{"total":168,"rows":[{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752,"area":null},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252,"area":null},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112,"area":null},{"id":"2106.01899","title":"Adversarially Adaptive Normalization for Single Domain Generalization","created":"2021-06-01","cited_by_count":85,"area":null},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2410.16499","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects","created":"2024-10-21","cited_by_count":69,"area":null},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59,"area":null},{"id":"2206.00216","title":"THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption","created":"2022-06-01","cited_by_count":57,"area":null},{"id":"2604.12946","title":"Parcae: Scaling Laws For Stable Looped Language Models","created":"2026-04-14","cited_by_count":55,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2312.09570","title":"CAGE: Controllable Articulation GEneration","created":"2023-12-15","cited_by_count":52,"area":null},{"id":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"area":null},{"id":"2403.02241","title":"Neural Redshift: Random Networks are not Random Functions","created":"2024-03-04","cited_by_count":43,"area":null},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2203.16102","title":"Continual Normalization: Rethinking Batch Normalization for Online Continual Learning","created":"2022-03-30","cited_by_count":40,"area":null},{"id":"2311.09847","title":"Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model","created":"2023-11-16","cited_by_count":40,"area":null},{"id":"2308.04047","title":"SODFormer: Streaming Object Detection with Transformer Using Events and Frames","created":"2023-08-08","cited_by_count":39,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35,"area":null},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34,"area":null},{"id":"2408.08345","title":"5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks","created":"2024-08-15","cited_by_count":34,"area":null},{"id":"2305.02582","title":"On the Expressivity Role of LayerNorm in Transformers' Attention","created":"2023-05-04","cited_by_count":33,"area":null},{"id":"2406.13597","title":"GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks","created":"2024-06-19","cited_by_count":32,"area":null},{"id":"2305.14858","title":"Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers","created":"2023-05-24","cited_by_count":30,"area":null},{"id":"2310.13088","title":"Sequence Length Independent Norm-Based Generalization Bounds for Transformers","created":"2023-10-19","cited_by_count":29,"area":null},{"id":"2306.04226","title":"Normalization Layers Are All That Sharpness-Aware Minimization Needs","created":"2023-06-07","cited_by_count":27,"area":null},{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2308.10305","title":"Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video","created":"2023-08-20","cited_by_count":25,"area":null},{"id":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"area":null},{"id":"2105.07205","title":"Rethinking Skip Connection with Layer Normalization in Transformers and ResNets","created":"2021-05-15","cited_by_count":22,"area":null},{"id":"2301.09479","title":"Modality-Agnostic Variational Compression of Implicit Neural Representations","created":"2023-01-23","cited_by_count":22,"area":null},{"id":"2404.00473","title":"Privacy Backdoors: Stealing Data with Corrupted Pretrained Models","created":"2024-03-30","cited_by_count":22,"area":null},{"id":"2502.12677","title":"Spiking Vision Transformer with Saccadic Attention","created":"2025-02-18","cited_by_count":21,"area":null},{"id":"2208.00553","title":"Search for or Navigate to? Dual Adaptive Thinking for Object Navigation","created":"2022-08-01","cited_by_count":20,"area":null},{"id":"2211.08682","title":"Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models","created":"2022-11-16","cited_by_count":19,"area":null},{"id":"2311.15010","title":"Adapter is All You Need for Tuning Visual Tasks","created":"2023-11-25","cited_by_count":19,"area":null},{"id":"2412.06234","title":"Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction","created":"2024-12-09","cited_by_count":18,"area":null},{"id":"2206.00330","title":"B2T Connection: Serving Stability and Performance in Deep Transformers","created":"2022-06-01","cited_by_count":16,"area":null},{"id":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2210.04172","title":"A Transformer-based deep neural network model for SSVEP classification","created":"2022-10-09","cited_by_count":14,"area":null},{"id":"2308.12538","title":"Mutual-Guided Dynamic Network for Image Fusion","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2405.03728","title":"Pretrained Optimization Model for Zero-Shot Black Box Optimization","created":"2024-05-06","cited_by_count":13,"area":null},{"id":"2512.10938","title":"Stronger Normalization-Free Transformers","created":"2025-12-11","cited_by_count":13,"area":null},{"id":"2210.05153","title":"Understanding the Failure of Batch Normalization for Transformers in NLP","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2306.14834","title":"Scalable Neural Contextual Bandit for Recommender Systems","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2308.06692","title":"SimMatchV2: Semi-Supervised Learning with Graph Consistency","created":"2023-08-13","cited_by_count":12,"area":null},{"id":"2506.22696","title":"Residual Matrix Transformers: Scaling the Size of the Residual Stream","created":"2025-06-28","cited_by_count":12,"area":null},{"id":"2201.06714","title":"AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization","created":"2022-01-18","cited_by_count":11,"area":null},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2112.02624","title":"Dynamic Token Normalization Improves Vision Transformers","created":"2021-12-05","cited_by_count":10,"area":null},{"id":"2203.16369","title":"Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2410.09344","title":"DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models","created":"2024-10-12","cited_by_count":10,"area":null},{"id":"2506.16961","title":"Reversing Flow for Image Restoration","created":"2025-06-20","cited_by_count":10,"area":null},{"id":"2112.00532","title":"FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks","created":"2021-12-01","cited_by_count":9,"area":null},{"id":"2302.01327","title":"Dual PatchNorm","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2401.12743","title":"Correlation-Embedded Transformer Tracking: A Single-Branch Framework","created":"2024-01-23","cited_by_count":9,"area":null},{"id":"2406.01255","title":"On the Nonlinearity of Layer Normalization","created":"2024-06-03","cited_by_count":9,"area":null},{"id":"2111.12143","title":"Critical Initialization of Wide and Deep Neural Networks through Partial Jacobians: General Theory and Applications","created":"2021-11-23","cited_by_count":8,"area":null},{"id":"2210.11049","title":"How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2308.11290","title":"ShadowNet for Data-Centric Quantum System Learning","created":"2023-08-22","cited_by_count":8,"area":null},{"id":"2411.06959","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2510.15262","title":"Robust Layerwise Scaling Rules by Proper Weight Decay Tuning","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2208.01313","title":"Unified Normalization for Accelerating and Stabilizing Transformers","created":"2022-08-02","cited_by_count":6,"area":null},{"id":"2307.10550","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer","created":"2023-07-20","cited_by_count":6,"area":null},{"id":"2312.00313","title":"Improving Normalization with the James-Stein Estimator","created":"2023-12-01","cited_by_count":6,"area":null},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2511.20258","title":"Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2108.01110","title":"Batch Normalization Preconditioning for Neural Network Training","created":"2021-08-02","cited_by_count":5,"area":null},{"id":"2210.05610","title":"MTet: Multi-domain Translation for English and Vietnamese","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2302.14470","title":"Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision","created":"2023-02-28","cited_by_count":5,"area":null},{"id":"2307.05946","title":"A Bayesian approach to quantifying uncertainties and improving generalizability in traffic prediction models","created":"2023-07-12","cited_by_count":5,"area":null},{"id":"2501.16373","title":"Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseases","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2502.04521","title":"Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstruction","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2502.09928","title":"Deep Tree Tensor Networks","created":"2025-02-14","cited_by_count":5,"area":null},{"id":"2504.19646","title":"xEdgeFace: Efficient Cross-Spectral Face Recognition for Edge Devices","created":"2025-04-28","cited_by_count":5,"area":null},{"id":"2510.16474","title":"SCALAR: Self-Calibrating Adaptive Latent Attention Representation Learning","created":"2025-10-18","cited_by_count":5,"area":null},{"id":"2208.06496","title":"Orthogonal Gated Recurrent Unit with Neumann-Cayley Transformation","created":"2022-08-12","cited_by_count":4,"area":null},{"id":"2309.12931","title":"On Separate Normalization in Self-supervised Transformers","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2310.01704","title":"Transformers are efficient hierarchical chemical graph learners","created":"2023-10-02","cited_by_count":4,"area":null},{"id":"2403.20284","title":"LayerNorm: A key component in parameter-efficient fine-tuning","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2410.00232","title":"Preconditioning for Accelerated Gradient Descent Optimization and Regularization","created":"2024-09-30","cited_by_count":4,"area":null},{"id":"2505.24293","title":"Equivalent Linear Mappings of Large Language Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2202.12411","title":"TrimBERT: Tailoring BERT for Trade-offs","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2205.15146","title":"Batch Normalization Is Blind to the First and Second Derivatives of the Loss","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2209.08898","title":"Batch Layer Normalization, A new normalization layer for CNNs and RNN","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2302.10144","title":"Stabilising and accelerating light gated recurrent units for automatic speech recognition","created":"2023-02-16","cited_by_count":3,"area":null},{"id":"2305.09312","title":"Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2401.16462","title":"Supervised Contrastive Learning based Dual-Mixer Model for Remaining Useful Life Prediction","created":"2024-01-29","cited_by_count":3,"area":null},{"id":"2409.12965","title":"Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2410.22448","title":"A Closer Look at Neural Codec Resynthesis: Bridging the Gap between Codec and Waveform Generation","created":"2024-10-29","cited_by_count":3,"area":null},{"id":"2502.18277","title":"Self-Adjust Softmax","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2506.07863","title":"VIVAT: Virtuous Improving VAE Training through Artifact Mitigation","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2508.07577","title":"Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification","created":"2025-08-11","cited_by_count":3,"area":null},{"id":"2604.02320","title":"Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining","created":"2026-04-02","cited_by_count":3,"area":null},{"id":"2108.00439","title":"Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach","created":"2021-08-01","cited_by_count":2,"area":null},{"id":"2207.01972","title":"Understanding and Improving Group Normalization","created":"2022-07-05","cited_by_count":2,"area":null}],"next_cursor":"100"}