20 results for “Variational autoencoders”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
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…
This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.
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.
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.
This paper proposes a method for improving the reconstruction of heard speech from non-invasive EEG using contrastive learning and variational regularization.
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.
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.
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…
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…
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…
This paper introduces two sparsity regularizers for the Top-$k$ sparse autoencoder to improve monosemanticity and robustness.
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.
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…
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.
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…
The paper proposes Consistent Sparse Dictionary Learning (ConSDL) to improve the reliability and reproducibility of sparse autoencoders.
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.
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…
This paper compares three generative models for Bach-style piano music and their strengths and weaknesses.