ensures that departures from linearity are modeled parsimoniously. In particular, they exhibit functional pooling where a small number of nonlinear factors are used to model common nonli…

Is Exchangeability better than I.I.D to handle Data Distribution Shifts while Pooling Data for Data-scarce Medical image segmentation?
Ayush Roy, Samin Enam, Jun Xia, Vishnu Suresh Lokhande, Won Hwa Kim
https://arxiv.org/abs/2507.19575

Is Exchangeability better than I.I.D to handle Data Distribution Shifts while Pooling Data for Data-scarce Medical image segmentation?
Data scarcity is a major challenge in medical imaging, particularly for deep learning models. While data pooling (combining datasets from multiple sources) and data addition (adding more data from a new dataset) have been shown to enhance model performance, they are not without complications. Specifically, increasing the size of the training dataset through pooling or addition can induce distributional shifts, negatively affecting downstream model performance, a phenomenon known as the "Data Ad…

Ensemble Average Analysis of Non-Adaptive Group Testing with Sparse Pooling Graphs
Emna Ben Yacoub, Gianluigi Liva, Enrico Paolini, Marco Chiani
https://arxiv.org/abs/2507.20281

Ensemble Average Analysis of Non-Adaptive Group Testing with Sparse Pooling Graphs
A combinatorial analysis of the false alarm (FA) and misdetection (MD) probabilities of non-adaptive group testing with sparse pooling graphs is developed. The analysis targets the combinatorial orthogonal matching pursuit and definite defective detection algorithms in the noiseless, non-quantitative setting. The approach follows an ensemble average perspective, where average FA/MD probabilities are computed for pooling graph ensembles with prescribed degree distributions. The accuracy of the a…

Balancing Profit and Traveller Acceptance in Ride-Pooling Personalised Fares
Michal Bujak, Rafal Kucharski
https://arxiv.org/abs/2508.20723 https://arxiv.o…

Balancing Profit and Traveller Acceptance in Ride-Pooling Personalised Fares
Ride-pooling systems, to succeed, must provide an attractive service, namely compensate perceived costs with an appealing price. However, because of a strong heterogeneity in a value-of-time, each traveller has his own acceptable price, unknown to the operator. Here, we show that individual acceptance levels can be learned by the operator (over $90\%$ accuracy for pooled travellers in $10$ days) to optimise personalised fares. We propose an adaptive pricing policy, where every day the operator …

DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction
Cheng-Yeh Yang, Kuan-Tang Huang, Chien-Chun Wang, Hung-Shin Lee, Hsin-Min Wang, Berlin Chen
https://arxiv.org/abs/2508.21407

DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction
A pooling mechanism is essential for mean opinion score (MOS) prediction, facilitating the transformation of variable-length audio features into a concise fixed-size representation that effectively encodes speech quality. Existing pooling methods typically operate at a singular granularity, concentrating either on a comprehensive global perspective or a detailed frame-level analysis, which may overlook complementary perceptual insights. To address this limitation, we introduce the Dual-Resoluti…

Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation
Van-Khang Nguyen, Duc-Hoang Pham, Huy-Son Nguyen, Cam-Van Thi Nguyen, Hoang-Quynh Le, Duc-Trong Le
https://arxiv.org/abs/2508.08042

Multi-modal Adaptive Mixture of Experts for Cold-start Recommendation
Recommendation systems have faced significant challenges in cold-start scenarios, where new items with a limited history of interaction need to be effectively recommended to users. Though multimodal data (e.g., images, text, audio, etc.) offer rich information to address this issue, existing approaches often employ simplistic integration methods such as concatenation, average pooling, or fixed weighting schemes, which fail to capture the complex relationships between modalities. Our study propo…

Hybrid Quantum-Classical Learning for Multiclass Image Classification
Shuchismita Anwar, Sowmitra Das, Muhammad Iqbal Hossain, Jishnu Mahmud
https://arxiv.org/abs/2508.18161 htt…

Hybrid Quantum-Classical Learning for Multiclass Image Classification
This study explores the challenge of improving multiclass image classification through quantum machine-learning techniques. It explores how the discarded qubit states of Noisy Intermediate-Scale Quantum (NISQ) quantum convolutional neural networks (QCNNs) can be leveraged alongside a classical classifier to improve classification performance. Current QCNNs discard qubit states after pooling; yet, unlike classical pooling, these qubits often remain entangled with the retained ones, meaning valua…

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 …

Bayesian Stacking via Proper Scoring Rule Optimization using a Gibbs Posterior
Spencer Wadsworth, Jarad Niemi
https://arxiv.org/abs/2509.04203 https://arxi…

Bayesian Stacking via Proper Scoring Rule Optimization using a Gibbs Posterior
In collaborative forecast projects, the combining of multiple probabilistic forecasts into an ensemble is standard practice, with linear pooling being a common combination method. The weighting scheme of a linear pool should be tailored to the specific research question, and weight selection is often performed via optimizing a proper scoring rule. This is known as optimal linear pooling. Besides optimal linear pooling, Bayesian predictive synthesis has emerged as a model probability updating sc…

Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems
Mingyu Cui, Mengzhe Geng, Jiajun Deng, Chengxi Deng, Jiawen Kang, Shujie Hu, Guinan Li, Tianzi Wang, Zhaoqing Li, Xie Chen, Xunying Liu
https://arxiv.org/abs/2508.10456

Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems
This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding concatenation; iii) cross-utterance Encoder embedding pooling projection; or iv) a novel chunk-based approach applied to C-T models for the first time. An efficient batch-training scheme is proposed for contextual C-Ts that uses spliced speech utterances withi…

Replaced article(s) found for q-fin.MF. https://arxiv.org/list/q-fin.MF/new
[1/1]:
- A General CoVaR Based on Entropy Pooling
Yuhong Xu, Xinyao Zhao
https://…

Efficient Code Embeddings from Code Generation Models
Daria Kryvosheieva, Saba Sturua, Michael G\"unther, Scott Martens, Han Xiao
https://arxiv.org/abs/2508.21290 https://

Efficient Code Embeddings from Code Generation Models
jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages. It makes innovative use of an autoregressive backbone pre-trained on both text and code, generating embeddings via last-token pooling. We outline the training recipe and demonstrate state-of-the-art performance despite the relatively small size of the models, validat…

Group Formation through Game Theory and Agent-Based Modeling: Spatial Cohesion, Heterogeneity, and Resource Pooling
Chenlan Wang, Jimin Han, Diana Jue-Rajasingh
https://arxiv.org/abs/2509.18551

Comparative Analysis of Global and Local Probabilistic Time Series Forecasting for Contiguous Spatial Demand Regions
Jiahe Ling, Wei Biao Wu
https://arxiv.org/abs/2509.08214 htt…

Comparative Analysis of Global and Local Probabilistic Time Series Forecasting for Contiguous Spatial Demand Regions
This study evaluates three probabilistic forecasting strategies using LightGBM: global pooling, cluster-level pooling, and station-level modeling across a range of scenarios, from fully homogeneous simulated data to highly heterogeneous real-world Divvy bike-share demand observed during 2023 to 2024. Clustering was performed using the K-means algorithm applied to principal component analysis transformed covariates, which included time series features, counts of nearby transportation infrastruct…

General CoVaR Based on Entropy Pooling
Yuhong Xu, Xinyao Zhao
https://arxiv.org/abs/2509.21904 https://arxiv.org/pdf/2509.21904

General CoVaR Based on Entropy Pooling
We propose a general CoVaR framework that extends the traditional CoVaR by incorporating diverse expert views and information, such as asset moment characteristics, quantile insights, and perspectives on the relative loss distribution between two assets. To integrate these expert views effectively while minimizing deviations from the prior distribution, we employ the entropy pooling method to derive the posterior distribution, which in turn enables us to compute the general CoVaR. Assuming biva…

PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis
Dinghao Zou, Yicheng Gong, Xiaokang Li, Xin Cao, Sunbowen Lee
https://arxiv.org/abs/2509.11976

PoolingVQ: A VQVAE Variant for Reducing Audio Redundancy and Boosting Multi-Modal Fusion in Music Emotion Analysis
Multimodal music emotion analysis leverages audio and MIDI modalities to enhance performance. While mainstream approaches focus on complex feature extraction networks, we posit that shortening the length of audio sequence features to mitigate redundancy, especially in contrast to MIDI's compact representation, may effectively boost task performance. To achieve this, we developed PoolingVQ by combining Vector Quantized Variational Autoencoder (VQVAE) with spatial pooling, which directly compress…

Replaced article(s) found for physics.soc-ph. https://arxiv.org/list/physics.soc-ph/new
[1/1]:
- Ride-pooling adoption model for $\mathrm{CO_2}$ emission estimation
Milli Keil, Felix Creutzig, Nora Molkenthin

Community detection robustness of graph neural networks
Jaidev Goel, Pablo Moriano, Ramakrishnan Kannan, Yulia R. Gel
https://arxiv.org/abs/2509.24662 https://

Community detection robustness of graph neural networks
Graph neural networks (GNNs) are increasingly widely used for community detection in attributed networks. They combine structural topology with node attributes through message passing and pooling. However, their robustness or lack of thereof with respect to different perturbations and targeted attacks in conjunction with community detection tasks is not well understood. To shed light into latent mechanisms behind GNN sensitivity on community detection tasks, we conduct a systematic computationa…

TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving
Bingyang Wu, Zili Zhang, Yinmin Zhong, Guanzhe Huang, Yibo Zhu, Xuanzhe Liu, Xin Jin
https://arxiv.org/abs/2508.17219

TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving
Prefix caching is crucial to accelerate multi-turn interactions and requests with shared prefixes. At the cluster level, existing prefix caching systems are tightly coupled with request scheduling to optimize cache efficiency and computation performance together, leading to load imbalance, data redundancy, and memory fragmentation of caching systems across instances. To address these issues, memory pooling is promising to shield the scheduler from the underlying cache management so that it can …

Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning
Benedikt Roth, Stephan Rappensperger, Tianming Qiu, Hamza Imamovi\'c, Julian W\"ormann, Hao Shen
https://arxiv.org/abs/2507.22729

Resource-Efficient Adaptation of Large Language Models for Text Embeddings via Prompt Engineering and Contrastive Fine-tuning
Large Language Models (LLMs) have become a cornerstone in Natural Language Processing (NLP), achieving impressive performance in text generation. Their token-level representations capture rich, human-aligned semantics. However, pooling these vectors into a text embedding discards crucial information. Nevertheless, many non-generative downstream tasks, such as clustering, classification, or retrieval, still depend on accurate and controllable sentence- or document-level embeddings. We explore se…

Enhancing compact convolutional transformers with super attention
Simpenzwe Honore Leandre, Natenaile Asmamaw Shiferaw, Dillip Rout
https://arxiv.org/abs/2508.18960 https://

Enhancing compact convolutional transformers with super attention
In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our model significantly improves the baseline of the top 1% and top 5% validation accuracy from 36.50% to 46.29% and 66.33% to 76.31%, while being more efficient than the Scaled Dot Product Attention (SDPA) transformers when the context length is less than the em…

Crosslisted article(s) found for q-fin.RM. https://arxiv.org/list/q-fin.RM/new
[1/1]:
- General CoVaR Based on Entropy Pooling
Yuhong Xu, Xinyao Zhao
https://

An Overlapping Coalition Game Approach for Collaborative Block Mining and Edge Task Offloading in MEC-assisted Blockchain Networks
Licheng Ye, Zehui Xiong, Lin Gao, Dusit Niyato
https://arxiv.org/abs/2508.06031

An Overlapping Coalition Game Approach for Collaborative Block Mining and Edge Task Offloading in MEC-assisted Blockchain Networks
Mobile edge computing (MEC) is a promising technology that enhances the efficiency of mobile blockchain networks, by enabling miners, often acted by mobile users (MUs) with limited computing resources, to offload resource-intensive mining tasks to nearby edge computing servers. Collaborative block mining can further boost mining efficiency by allowing multiple miners to form coalitions, pooling their computing resources and transaction data together to mine new blocks collaboratively. Therefore…

CUHK-EE Systems for the vTAD Challenge at NCMMSC 2025
Aemon Yat Fei Chiu, Jingyu Li, Yusheng Tian, Guangyan Zhang, Tan Lee
https://arxiv.org/abs/2507.23266 https://

CUHK-EE Systems for the vTAD Challenge at NCMMSC 2025
This paper presents the Voice Timbre Attribute Detection (vTAD) systems developed by the Digital Signal Processing & Speech Technology Laboratory (DSP&STL) of the Department of Electronic Engineering (EE) at The Chinese University of Hong Kong (CUHK) for the 20th National Conference on Human-Computer Speech Communication (NCMMSC 2025) vTAD Challenge. The proposed systems leverage WavLM-Large embeddings with attentive statistical pooling to extract robust speaker representations, followed by two…

SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
Jiaye Tan, Haonan Luo, Linfeng Song, Shuaiqi Chen, Yishan Lyu, Zian Zhong, Roujia Wang, Daniel Jiang, Haoran Zhang, Jiaming Bai, Haoran Cheng, Q. Vera Liao, Hao-Wen Dong
https://arxiv.org/abs/2510.00395…

SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
Low-latency symbolic music generation is essential for real-time improvisation and human-AI co-creation. Existing transformer-based models, however, face a trade-off between inference speed and musical quality. Traditional acceleration techniques such as embedding pooling significantly degrade quality, while recently proposed Byte Pair Encoding (BPE) methods - though effective on single-track piano data - suffer large performance drops in multi-track settings, as revealed by our analysis. We pr…

Incentives in Federated Learning with Heterogeneous Agents
Ariel D. Procaccia, Han Shao, Itai Shapira
https://arxiv.org/abs/2509.21612 https://arxiv.org/pd…

Incentives in Federated Learning with Heterogeneous Agents
Federated learning promises significant sample-efficiency gains by pooling data across multiple agents, yet incentive misalignment is an obstacle: each update is costly to the contributor but boosts every participant. We introduce a game-theoretic framework that captures heterogeneous data: an agent's utility depends on who supplies each sample, not just how many. Agents aim to meet a PAC-style accuracy threshold at minimal personal cost. We show that uncoordinated play yields pathologies: pure…

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Lukas Rauch, Ren\'e Heinrich, Houtan Ghaffari, Lukas Miklautz, Ilyass Moummad, Bernhard Sick, Christoph Scholz
https://arxiv.org/abs/2509.24901

Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning. A key reason is that global pooling creates an information bottleneck causing linear probes to misrepresent the embedding quality: The $\texttt{cls}$-token discards crucial token information about dispersed, localized events in multi-label audio. This weakness is rooted in the mismatch between the pretraining objective (operating globally) and the downstream task …