Tootfinder

Bayesian online collective anomaly and change point detection in fine-grained time series
Xian Chen, Weichi Wu
https://arxiv.org/abs/2508.06385 https://arx…

Bayesian online collective anomaly and change point detection in fine-grained time series
Fine-grained time series data are crucial for accurate and timely online change detection. While both collective anomalies and change points can coexist in such data, their joint online detection has received limited attention. In this research, we develop a Bayesian framework capturing time series with collective anomalies and change points, and introduce a recursive online inference algorithm to detect the most recent collective anomaly and change point jointly. For scaling, we further propos…

This https://arxiv.org/abs/2506.03296 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Parallel CPU-GPU Execution for LLM Inference on Constrained GPUs
Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution by offloading KV cache management and parts of attention computation to the CPU. However, a key bottleneck remains: existing schedulers fail to effectively overlap CPU-offloaded tasks with GPU execution during the latency-critical, bandwidth-bound decode phase…

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
Cheng-Long Wang, Qi Li, Zihang Xiang, Yinzhi Cao, Di Wang
https://arxiv.org/abs/2506.06112

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techniques like Membership Inference Attacks (MIAs) are widely used to externally assess successful unlearning. However, existing methods face two key limitations: (1) maximizing MIA effectiveness (e.g., via online attacks) requires prohibitive computational resources, often exceeding retraining costs; (2) MIAs, designed f…

Neural Visibility Cache for Real-Time Light Sampling
Jakub Bok\v{s}ansk\'y, Daniel Meister
https://arxiv.org/abs/2506.05930 https://

Neural Visibility Cache for Real-Time Light Sampling
Direct illumination with many lights is an inherent component of physically-based rendering, remaining challenging, especially in real-time scenarios. We propose an online-trained neural cache that stores visibility between lights and 3D positions. We feed light visibility to weighted reservoir sampling (WRS) to sample a light source. The cache is implemented as a fully-fused multilayer perceptron (MLP) with multi-resolution hash-grid encoding, enabling online training and efficient inference o…

Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models
Julian Lemmel, Manuel Kranzl, Adam Lamine, Philipp Neubauer, Radu Grosu, Sophie Neubauer
https://arxiv.org/abs/2508.00804

Online Fine-Tuning of Carbon Emission Predictions using Real-Time Recurrent Learning for State Space Models
This paper introduces a new approach for fine-tuning the predictions of structured state space models (SSMs) at inference time using real-time recurrent learning. While SSMs are known for their efficiency and long-range modeling capabilities, they are typically trained offline and remain static during deployment. Our method enables online adaptation by continuously updating model parameters in response to incoming data. We evaluate our approach for linear-recurrent-unit SSMs using a small carbo…

Harnessing the Power of Interleaving and Counterfactual Evaluation for Airbnb Search Ranking
Qing Zhang, Alex Deng, Michelle Du, Huiji Gao, Liwei He, Sanjeev Katariya
https://arxiv.org/abs/2508.00751

Harnessing the Power of Interleaving and Counterfactual Evaluation for Airbnb Search Ranking
Evaluation plays a crucial role in the development of ranking algorithms on search and recommender systems. It enables online platforms to create user-friendly features that drive commercial success in a steady and effective manner. The online environment is particularly conducive to applying causal inference techniques, such as randomized controlled experiments (known as A/B test), which are often more challenging to implement in fields like medicine and public policy. However, businesses face…

Parallel CPU-GPU Execution for LLM Inference on Constrained GPUs
Jiakun Fan, Yanglin Zhang, Xiangchen Li, Dimitrios S. Nikolopoulos
https://arxiv.org/abs/2506.03296

Parallel CPU-GPU Execution for LLM Inference on Constrained GPUs
Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution by offloading KV cache management and parts of attention computation to the CPU. However, a key bottleneck remains: existing schedulers fail to effectively overlap CPU-offloaded tasks with GPU execution during the latency-critical, bandwidth-bound decode phase…

LLM-Powered CPI Prediction Inference with Online Text Time Series
Yingying Fan, Jinchi Lv, Ao Sun, Yurou Wang
https://arxiv.org/abs/2506.09516 https://

LLM-Powered CPI Prediction Inference with Online Text Time Series
Forecasting the Consumer Price Index (CPI) is an important yet challenging task in economics, where most existing approaches rely on low-frequency, survey-based data. With the recent advances of large language models (LLMs), there is growing potential to leverage high-frequency online text data for improved CPI prediction, an area still largely unexplored. This paper proposes LLM-CPI, an LLM-based approach for CPI prediction inference incorporating online text time series. We collect a large se…

At Berlin Buzzwords 2025, join Dhrubo Saha to discover how OpenSearch pipelines are integrating ML inference processors for powerful multi-modal search. Learn to search directly within images, audio, and text – locally on your own hardware!
Learn more: https://

Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency
Bunlong Lay, Rostilav Makarov, Timo Gerkmann
https://arxiv.org/abs/2506.02908

Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency
Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical for processing streaming data in real-time. In this work, we adapt a sliding window diffusion framework to the speech enhancement task. Our approach progressively corrupts speech signals through time, assigning more noise to frames close to the present in a buffer. This approach …

Embedded FPGA Acceleration of Brain-Like Neural Networks: Online Learning to Scalable Inference
Muhammad Ihsan Al Hafiz, Naresh Ravichandran, Anders Lansner, Pawel Herman, Artur Podobas
https://arxiv.org/abs/2506.18530

Embedded FPGA Acceleration of Brain-Like Neural Networks: Online Learning to Scalable Inference
Edge AI applications increasingly require models that can learn and adapt on-device with minimal energy budget. Traditional deep learning models, while powerful, are often overparameterized, energy-hungry, and dependent on cloud connectivity. Brain-Like Neural Networks (BLNNs), such as the Bayesian Confidence Propagation Neural Network (BCPNN), propose a neuromorphic alternative by mimicking cortical architecture and biologically-constrained learning. They offer sparse architectures with local …

Online survival analysis with quantile regression
Yi Deng, Shuwei Li, Liuquan Sun, Baoxue Zhang
https://arxiv.org/abs/2507.15696 https://

Online survival analysis with quantile regression
We propose an online inference method for censored quantile regression with streaming data sets. A key strategy is to approximate the martingale-based unsmooth objective function with a quadratic loss function involving a well-justified second-order expansion. This enables us to derive a new online convex function based on the current data batch and summary statistics of historical data, thereby achieving online updating and occupying low storage space. To estimate the regression parameters, we…

Online Rolling Controlled Sequential Monte Carlo
Liwen Xue, Axel Finke, Adam M. Johansen
https://arxiv.org/abs/2508.00696 https://arxiv.org/pdf/2508.00696

Online Rolling Controlled Sequential Monte Carlo
We introduce methodology for real-time inference in general-state-space hidden Markov models. Specifically, we extend recent advances in controlled sequential Monte Carlo (CSMC) methods-originally proposed for offline smoothing-to the online setting via a rolling window mechanism. Our novel online rolling controlled sequential Monte Carlo (ORCSMC) algorithm employs two particle systems to simultaneously estimate twisting functions and perform filtering, ensuring real-time adaptivity to new obse…

InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching
Yilun Wang, Pengfei Chen, Haiyu Huang, Zilong He, Gou Tan, Chuanfu Zhang, Jingkai He, Zibin Zheng
https://arxiv.org/abs/2507.08523

InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching
Modern software systems generate massive volumes of runtime logs, necessitating efficient and accurate log parsing to enable critical downstream tasks such as anomaly detection and root cause analysis. Recently, large language models (LLMs) have achieved advanced accuracy on log parsing, but their deployment in production environments faces two major limitations: (1) the privacy risks associated with commercial LLMs, driving the adoption of local deployment, and (2) the stringent latency and th…

Learning Binarized Representations with Pseudo-positive Sample Enhancement for Efficient Graph Collaborative Filtering
Yankai Chen, Yue Que, Xinni Zhang, Chen Ma, Irwin King
https://arxiv.org/abs/2506.02750

Learning Binarized Representations with Pseudo-positive Sample Enhancement for Efficient Graph Collaborative Filtering
Learning vectorized embeddings is fundamental to many recommender systems for user-item matching. To enable efficient online inference, representation binarization, which embeds latent features into compact binary sequences, has recently shown significant promise in optimizing both memory usage and computational overhead. However, existing approaches primarily focus on numerical quantization, neglecting the associated information loss, which often results in noticeable performance degradation. …

Let's Measure the Elephant in the Room: Facilitating Personalized Automated Analysis of Privacy Policies at Scale
Rui Zhao, Vladyslav Melnychuk, Jun Zhao, Jesse Wright, Nigel Shadbolt
https://arxiv.org/abs/2507.14214

Let's Measure the Elephant in the Room: Facilitating Personalized Automated Analysis of Privacy Policies at Scale
In modern times, people have numerous online accounts, but they rarely read the Terms of Service or Privacy Policy of those sites despite claiming otherwise. This paper introduces PoliAnalyzer, a neuro-symbolic system that assists users with personalized privacy policy analysis. PoliAnalyzer uses Natural Language Processing (NLP) to extract formal representations of data usage practices from policy texts. In favor of deterministic, logical inference is applied to compare user preferences with t…

Advancing global sea ice prediction capabilities using a fully-coupled climate model with integrated machine learning
William Gregory, Mitchell Bushuk, Yong-Fei Zhang, Alistair Adcroft, Laure Zanna, Colleen McHugh, Liwei Jia
https://arxiv.org/abs/2505.18328

Advancing global sea ice prediction capabilities using a fully-coupled climate model with integrated machine learning
We showcase a hybrid modeling framework which embeds machine learning (ML) inference into the GFDL SPEAR climate model, for online sea ice bias correction during a set of global fully-coupled 1-year retrospective forecasts. We compare two hybrid versions of SPEAR to understand the importance of exposing ML models to coupled ice-atmosphere-ocean feedbacks before implementation into fully-coupled simulations: Hybrid_CPL (with feedbacks) and Hybrid_IO (without feedbacks). Relative to SPEAR, Hybrid…

Analysis of Anonymous User Interaction Relationships and Prediction of Advertising Feedback Based on Graph Neural Network
Yanjun Dai, Haoyang Feng, Yuan Gao
https://arxiv.org/abs/2506.13787

Analysis of Anonymous User Interaction Relationships and Prediction of Advertising Feedback Based on Graph Neural Network
While online advertising is highly dependent on implicit interaction networks of anonymous users for engagement inference, and for the selection and optimization of delivery strategies, existing graph models seldom can capture the multi-scale temporal, semantic and higher-order dependency features of these interaction networks, thus it's hard to describe the complicated patterns of the anonymous behavior. In this paper, we propose Decoupled Temporal-Hierarchical Graph Neural Network (DTH-GNN), …