惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

U
Unit 42
V
V2EX
Martin Fowler
Martin Fowler
博
博客园 - Franky
P
Proofpoint News Feed
P
Palo Alto Networks Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
B
Blog
The Register - Security
The Register - Security
Latest news
Latest news
S
Security @ Cisco Blogs
Simon Willison's Weblog
Simon Willison's Weblog
Recorded Future
Recorded Future
大猫的无限游戏
大猫的无限游戏
M
Microsoft Research Blog - Microsoft Research
Scott Helme
Scott Helme
T
Tailwind CSS Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Application and Cybersecurity Blog
Application and Cybersecurity Blog
T
True Tiger Recordings
有赞技术团队
有赞技术团队
I
Intezer
Cisco Talos Blog
Cisco Talos Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
The GitHub Blog
The GitHub Blog
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
T
Tenable Blog
博
博客园 - 叶小钗
Hugging Face - Blog
Hugging Face - Blog
Hacker News: Ask HN
Hacker News: Ask HN
S
Security Archives - TechRepublic
F
Future of Privacy Forum
爱范儿
爱范儿
PCI Perspectives
PCI Perspectives
H
Help Net Security
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
T
The Blog of Author Tim Ferriss
MyScale Blog
MyScale Blog
N
Netflix TechBlog - Medium
罗
罗磊的独立博客
Apple Machine Learning Research
Apple Machine Learning Research
MongoDB | Blog
MongoDB | Blog
Security Latest
Security Latest
美
美团技术团队
博
博客园 - 三生石上(FineUI控件)
S
Schneier on Security
量
量子位
C
CERT Recently Published Vulnerability Notes
SecWiki News
SecWiki News

cs.LG updates on arXiv.org

ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning One-Way Policy Optimization for Self-Evolving LLMs Three Costs of Amortizing Gaussian Process Inference with Neural Processes When to Switch, Not Just What: Transition Quality Prediction in Clash Royale TBP-mHC: full expressivity for manifold-constrained hyper connections through transportation polytopes Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation Bandit Convex Optimization with Gradient Prediction Adaptivity Harnesses for Inference-Time Alignment over Execution Trajectories Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization How Many Different Outputs Can a Transformer Generate? Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning AgForce Enables Antigen-conditioned Generative Antibody Design SepsisAI Orchestrator: A Containerized and Scalable Platform for Deploying AI Models and Real-Time Monitoring in Early Sepsis Detection SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization Predicting Performance of Symbolic and Prompt Programs with Examples Tabular foundation models for robust calibration of near-infrared chemical sensing data OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans $\textit{BlockFormer}$ : Transformer-based inference from interaction maps Neural Acceleration for Graph Partitioning IKNO: Infinite-order Kernel Neural Operators Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks Detecting Atypical Clients in Federated Learning via Representation-Level Divergence PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting Toward Understanding Adversarial Distillation: Why Robust Teachers Fail From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy CausalGuard: Conformal Inference under Graph Uncertainty Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations Noise Schedule Design for Diffusion Models: An Optimal Control Perspective Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems Learning Causal Orderings for In-Context Tabular Prediction The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models ASAP: Attention Sink Anchored Pruning Can Breath Biomarkers Causally Influence Blood Glucose? Investigating VOC-Mediated Modulation in Diabetes Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning What are the Right Symmetries for Formal Theorem Proving? Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations Provable Joint Decontamination for Benchmarking Multiple Large Language Models Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation Manifold-Guided Attention Steering Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation Can Transformers Learn to Verify During Backtracking Search? Holomorphic Neural ODEs with Kolmogorov-Arnold Networks for Interpretable Discovery of Complex Dynamics stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation Dynamic Mixture of Latent Memories for Self-Evolving Agents Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models Double descent for least-squares interpolation on contaminated data: A simulation study Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction Aerodynamic force reconstruction using physics-informed Gaussian processes Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks Long-term Fairness with Selective Labels Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation Symbolic Density Estimation for Discrete Distributions Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification
ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification
Jos\'e Alber · 2026-05-23 · via cs.LG updates on arXiv.org

View PDF HTML (experimental)

Abstract:Time Series Foundation Models (TSFMs) have become a new component of the state-of-the-art in general time series forecasting. However, adapting them to specialized classification tasks remains constrained by two interconnected challenges: the quadratic cost of standard attention mechanisms and the inability to disentangle the structural components underlying time series variability. This technical report introduces ChronoVAE-HOPE, a next-generation TSFM that reconciles massive generalization with structured latent representation for time series classification. The core of the proposal is a Variational Autoencoder (VAE) framework built upon the HOPE Block, which replaces quadratic attention with a dual-memory system: Titans modules for dynamic short-term retention and a Continuum Memory System (CMS) for the abstraction of long-term historical context. A key architectural novelty is the disentangled latent space, which factorizes representations into independent trend and seasonal components via dedicated encoder heads and separate decoder pathways. ChronoVAE-HOPE undergoes self-supervised pre-training on the Monash archive, combining a Masked Time Series Modeling (MTSM) auxiliary objective with a disentangled VAE reconstruction loss. The pre-trained encoder is subsequently frozen and used to generate fixed-length embeddings for downstream classification on the UCR benchmark datasets. Empirical results demonstrate strong performance across diverse temporal domains, particularly in settings characterized by strict causal structure. ChronoVAE-HOPE establishes a robust and interpretable framework for the adaptation of foundation models to time series classification through structured generative representations.
Subjects: Machine Learning (cs.LG)
Cite as: arXiv:2605.22684 [cs.LG]
  (or arXiv:2605.22684v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2605.22684

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Luis Balderas Ruiz [view email]
[v1] Thu, 21 May 2026 16:26:09 UTC (652 KB)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。