Tag
The paper introduces Variational Atlas Autoencoders, a mixture-of-charts framework that learns multiple local latent representations over a data manifold, using latent-evidence routing to treat chart assignment as self-supervised posterior inference, achieving better-structured latent spaces and higher sample quality on datasets like CelebA.
本文提出 D-VAE（Deconfounder Variational Autoencoder）因果推断框架，用于评估 LLM 生成广告中专家营销标签的因果价值，并在 29,177 个化妆品广告创意上验证其效果，实验显示推荐配置可提升 32.7% 的用户互动。
Empirical Variational Autoencoder (EVA) is a general generative framework for continuous-valued sequences that learns autoregressive latent priors empirically from training data, alleviating the prior-posterior gap of conventional VAEs and achieving competitive generation quality with autoregressive diffusion baselines at much faster inference speed.
论文提出 E-MoE（Enhanced Mixture-of-Experts），用 MoE 路由决策构成的离散共享隐变量来建模非因子化的反向过程，缓解连续隐变量的后验坍缩问题，并在无需增加活跃参数的情况下提升掩码扩散语言模型在少步生成场景下的样本质量。
This paper presents a workflow using text-to-image foundation models and variational autoencoders to rank competing geologic interpretations based on their consistency with hydraulic-head observations, improving early-stage subsurface decision-making.
This paper proposes a zero-shot learning framework for multivariate IoT traffic anomaly detection using adversarial and contrastive learning within a variational autoencoder, enabling domain adaptation without labeled data and demonstrating strong performance across diverse datasets.
Luce unifies geometry and PBR materials in a voxelized Gaussian cloud to generate relightable 3D assets from single images, achieving state-of-the-art results on benchmarks like Toys4K.
CLaST introduces a context-aware contrastive VAE framework for probabilistic multivariate time series forecasting, demonstrating significant performance improvements over baseline methods on multiple benchmarks.
This paper releases an open eleven-structure cardiac CT statistical shape model and compares shape completion methods, demonstrating that a closed-form conditional-Gaussian estimator outperforms deep learning approaches like variational autoencoders.
This paper studies how β-VAEs act as effective theories where the KL weight acts as a spectral cutoff, and analyzes how nonlinear interactions and network depth affect the tolerance-dependent effective dimension of representations.
Introduces ELVAE, a VAE with evidential learning that models latent coordinates with normal-inverse-gamma posteriors to obtain explicit uncertainty estimates. Experiments on MNIST show that within-class uncertainty ranking can stratify synthetic sample reliability and stress-testing, though results require class-wise normalization and vary across seeds.
This paper presents an AI-driven multimodal mediation framework using variational autoencoders to discover latent pathways linking socioeconomic disadvantage, psychosocial factors, and cardiometabolic multimorbidity in the All of Us Research Program cohort.
Proposes a two-timescale multi-layer deep reinforcement learning framework with latent action space for joint service placement, computational delegation, and power control in hierarchical edge-cloud computing, achieving up to 20.8% latency reduction and 13% resource utilization improvement.
This paper presents BattVAE-GP, a hybrid physics-probabilistic framework that combines a Variational Autoencoder with a sparse multitask Gaussian Process to generate and interpolate long-horizon battery degradation trajectories with uncertainty estimates, enabling efficient surrogate modeling for lithium-ion battery health prediction.
Presents a Variational Graph Autoencoder (VGAE) for detecting power flow solution feasibility in electric power networks, using the IEEE 118-bus case. The method distinguishes between problem infeasibility and algorithm non-convergence.
Identifies two coupled causes of posterior collapse in VAEs and introduces λ-VAE, a modification to the reparameterization step that equalizes variance across latent dimensions, reducing collapse and improving information capacity.
Proposes an end-to-end agentic pipeline combining SSA-LSTM forecasting, LSTM VAE anomaly detection, and LLM-based reasoning with dynamic retrieval to generate prioritized maintenance recommendations for appliance-level energy anomalies, achieving a 90.4/100 score on a 16-scenario benchmark.
This paper presents a discrete autoregressive transformer that generates planar mechanisms from target coupler curves, using variational autoencoder latents and tokenized joint coordinates to achieve diverse, accurate designs across multiple topologies.
This paper proposes a hybrid classical-quantum variational autoencoder for neural topic modeling, embedding parameterized quantum circuits in the inference network. Experiments on the AgNews dataset demonstrate improved topic coherence and diversity compared to state-of-the-art classical models, showing viability on NISQ-era quantum devices.
DeepRHP is a hybrid variational autoencoder that guides the design of random heteropolymers as protein mimics, demonstrated by stabilizing membrane proteins like Aquaporin Z in non-native environments.