{"total":72,"rows":[{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233,"area":null},{"id":"2102.13451","title":"FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout","created":"2021-02-26","cited_by_count":192,"area":null},{"id":"2305.15391","title":"A Neural Space-Time Representation for Text-to-Image Personalization","created":"2023-05-24","cited_by_count":123,"area":null},{"id":"2311.11696","title":"Sparse Low-rank Adaptation of Pre-trained Language Models","created":"2023-11-20","cited_by_count":96,"area":null},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2104.13766","title":"Boosting Co-teaching with Compression Regularization for Label Noise","created":"2021-04-28","cited_by_count":31,"area":null},{"id":"2302.05927","title":"Transfer Learning for Bayesian Optimization: A Survey","created":"2023-02-12","cited_by_count":27,"area":null},{"id":"2503.08685","title":"\"Principal Components\" Enable A New Language of Images","created":"2025-03-11","cited_by_count":27,"area":null},{"id":"2102.02913","title":"Progressive Neural Image Compression with Nested Quantization and Latent Ordering","created":"2021-02-04","cited_by_count":24,"area":null},{"id":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2102.12810","title":"Hyperparameter Transfer Learning with Adaptive Complexity","created":"2021-02-25","cited_by_count":17,"area":null},{"id":"2501.03992","title":"NeuralSVG: An Implicit Representation for Text-to-Vector Generation","created":"2025-01-07","cited_by_count":17,"area":null},{"id":"2602.04215","title":"OAT: Ordered Action Tokenization","created":"2026-02-04","cited_by_count":15,"area":null},{"id":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2210.16105","title":"Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout","created":"2022-10-28","cited_by_count":12,"area":null},{"id":"2102.11495","title":"Anytime Sampling for Autoregressive Models via Ordered Autoencoding","created":"2021-02-23","cited_by_count":11,"area":null},{"id":"2404.13649","title":"Distributional Principal Autoencoders","created":"2024-04-21","cited_by_count":11,"area":null},{"id":"2409.17978","title":"HydraViT: Stacking Heads for a Scalable ViT","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2507.07997","title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization","created":"2025-07-10","cited_by_count":9,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2406.13046","title":"Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates","created":"2024-06-18","cited_by_count":8,"area":null},{"id":"2512.16975","title":"InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2206.13140","title":"Compressing Features for Learning with Noisy Labels","created":"2022-06-27","cited_by_count":7,"area":null},{"id":"2407.21139","title":"Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2212.04084","title":"Federated Learning for Inference at Anytime and Anywhere","created":"2022-12-08","cited_by_count":6,"area":null},{"id":"2502.04850","title":"Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks","created":"2025-02-07","cited_by_count":6,"area":null},{"id":"2601.01535","title":"Improving Flexible Image Tokenizers for Autoregressive Image Generation","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2401.02993","title":"ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion","created":"2024-01-04","cited_by_count":5,"area":null},{"id":"2603.06449","title":"CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization","created":"2026-03-06","cited_by_count":5,"area":null},{"id":"2101.11353","title":"Variational Nested Dropout","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2502.00382","title":"Masked Generative Nested Transformers with Decode Time Scaling","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2603.17995","title":"LoST: Level of Semantics Tokenization for 3D Shapes","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2604.27796","title":"Post-Optimization Adaptive Rank Allocation for LoRA","created":"2026-04-30","cited_by_count":4,"area":null},{"id":"2207.06924","title":"Learning Representations for CSI Adaptive Quantization and Feedback","created":"2022-07-13","cited_by_count":3,"area":null},{"id":"2305.11213","title":"Information-Ordered Bottlenecks for Adaptive Semantic Compression","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2607.21670","title":"Ordered Action Tokens for Visuomotor Policy Learning","created":"2026-07-23","cited_by_count":3,"area":null},{"id":"2601.19179","title":"PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2602.06418","title":"Adaptive Protein Tokenization","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2601.14246","title":"Soft Tail-dropping for Adaptive Visual Tokenization","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2603.07357","title":"Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2603.19234","title":"Matryoshka Gaussian Splatting","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.15453","title":"(1D) Ordered Tokens Enable Efficient Test-Time Search","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2606.07185","title":"AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.19408","title":"FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.30940","title":"Motion Planning in Compressed Representation Spaces","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.26278","title":"FloDR: An invertible dimensionality reduction method based on a normalising flow","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2609.01740","title":"ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.31620","title":"FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2305.16043","title":"Ordered and Binary Speaker Embedding","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2308.01609","title":"Feature Noise Boosts DNN Generalization under Label Noise","created":"2023-08-03","cited_by_count":0,"area":null},{"id":"2405.13374","title":"Collaboration of Teachers for Semi-supervised Object Detection","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2602.06940","title":"From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2605.09160","title":"Objective-Specific Privileged Bases via Full-Prefix Matryoshka Learning","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.12491","title":"Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.22677","title":"Slimmable ConvNeXt: Width-Adaptive Inference for Efficient Multi-Device Deployment","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.26089","title":"Channel-wise Vector Quantization","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.03314","title":"TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.13957","title":"High-Fidelity Video Compression based on Invertible Neural Transform and Implicit Conditioning","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.25232","title":"Semantic Allocation in Ordered Bottlenecks: Predictive Residual Inference for Visual Representation Learning","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.26106","title":"ScalablePromptus: Scalable and High-Fidelity Prompt-Based Video Streaming","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.16591","title":"FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.30755","title":"Training-Free Bottleneck Width Planning for Convolutional Autoencoders","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.34860","title":"Attention-based Hierarchical Variational Information Bottleneck for Robust Multi-Agent Communication under Variable Bandwidth","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35769","title":"Telescopic Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.15515","title":"Semantically Steerable Image Tokenization","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16552","title":"Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19966","title":"Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}