{"total":46,"rows":[{"id":"2312.04501","title":"Graph Metanetworks for Processing Diverse Neural Architectures","created":"2023-12-07","cited_by_count":57,"area":null},{"id":"2404.01547","title":"Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining","created":"2024-04-02","cited_by_count":54,"area":null},{"id":"2406.09997","title":"Towards Scalable and Versatile Weight Space Learning","created":"2024-06-14","cited_by_count":41,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2405.20231","title":"The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof","created":"2024-05-30","cited_by_count":21,"area":null},{"id":"2310.17653","title":"Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model","created":"2023-10-26","cited_by_count":19,"area":null},{"id":"2404.00498","title":"94% on CIFAR-10 in 3.29 Seconds on a Single GPU","created":"2024-03-30","cited_by_count":16,"area":null},{"id":"2312.00379","title":"Optimal Sample Complexity of Contrastive Learning","created":"2023-12-01","cited_by_count":15,"area":null},{"id":"2401.01764","title":"Understanding the Detrimental Class-level Effects of Data Augmentation","created":"2023-12-07","cited_by_count":13,"area":null},{"id":"2402.04051","title":"Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods","created":"2024-02-06","cited_by_count":9,"area":null},{"id":"2312.09832","title":"Disentangling Linear Mode-Connectivity","created":"2023-12-15","cited_by_count":8,"area":null},{"id":"2403.18955","title":"Structurally Prune Anything: Any Architecture, Any Framework, Any Time","created":"2024-03-03","cited_by_count":8,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2403.07968","title":"Do Deep Neural Network Solutions Form a Star Domain?","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","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":"2311.03386","title":"A Simple and Efficient Baseline for Data Attribution on Images","created":"2023-11-03","cited_by_count":5,"area":null},{"id":"2402.17863","title":"Vision Transformers with Natural Language Semantics","created":"2024-02-27","cited_by_count":5,"area":null},{"id":"2405.16493","title":"Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2311.03233","title":"Navigating Scaling Laws: Compute Optimality in Adaptive Model Training","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2407.13841","title":"Many Perception Tasks are Highly Redundant Functions of their Input Data","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2510.05684","title":"D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI","created":"2025-10-07","cited_by_count":4,"area":null},{"id":"2310.03149","title":"Attributing Learned Concepts in Neural Networks to Training Data","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2310.07555","title":"Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configuration","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2312.15088","title":"Adaptive Domain Inference Attack with Concept Hierarchy","created":"2023-12-22","cited_by_count":3,"area":null},{"id":"2404.10386","title":"I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2502.04121","title":"First-Passage Approach to Optimizing Perturbations for Improved Training of Machine Learning Models","created":"2025-02-06","cited_by_count":3,"area":null},{"id":"2511.14440","title":"Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2311.08525","title":"Efficient Rotation Invariance in Deep Neural Networks through Artificial Mental Rotation","created":"2023-11-14","cited_by_count":2,"area":null},{"id":"2404.00509","title":"DailyMAE: Towards Pretraining Masked Autoencoders in One Day","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2406.12368","title":"MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2502.16733","title":"Coreset Selection via LLM-based Concept Bottlenecks","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2602.03766","title":"FOVI: A biologically-inspired foveated interface for deep vision models","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2404.12330","title":"A Perspective on Deep Vision Performance with Standard Image and Video Codecs","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2406.02773","title":"Cyclic Sparse Training: Is it Enough?","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2410.06878","title":"Noise is All You Need: Private Second-Order Convergence of Noisy SGD","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2410.22651","title":"FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participation","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2506.20686","title":"MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2501.13718","title":"A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation","created":"2025-01-23","cited_by_count":0,"area":null},{"id":"2503.03401","title":"Evolutionary Prediction Games","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.21061","title":"Neural Architecture Search by Learning a Hierarchical Search Space","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2506.06235","title":"Optimizing Cloud-to-GPU Throughput for Deep Learning With Earth Observation Data","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2602.22434","title":"GetBatch: Distributed Multi-Object Retrieval for ML Data Loading","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2605.08731","title":"Choosing a JPEG Decoder for PyTorch DataLoaders: Workload-Specific Throughput on Four CPUs","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.25134","title":"Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate","created":"2026-05-24","cited_by_count":0,"area":null}],"next_cursor":null}