{"total":98,"rows":[{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109,"area":null},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327,"area":"diffusion"},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2402.19449","title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models","created":"2024-02-29","cited_by_count":80,"area":null},{"id":"2310.13355","title":"SILC: Improving Vision Language Pretraining with Self-Distillation","created":"2023-10-20","cited_by_count":66,"area":"mllm"},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2309.08586","title":"Replacing softmax with ReLU in Vision Transformers","created":"2023-09-15","cited_by_count":44,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2406.09415","title":"An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels","created":"2024-06-13","cited_by_count":33,"area":null},{"id":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2206.15369","title":"No Reason for No Supervision: Improved Generalization in Supervised Models","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2301.11323","title":"Joint Training of Deep Ensembles Fails Due to Learner Collusion","created":"2023-01-26","cited_by_count":23,"area":null},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23,"area":null},{"id":"2210.07224","title":"Exploring Long-Sequence Masked Autoencoders","created":"2022-10-13","cited_by_count":22,"area":null},{"id":"2301.13195","title":"Adaptive Computation with Elastic Input Sequence","created":"2023-01-30","cited_by_count":22,"area":null},{"id":"2211.10686","title":"Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Network","created":"2022-11-19","cited_by_count":19,"area":null},{"id":"2211.16421","title":"RGB no more: Minimally-decoded JPEG Vision Transformers","created":"2022-11-29","cited_by_count":18,"area":null},{"id":"2310.13807","title":"Learning to (Learn at Test Time)","created":"2023-10-20","cited_by_count":17,"area":null},{"id":"2304.06028","title":"RECLIP: Resource-efficient CLIP by Training with Small Images","created":"2023-04-12","cited_by_count":16,"area":null},{"id":"2401.12033","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","created":"2024-01-22","cited_by_count":14,"area":null},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2504.04708","title":"SapiensID: Foundation for Human Recognition","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2403.10519","title":"Frozen Feature Augmentation for Few-Shot Image Classification","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2405.15018","title":"What Variables Affect Out-of-Distribution Generalization in Pretrained Models?","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2411.00715","title":"B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2207.05843","title":"A new hope for network model generalization","created":"2022-07-12","cited_by_count":11,"area":null},{"id":"2404.07292","title":"Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers","created":"2024-04-10","cited_by_count":11,"area":null},{"id":"2410.19964","title":"Understanding Adam Requires Better Rotation Dependent Assumptions","created":"2024-10-25","cited_by_count":11,"area":null},{"id":"2502.10691","title":"Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning","created":"2025-02-15","cited_by_count":11,"area":null},{"id":"2303.17376","title":"A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2405.13985","title":"LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2502.07503","title":"Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2302.01327","title":"Dual PatchNorm","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2412.11768","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","created":"2024-12-16","cited_by_count":8,"area":null},{"id":"2502.06785","title":"DeepCrossAttention: Supercharging Transformer Residual Connections","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2312.02843","title":"Are Vision Transformers More Data Hungry Than Newborn Visual Systems?","created":"2023-12-05","cited_by_count":7,"area":null},{"id":"2405.10284","title":"Quantum Vision Transformers for Quark-Gluon Classification","created":"2024-05-16","cited_by_count":7,"area":null},{"id":"2406.16540","title":"Improving robustness to corruptions with multiplicative weight perturbations","created":"2024-06-24","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":"2402.18508","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2407.08567","title":"Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2408.08258","title":"Snuffy: Efficient Whole Slide Image Classifier","created":"2024-08-15","cited_by_count":6,"area":null},{"id":"2502.00571","title":"Contrastive Forward-Forward: A Training Algorithm of Vision Transformer","created":"2025-02-01","cited_by_count":6,"area":null},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2503.21305","title":"DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2311.02803","title":"Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2401.12511","title":"Convolutional Initialization for Data-Efficient Vision Transformers","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2403.13731","title":"Emotion Recognition Using Transformers with Masked Learning","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2410.21275","title":"Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2311.09350","title":"Generalizable Imitation Learning Through Pre-Trained Representations","created":"2023-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2402.14385","title":"WindDragon: Enhancing wind power forecasting with Automated Deep Learning","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2405.03089","title":"Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Composition","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2410.04941","title":"TOAST: Transformer Optimization using Adaptive and Simple Transformations","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2410.18267","title":"Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2502.12511","title":"Myna: Masking-Based Contrastive Learning of Musical Representations","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2502.18153","title":"SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2504.10231","title":"A Model Zoo of Vision Transformers","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2510.25244","title":"BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2606.09646","title":"How Do Video Foundation Models Encode Intuitive Physics? Probing Across Pretraining Paradigms","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2403.15010","title":"Clean-image Backdoor Attacks","created":"2024-03-22","cited_by_count":2,"area":null},{"id":"2412.18675","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","created":"2024-12-24","cited_by_count":2,"area":"mllm"},{"id":"2503.13724","title":"Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2504.06738","title":"EDIT: Enhancing Vision Transformers by Mitigating Attention Sink through an Encoder-Decoder Architecture","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2504.11083","title":"QAMA: Scalable Quantum Annealing Multi-Head Attention Operator for Deep Learning","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2602.03001","title":"Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2305.04961","title":"Joint Moment Retrieval and Highlight Detection Via Natural Language Queries","created":"2023-05-08","cited_by_count":1,"area":null},{"id":"2401.06898","title":"Always-Sparse Training by Growing Connections with Guided Stochastic Exploration","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2505.02075","title":"Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2510.25480","title":"Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2512.08217","title":"Correction of Decoupled Weight Decay","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2605.30126","title":"PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding","created":"2026-05-28","cited_by_count":1,"area":"mllm"},{"id":"2607.26001","title":"Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2303.03340","title":"Symbolic Synthesis of Neural Networks","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2303.14096","title":"Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2306.10959","title":"RaViTT: Random Vision Transformer Tokens","created":"2023-06-19","cited_by_count":0,"area":null},{"id":"2312.16339","title":"Universal Pyramid Adversarial Training for Improved ViT Performance","created":"2023-12-26","cited_by_count":0,"area":null},{"id":"2403.08024","title":"xMLP: Revolutionizing Private Inference with Exclusive Square Activation","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2403.13677","title":"Retina Vision Transformer (RetinaViT): Introducing Scaled Patches into Vision Transformers","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2406.09185","title":"Thoracic Surgery Video Analysis for Surgical Phase Recognition","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2502.06268","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2512.03862","title":"Diminishing Returns in Self-Supervised Learning","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.10402","title":"The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.15506","title":"ViT Registers and Fractal ViT","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.02142","title":"When Bigger is Worse: A Practitioner's Guide to Model Selection Under Data Scarcity","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.10021","title":"Masked Contrastive Pre-Training Improves Music Audio Key Detection","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2605.24789","title":"Self-Supervised Contrastive Learning for Cardiac MR Sequence Classification","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.27144","title":"Is an Image Also Worth 16x16=256 Superpixels? A Framework for Attentional Image Classification","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.29823","title":"Quantifying and Optimizing Simplicity via Polynomial Representations","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.07558","title":"Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.12881","title":"Inhibited Self-Attention: Sharpening Focus in Vision Transformers","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.00831","title":"FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.32899","title":"Rethinking the Fully Hyperbolic Vision Transformer in Polar Coordinates","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.04147","title":"You May Be Running the Wrong Inception Crop","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}