{"total":612,"rows":[{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636,"area":"diffusion"},{"id":"2105.04668","title":"HuMoR: 3D Human Motion Model for Robust Pose Estimation","created":"2021-05-10","cited_by_count":324,"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":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225,"area":"mechinterp"},{"id":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192,"area":null},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187,"area":null},{"id":"2103.16091","title":"Symbolic Music Generation with Diffusion Models","created":"2021-03-30","cited_by_count":154,"area":"diffusion"},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151,"area":null},{"id":"2204.06252","title":"What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data","created":"2022-04-13","cited_by_count":138,"area":"offlinerl"},{"id":"2104.00563","title":"Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction","created":"2021-02-19","cited_by_count":131,"area":null},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"2112.06749","title":"Step-unrolled Denoising Autoencoders for Text Generation","created":"2021-12-13","cited_by_count":102,"area":null},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88,"area":null},{"id":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","cited_by_count":84,"area":null},{"id":"2207.12824","title":"Compositional Human-Scene Interaction Synthesis with Semantic Control","created":"2022-07-26","cited_by_count":83,"area":null},{"id":"2104.02330","title":"Visual Alignment Constraint for Continuous Sign Language Recognition","created":"2021-04-06","cited_by_count":80,"area":null},{"id":"2107.02173","title":"Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence","created":"2021-07-05","cited_by_count":74,"area":null},{"id":"2103.03864","title":"Learning to Extend Molecular Scaffolds with Structural Motifs","created":"2021-03-05","cited_by_count":71,"area":null},{"id":"2111.12701","title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","created":"2021-11-24","cited_by_count":71,"area":"diffusion"},{"id":"2101.07965","title":"Directed Acyclic Graph Neural Networks","created":"2021-01-20","cited_by_count":70,"area":null},{"id":"2206.05895","title":"Latent Diffusion Energy-Based Model for Interpretable Text Modeling","created":"2022-06-13","cited_by_count":67,"area":"diffusion"},{"id":"2210.06756","title":"Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features","created":"2022-10-13","cited_by_count":63,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2201.07189","title":"MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Prediction","created":"2022-01-18","cited_by_count":59,"area":null},{"id":"2306.02531","title":"PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model","created":"2023-06-05","cited_by_count":58,"area":"diffusion"},{"id":"2308.16406","title":"CktGNN: Circuit Graph Neural Network for Electronic Design Automation","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2109.15163","title":"HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning","created":"2021-09-30","cited_by_count":57,"area":null},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57,"area":"safety"},{"id":"2301.00537","title":"Posterior Collapse and Latent Variable Non-identifiability","created":"2023-01-02","cited_by_count":57,"area":null},{"id":"2304.00008","title":"On the Creativity of Large Language Models","created":"2023-03-27","cited_by_count":57,"area":null},{"id":"2106.01071","title":"Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection","created":"2021-06-02","cited_by_count":56,"area":null},{"id":"2203.05789","title":"FLAG: Flow-based 3D Avatar Generation from Sparse Observations","created":"2022-03-11","cited_by_count":55,"area":null},{"id":"2105.14859","title":"Consistency Regularization for Variational Auto-Encoders","created":"2021-05-31","cited_by_count":51,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2107.00096","title":"Improving black-box optimization in VAE latent space using decoder uncertainty","created":"2021-06-30","cited_by_count":51,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2211.12717","title":"Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks","created":"2022-11-23","cited_by_count":49,"area":null},{"id":"2105.14761","title":"G-Transformer for Document-level Machine Translation","created":"2021-05-31","cited_by_count":46,"area":null},{"id":"2302.01129","title":"De Novo Molecular Generation via Connection-aware Motif Mining","created":"2023-02-02","cited_by_count":46,"area":null},{"id":"2101.10579","title":"Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs","created":"2021-01-26","cited_by_count":45,"area":null},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"area":null},{"id":"2101.00828","title":"Transformer-based Conditional Variational Autoencoder for Controllable Story Generation","created":"2021-01-04","cited_by_count":44,"area":null},{"id":"2106.01625","title":"Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech","created":"2021-06-03","cited_by_count":42,"area":null},{"id":"2105.04090","title":"MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE","created":"2021-05-10","cited_by_count":40,"area":null},{"id":"2405.09591","title":"A Comprehensive Survey on Data Augmentation","created":"2024-05-15","cited_by_count":40,"area":null},{"id":"2206.03066","title":"Recent Advances for Quantum Neural Networks in Generative Learning","created":"2022-06-07","cited_by_count":39,"area":null},{"id":"2308.07200","title":"Neural Categorical Priors for Physics-Based Character Control","created":"2023-08-14","cited_by_count":38,"area":null},{"id":"2310.08303","title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2202.12350","title":"DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation","created":"2022-02-24","cited_by_count":37,"area":null},{"id":"2105.13010","title":"An error analysis of generative adversarial networks for learning distributions","created":"2021-05-27","cited_by_count":36,"area":null},{"id":"2101.05850","title":"Continual Learning of Knowledge Graph Embeddings","created":"2021-01-14","cited_by_count":35,"area":null},{"id":"2204.13031","title":"DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation","created":"2022-04-27","cited_by_count":35,"area":null},{"id":"2310.11142","title":"BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference","created":"2023-10-17","cited_by_count":35,"area":"diffusion"},{"id":"2110.12091","title":"Contrastively Disentangled Sequential Variational Autoencoder","created":"2021-10-22","cited_by_count":34,"area":null},{"id":"2209.00852","title":"Geometry Aligned Variational Transformer for Image-conditioned Layout Generation","created":"2022-09-02","cited_by_count":33,"area":null},{"id":"2305.04147","title":"Controllable Mixed-Initiative Dialogue Generation through Prompting","created":"2023-05-06","cited_by_count":32,"area":null},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2508.13446","title":"CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models","created":"2025-08-19","cited_by_count":29,"area":"vla"},{"id":"2204.07172","title":"Diagnosing and Fixing Manifold Overfitting in Deep Generative Models","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2208.00638","title":"Composable Text Controls in Latent Space with ODEs","created":"2022-08-01","cited_by_count":28,"area":null},{"id":"2502.13063","title":"Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity","created":"2025-02-18","cited_by_count":28,"area":"inference"},{"id":"2101.09374","title":"Slot Self-Attentive Dialogue State Tracking","created":"2021-01-22","cited_by_count":27,"area":null},{"id":"2103.11070","title":"Attribute Alignment: Controlling Text Generation from Pre-trained Language Models","created":"2021-03-20","cited_by_count":27,"area":null},{"id":"2211.13926","title":"Generative Modeling in Sinogram Domain for Sparse-view CT Reconstruction","created":"2022-11-25","cited_by_count":27,"area":"diffusion"},{"id":"2104.01374","title":"Interpretable Unsupervised Diversity Denoising and Artefact Removal","created":"2021-04-03","cited_by_count":26,"area":null},{"id":"2111.08386","title":"Towards Generating Real-World Time Series Data","created":"2021-11-16","cited_by_count":26,"area":null},{"id":"2203.10299","title":"Neural Machine Translation with Phrase-Level Universal Visual Representations","created":"2022-03-19","cited_by_count":26,"area":null},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25,"area":null},{"id":"2409.12452","title":"Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning","created":"2024-09-19","cited_by_count":25,"area":"lr"},{"id":"2502.01567","title":"Latent Thought Models with Variational Bayes Inference-Time Computation","created":"2025-02-03","cited_by_count":25,"area":"lr"},{"id":"2504.16431","title":"Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion","created":"2025-04-23","cited_by_count":25,"area":"diffusion"},{"id":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2109.01300","title":"How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data","created":"2021-09-03","cited_by_count":24,"area":null},{"id":"2207.02466","title":"GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation","created":"2022-07-06","cited_by_count":24,"area":null},{"id":"2302.05096","title":"Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2209.00517","title":"The Neural Process Family: Survey, Applications and Perspectives","created":"2022-09-01","cited_by_count":23,"area":null},{"id":"2312.15645","title":"Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment","created":"2023-12-25","cited_by_count":23,"area":null},{"id":"2103.01071","title":"A survey on Variational Autoencoders from a GreenAI perspective","created":"2021-03-01","cited_by_count":22,"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":"2107.00110","title":"Classical Planning in Deep Latent Space","created":"2021-06-30","cited_by_count":22,"area":null},{"id":"2203.03463","title":"Hierarchical Sketch Induction for Paraphrase Generation","created":"2022-03-07","cited_by_count":22,"area":null},{"id":"2305.10399","title":"End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics","created":"2023-05-17","cited_by_count":22,"area":"diffusion"},{"id":"2104.01371","title":"Convex Aggregation for Opinion Summarization","created":"2021-04-03","cited_by_count":21,"area":null},{"id":"2104.02726","title":"Creativity and Machine Learning: A Survey","created":"2021-04-06","cited_by_count":21,"area":null},{"id":"2109.03415","title":"Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2109.04999","title":"Fairness without the sensitive attribute via Causal Variational Autoencoder","created":"2021-09-10","cited_by_count":21,"area":null},{"id":"2110.08552","title":"Virtual Augmentation Supported Contrastive Learning of Sentence Representations","created":"2021-10-16","cited_by_count":21,"area":null},{"id":"2310.02807","title":"A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability","created":"2023-10-04","cited_by_count":21,"area":null},{"id":"2401.08358","title":"Hallucination Detection and Hallucination Mitigation: An Investigation","created":"2024-01-16","cited_by_count":21,"area":null},{"id":"2103.00213","title":"Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention","created":"2021-02-27","cited_by_count":20,"area":null},{"id":"2103.00806","title":"Representation Learning for Event-based Visuomotor Policies","created":"2021-03-01","cited_by_count":20,"area":null},{"id":"2203.10304","title":"PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs","created":"2022-03-19","cited_by_count":20,"area":null},{"id":"2207.06130","title":"Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation","created":"2022-07-13","cited_by_count":20,"area":null},{"id":"2210.10243","title":"CLUTR: Curriculum Learning via Unsupervised Task Representation Learning","created":"2022-10-19","cited_by_count":20,"area":null}],"next_cursor":"100"}