{"total":87,"rows":[{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174,"area":null},{"id":"2205.13218","title":"A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning","created":"2022-05-26","cited_by_count":154,"area":null},{"id":"2303.08566","title":"Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning","created":"2023-03-15","cited_by_count":74,"area":null},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73,"area":null},{"id":"2307.09542","title":"Can Neural Network Memorization Be Localized?","created":"2023-07-18","cited_by_count":69,"area":null},{"id":"2203.01825","title":"What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors","created":"2022-03-02","cited_by_count":61,"area":null},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59,"area":null},{"id":"2206.01717","title":"A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features","created":"2022-06-03","cited_by_count":49,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2106.16004","title":"What can linear interpolation of neural network loss landscapes tell us?","created":"2021-06-30","cited_by_count":28,"area":null},{"id":"2105.10585","title":"Properties of the After Kernel","created":"2021-05-21","cited_by_count":27,"area":null},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23,"area":null},{"id":"2211.10844","title":"Learning to Generate Image Embeddings with User-level Differential Privacy","created":"2022-11-20","cited_by_count":23,"area":null},{"id":"2308.02533","title":"Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning","created":"2023-08-01","cited_by_count":23,"area":null},{"id":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","cited_by_count":22,"area":null},{"id":"2307.06966","title":"Layer-wise Linear Mode Connectivity","created":"2023-07-13","cited_by_count":22,"area":null},{"id":"2304.04158","title":"Does Continual Learning Equally Forget All Parameters?","created":"2023-04-09","cited_by_count":18,"area":null},{"id":"2110.05607","title":"Partial Variable Training for Efficient On-Device Federated Learning","created":"2021-10-11","cited_by_count":14,"area":null},{"id":"2206.07311","title":"Can pruning improve certified robustness of neural networks?","created":"2022-06-15","cited_by_count":14,"area":null},{"id":"2310.12408","title":"Provable Guarantees for Neural Networks via Gradient Feature Learning","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2311.05858","title":"Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation","created":"2023-11-10","cited_by_count":14,"area":null},{"id":"2110.03450","title":"Efficient and Private Federated Learning with Partially Trainable Networks","created":"2021-10-06","cited_by_count":13,"area":null},{"id":"2110.03634","title":"Enabling On-Device Training of Speech Recognition Models with Federated Dropout","created":"2021-10-07","cited_by_count":12,"area":null},{"id":"2301.12309","title":"On the Lipschitz Constant of Deep Networks and Double Descent","created":"2023-01-28","cited_by_count":11,"area":null},{"id":"2206.07839","title":"Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2312.14378","title":"Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification","created":"2023-12-22","cited_by_count":10,"area":null},{"id":"2506.23271","title":"Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation","created":"2025-06-29","cited_by_count":10,"area":null},{"id":"2203.03324","title":"Dynamic ConvNets on Tiny Devices via Nested Sparsity","created":"2022-03-07","cited_by_count":8,"area":null},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2403.10650","title":"PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation","created":"2024-03-15","cited_by_count":8,"area":null},{"id":"2507.20057","title":"What Can Grokking Teach Us About Learning Under Nonstationarity?","created":"2025-07-26","cited_by_count":8,"area":null},{"id":"2509.17738","title":"Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking","created":"2025-09-22","cited_by_count":8,"area":null},{"id":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2203.00481","title":"Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks","created":"2022-03-01","cited_by_count":7,"area":null},{"id":"2312.05743","title":"Building Variable-sized Models via Learngene Pool","created":"2023-12-10","cited_by_count":7,"area":null},{"id":"2205.05282","title":"ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning","created":"2022-05-11","cited_by_count":6,"area":null},{"id":"2310.07996","title":"Reset It and Forget It: Relearning Last-Layer Weights Improves Continual and Transfer Learning","created":"2023-10-12","cited_by_count":6,"area":null},{"id":"2405.17081","title":"Effective Layer Pruning Through Similarity Metric Perspective","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2106.07214","title":"Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions","created":"2021-06-14","cited_by_count":5,"area":null},{"id":"2106.10771","title":"Multirate Training of Neural Networks","created":"2021-06-20","cited_by_count":5,"area":null},{"id":"2311.04592","title":"On Characterizing the Evolution of Embedding Space of Neural Networks using Algebraic Topology","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2312.00694","title":"Object Detector Differences when using Synthetic and Real Training Data","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2107.12490","title":"LEGATO: A LayerwisE Gradient AggregaTiOn Algorithm for Mitigating Byzantine Attacks in Federated Learning","created":"2021-07-26","cited_by_count":4,"area":null},{"id":"2112.00407","title":"Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data","created":"2021-12-01","cited_by_count":4,"area":null},{"id":"2301.11360","title":"The Power of Linear Combinations: Learning with Random Convolutions","created":"2023-01-26","cited_by_count":4,"area":null},{"id":"2303.14115","title":"Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2406.02428","title":"Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2405.07527","title":"Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models","created":"2024-05-13","cited_by_count":3,"area":null},{"id":"2410.14470","title":"How Do Training Methods Influence the Utilization of Vision Models?","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2507.11839","title":"Protenix-Mini: Efficient Structure Predictor via Compact Architecture, Few-Step Diffusion and Switchable pLM","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2102.13522","title":"Experiments with Rich Regime Training for Deep Learning","created":"2021-02-26","cited_by_count":2,"area":null},{"id":"2203.07713","title":"LDP: Learnable Dynamic Precision for Efficient Deep Neural Network Training and Inference","created":"2022-03-15","cited_by_count":2,"area":null},{"id":"2203.12091","title":"FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2212.04461","title":"Leveraging Unlabeled Data to Track Memorization","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2501.02364","title":"Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension","created":"2025-01-04","cited_by_count":2,"area":null},{"id":"2602.04019","title":"Understanding and Guiding Layer Placement in Parameter-Efficient Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2605.03869","title":"On Adaptivity in Zeroth-Order Optimization","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2107.04827","title":"Identifying Layers Susceptible to Adversarial Attacks","created":"2021-07-10","cited_by_count":1,"area":null},{"id":"2110.04267","title":"Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training","created":"2021-10-08","cited_by_count":1,"area":null},{"id":"2308.03128","title":"Iterative Magnitude Pruning as a Renormalisation Group: A Study in The Context of The Lottery Ticket Hypothesis","created":"2023-08-06","cited_by_count":1,"area":null},{"id":"2312.03885","title":"Gathering and Exploiting Higher-Order Information when Training Large Structured Models","created":"2023-12-06","cited_by_count":1,"area":null},{"id":"2408.09015","title":"AdaRank: Disagreement Based Module Rank Prediction for Low-rank Adaptation","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2504.15991","title":"Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space Applications","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2505.18107","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2510.19675","title":"Study of Training Dynamics for Memory-Constrained Fine-Tuning","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2510.26560","title":"On Measuring Localization of Shortcuts in Deep Networks","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2110.06435","title":"Dropout Prediction Uncertainty Estimation Using Neuron Activation Strength","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2201.11939","title":"With Greater Distance Comes Worse Performance: On the Perspective of Layer Utilization and Model Generalization","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2203.15297","title":"Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks","created":"2022-03-29","cited_by_count":0,"area":null},{"id":"2306.13682","title":"Evaluating the overall sensitivity of saliency-based explanation methods","created":"2023-06-21","cited_by_count":0,"area":null},{"id":"2307.03500","title":"DEFT: Exploiting Gradient Norm Difference between Model Layers for Scalable Gradient Sparsification","created":"2023-07-07","cited_by_count":0,"area":null},{"id":"2402.13781","title":"Preserving Near-Optimal Gradient Sparsification Cost for Scalable Distributed Deep Learning","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2405.04513","title":"Switchable Decision: Dynamic Neural Generation Networks","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2405.15895","title":"Manifold Metric: A Loss Landscape Approach for Predicting Model Performance","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2411.14345","title":"Layer Pruning with Consensus: A Triple-Win Solution","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2506.18011","title":"Probing the Embedding Space of Transformers via Minimal Token Perturbations","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2510.12842","title":"Protenix-Mini+: efficient structure prediction model with scalable pairformer","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2512.05790","title":"Learnability Window in Gated Recurrent Neural Networks","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2603.00910","title":"Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2608.13660","title":"What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2610.00771","title":"Localizing Transfer Between Memorization Tasks","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}