ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Variational autoencoders”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.LGmath.OCstat.MLEmpiricalRecentJul 26, 2026

A Multi-stage Constrained Optimization Framework for Data-driven Problems

Ye Shi

This paper proposes a Multi-stage Constrained Optimization Framework (MCOF) for Variational Autoencoders (VAEs) to address challenges in sampling, identifying active decision variables, and enforcing…

View →
cs.LGcs.AIRecentMay 28, 2026

The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer

Tianhua Chen

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

View →
eess.AScs.SDEmpiricalRecentJun 22, 2026

STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation

Huadai Liu, Wen Wang, Kaicheng Luo, Qian Chen +2 more

This paper proposes Structured Topology-Aware Regularization (STAR) to address the Rate-Distortion-Regularity Trilemma in continuous Variational Autoencoders (VAEs) for audio generation.

View →
cs.LGstat.MLEmpiricalRecentJul 26, 2026

Soft-Constrained Optimization of Latent Space in Variational Autoencoders

Ye Shi

This paper proposes methods to improve the encoding capacity and disentanglement of Variational Autoencoders (VAE) by imposing entropy-based constraints and a weight-filter method.

View →
eess.AScs.SDeess.SPEmpiricalRecentAug 17, 2026

Contrastive Learning with Variational Regularization for Multi-Session EEG-to-Speech Decoding

Tomoaki Mizuno, Toru Nakashika

This paper proposes a method for improving the reconstruction of heard speech from non-invasive EEG using contrastive learning and variational regularization.

View →
cs.CVcs.LGEmpiricalRecentSep 23, 2026

On the Diffusibility of High-Dimensional Latents

Chao Feng, Zhiyang Xu, Bowei Chen, Yuanjun Xiong +6 more

This paper improves text-to-image generation performance by using the clean data parameterization in RAEs.

View →
cs.CVEmpiricalRecentSep 25, 2026

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Hongyang Du, Yunfei Xie, Junjie Ye, Jiawei Yang +12 more

The paper introduces FuseReg, a method that replaces heuristic feature selection with training over random subsets of encoder layers in representation autoencoders.

View →
cs.LGcs.AIRecentMay 27, 2026

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions

Prathyush Poduval, Calvin Yeung, Neel Desai, Mohsen Imani

The paper introduces Residualized Sparse Autoencoders (ReSAEs) to improve multi-layer interventions in transformers by training each layer on the residual activation, which better preserves cross-laye…

View →
cs.LGcs.AIRecentMay 27, 2026

Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression

Tue M. Cao, Nguyen Do, My T. Thai

The paper introduces a distributional framework using Wasserstein distance to unify the semantic comparison of sparse autoencoder features across different layers and to automatically compress large f…

View →
cs.LGcs.AIEmpiricalRecentJun 29, 2026

C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

Haoran Jin, Xiting Wang, Shijie Ren, Hong Xie +1 more

The paper introduces C$^2$R (Cross-sample Consistency Regularization) to address feature splitting and absorption issues in Sparse Autoencoders by encouraging consistent latent assignment across sampl…

View →
cs.LGcs.AIEmpiricalRecentJun 25, 2026

Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders

Nathanaël Jacquier, Maria Vakalopoulou, Mahdi S. Hosseini

This paper introduces two sparsity regularizers for the Top-$k$ sparse autoencoder to improve monosemanticity and robustness.

View →
cs.CVEmpiricalRecentJun 30, 2026

GEAR: Guided End-to-End AutoRegression for Image Synthesis

Bin Lin, Zheyuan Liu, Chenguo Lin, Sixiang Chen +7 more

This paper introduces GEAR, a method for training a vector-quantized tokenizer and an autoregressive generator jointly and end-to-end, resolving the issue of non-differentiable VQ indices.

View →
q-bio.NCcs.LGRecentJun 1, 2026

How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations

William Dorrell

The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…

View →
cs.AIRecentMay 28, 2026

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey +22 more

The paper demonstrates that sparse autoencoders can successfully extract a large set of interpretable, causally influential features from the production-scale Claude 3 Sonnet language model.

View →
cs.LGcs.CLEmpiricalRecentAug 11, 2026

Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders

Nikolai Bolik, Lennart Stöpler, Artur Andrzejak

The authors re-evaluate a previous study on LLM representations using a different similarity measure and find that SAE activation sets do not recover human category boundaries or typicality as effecti…

View →
cs.AIEmpiricalRecentOct 16, 2026

Beyond SAEs: Consistent Concept Discovery with Sparse Coding

Jinho Choi, Hyesu Lim, Jaegul Choo, Steffen Schneider

The paper proposes Consistent Sparse Dictionary Learning (ConSDL) to improve the reliability and reproducibility of sparse autoencoders.

View →
cs.CVEmpiricalRecentJun 12, 2026

RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space

Xichen Pan, Aashu Singh, Satya Narayan Shukla, Xiangjun Fan +2 more

This paper presents RepFusion, a method that uses multimodal language models as noisy representation encoders to improve text-to-image synthesis.

View →
cs.LGcs.AIRecentMay 27, 2026

Learning Compositional Latent Structure with Vector Networks

Niclas Pokel, Benjamin F. Grewe

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

View →
cs.SDcs.LGEmpiricalRecentJun 11, 2026

Generative Modeling of Bach-Style Symbolic Music: A Comparative Study of Autoregressive, Latent-Variable, and Adversarial Approaches

Kyuil Lee, Dezhi Yu, Yongkang Huang

This paper compares three generative models for Bach-style piano music and their strengths and weaknesses.

View →