{"total":83,"rows":[{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027,"area":null},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2112.06749","title":"Step-unrolled Denoising Autoencoders for Text Generation","created":"2021-12-13","cited_by_count":102,"area":null},{"id":"2305.08842","title":"Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks","created":"2023-05-15","cited_by_count":82,"area":null},{"id":"2205.07547","title":"SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization","created":"2022-05-16","cited_by_count":68,"area":null},{"id":"2204.09269","title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","created":"2022-04-20","cited_by_count":64,"area":null},{"id":"2205.07459","title":"Directed Acyclic Transformer for Non-Autoregressive Machine Translation","created":"2022-05-16","cited_by_count":44,"area":null},{"id":"2305.18378","title":"Disentanglement via Latent Quantization","created":"2023-05-28","cited_by_count":40,"area":null},{"id":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","cited_by_count":31,"area":null},{"id":"2206.05975","title":"On the Learning of Non-Autoregressive Transformers","created":"2022-06-13","cited_by_count":27,"area":null},{"id":"2401.00365","title":"HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes","created":"2023-12-31","cited_by_count":27,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2103.11405","title":"Non-Autoregressive Translation by Learning Target Categorical Codes","created":"2021-03-21","cited_by_count":25,"area":null},{"id":"2105.15053","title":"Factorising Meaning and Form for Intent-Preserving Paraphrasing","created":"2021-05-31","cited_by_count":22,"area":null},{"id":"2204.02030","title":"$\\textit{latent}$-GLAT: Glancing at Latent Variables for Parallel Text Generation","created":"2022-04-05","cited_by_count":20,"area":null},{"id":"2205.14333","title":"One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2106.08122","title":"Sequence-Level Training for Non-Autoregressive Neural Machine Translation","created":"2021-06-15","cited_by_count":18,"area":null},{"id":"2209.01425","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","created":"2022-09-03","cited_by_count":17,"area":null},{"id":"2404.11499","title":"A Data-Driven Representation for Sign Language Production","created":"2024-04-17","cited_by_count":17,"area":null},{"id":"2210.03953","title":"Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation","created":"2022-10-08","cited_by_count":16,"area":null},{"id":"2308.05396","title":"Learning Gabor Texture Features for Fine-Grained Recognition","created":"2023-08-10","cited_by_count":16,"area":null},{"id":"2310.05718","title":"EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders","created":"2023-10-09","cited_by_count":16,"area":null},{"id":"2207.06366","title":"N-Grammer: Augmenting Transformers with latent n-grams","created":"2022-07-13","cited_by_count":14,"area":null},{"id":"2101.08942","title":"Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translation","created":"2021-01-22","cited_by_count":13,"area":null},{"id":"2210.05193","title":"Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation","created":"2022-10-11","cited_by_count":13,"area":null},{"id":"2305.03462","title":"General Neural Gauge Fields","created":"2023-05-05","cited_by_count":12,"area":null},{"id":"2305.19744","title":"Neural Markov Jump Processes","created":"2023-05-31","cited_by_count":12,"area":null},{"id":"2205.01966","title":"Non-Autoregressive Machine Translation: It's Not as Fast as it Seems","created":"2022-05-04","cited_by_count":11,"area":null},{"id":"2210.06007","title":"JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAE","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2208.10497","title":"Are disentangled representations all you need to build speaker anonymization systems?","created":"2022-08-22","cited_by_count":10,"area":null},{"id":"2306.07735","title":"Discrete Graph Auto-Encoder","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2310.03004","title":"Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization","created":"2023-10-04","cited_by_count":10,"area":null},{"id":"2411.16550","title":"Representation Collapsing Problems in Vector Quantization","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2109.04411","title":"Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2107.13132","title":"Unsupervised Learning of Neurosymbolic Encoders","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2405.07663","title":"Sign Stitching: A Novel Approach to Sign Language Production","created":"2024-05-13","cited_by_count":8,"area":null},{"id":"2407.12665","title":"Beyond Next Token Prediction: Patch-Level Training for Large Language Models","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2501.16811","title":"Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2207.10833","title":"Few-shot Image Generation Using Discrete Content Representation","created":"2022-07-22","cited_by_count":6,"area":null},{"id":"2210.11017","title":"Multi-Granularity Optimization for Non-Autoregressive Translation","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2412.00740","title":"Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer","created":"2024-12-01","cited_by_count":6,"area":null},{"id":"2108.08447","title":"MvSR-NAT: Multi-view Subset Regularization for Non-Autoregressive Machine Translation","created":"2021-08-19","cited_by_count":5,"area":null},{"id":"2103.12328","title":"Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrieval","created":"2021-03-23","cited_by_count":4,"area":null},{"id":"2207.03777","title":"Hidden Schema Networks","created":"2022-07-08","cited_by_count":4,"area":null},{"id":"2211.01292","title":"Learning an Artificial Language for Knowledge-Sharing in Multilingual Translation","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2306.07764","title":"Tokenization with Factorized Subword Encoding","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2311.07941","title":"Non-autoregressive Machine Translation with Probabilistic Context-free Grammar","created":"2023-11-14","cited_by_count":4,"area":null},{"id":"2407.04939","title":"Balance of Number of Embedding and their Dimensions in Vector Quantization","created":"2024-07-06","cited_by_count":4,"area":null},{"id":"2603.25340","title":"Large Language Model as Token Compressor and Decompressor","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2110.04005","title":"KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2110.12539","title":"Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech","created":"2021-10-24","cited_by_count":3,"area":null},{"id":"2203.16266","title":"DePA: Improving Non-autoregressive Machine Translation with Dependency-Aware Decoder","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2204.13355","title":"Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints","created":"2022-04-28","cited_by_count":3,"area":null},{"id":"2210.10416","title":"Hybrid-Regressive Neural Machine Translation","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2211.16863","title":"Rephrasing the Reference for Non-Autoregressive Machine Translation","created":"2022-11-30","cited_by_count":3,"area":null},{"id":"2105.00602","title":"OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning","created":"2021-05-03","cited_by_count":2,"area":null},{"id":"2407.10462","title":"BandCondiNet: Parallel Transformers-based Conditional Popular Music Generation with Multi-View Features","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2101.09698","title":"Fast Sequence Generation with Multi-Agent Reinforcement Learning","created":"2021-01-24","cited_by_count":1,"area":null},{"id":"2201.10936","title":"FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control","created":"2022-01-26","cited_by_count":1,"area":null},{"id":"2212.09450","title":"Accelerating Antimicrobial Peptide Discovery with Latent Structure","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2303.14011","title":"SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization","created":"2023-03-24","cited_by_count":1,"area":null},{"id":"2310.09876","title":"Bounding and Filling: A Fast and Flexible Framework for Image Captioning","created":"2023-10-15","cited_by_count":1,"area":null},{"id":"2310.19322","title":"Progressive Neural Network for Multi-Horizon Time Series Forecasting","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2405.12788","title":"What Have We Achieved on Non-autoregressive Translation?","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2406.09676","title":"Optimizing Byte-level Representation for End-to-end ASR","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2409.14851","title":"Disentanglement with Factor Quantized Variational Autoencoders","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2506.23703","title":"A New Perspective On AI Safety Through Control Theory Methodologies","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2603.26782","title":"Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2605.21195","title":"RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2108.12522","title":"Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP","created":"2021-08-27","cited_by_count":0,"area":null},{"id":"2111.08453","title":"Entropy optimized semi-supervised decomposed vector-quantized variational autoencoder model based on transfer learning for multiclass text classification and generation","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2203.08080","title":"Implicit Feature Decoupling with Depthwise Quantization","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2203.09518","title":"Privacy-Preserving Speech Representation Learning using Vector Quantization","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2211.03616","title":"Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2302.07950","title":"Self-Organising Neural Discrete Representation Learning \\`a la Kohonen","created":"2023-02-15","cited_by_count":0,"area":null},{"id":"2308.15003","title":"Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2402.09725","title":"Improving Non-autoregressive Machine Translation with Error Exposure and Consistency Regularization","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2503.07506","title":"ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2507.15386","title":"Learning to Gridize: Segment Physical World by Wireless Communication Channel","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2510.13331","title":"Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2605.13517","title":"ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.01353","title":"Spatial-Temporal Expert Learning for Video-based Person Re-identification","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.05148","title":"Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":null}