{"total":422,"rows":[{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2102.06062","title":"Deep Learning with Label Differential Privacy","created":"2021-02-11","cited_by_count":117,"area":null},{"id":"2502.04959","title":"No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces","created":"2025-02-07","cited_by_count":96,"area":null},{"id":"2104.14726","title":"MOOD: Multi-level Out-of-distribution Detection","created":"2021-04-30","cited_by_count":94,"area":null},{"id":"2110.02796","title":"An Unconstrained Layer-Peeled Perspective on Neural Collapse","created":"2021-10-06","cited_by_count":87,"area":null},{"id":"2209.14107","title":"Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure","created":"2022-09-28","cited_by_count":83,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2106.05731","title":"Leveraged Weighted Loss for Partial Label Learning","created":"2021-06-10","cited_by_count":66,"area":null},{"id":"2102.06289","title":"When and How Mixup Improves Calibration","created":"2021-02-11","cited_by_count":60,"area":null},{"id":"2302.10326","title":"Unsupervised Out-of-Distribution Detection with Diffusion Inpainting","created":"2023-02-20","cited_by_count":59,"area":"diffusion"},{"id":"2102.08248","title":"Hierarchical VAEs Know What They Don't Know","created":"2021-02-16","cited_by_count":58,"area":null},{"id":"2303.02045","title":"Uncertainty Estimation by Fisher Information-based Evidential Deep Learning","created":"2023-03-03","cited_by_count":58,"area":null},{"id":"2105.09513","title":"Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions","created":"2021-05-20","cited_by_count":49,"area":null},{"id":"2110.12911","title":"Instance-Dependent Partial Label Learning","created":"2021-10-25","cited_by_count":49,"area":null},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2106.03812","title":"Neural Monge Map estimation and its applications","created":"2021-06-07","cited_by_count":40,"area":null},{"id":"2107.04150","title":"MCMC Variational Inference via Uncorrected Hamiltonian Annealing","created":"2021-07-08","cited_by_count":39,"area":null},{"id":"2205.15403","title":"Neural Optimal Transport with General Cost Functionals","created":"2022-05-30","cited_by_count":36,"area":null},{"id":"2505.12477","title":"Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning","created":"2025-05-18","cited_by_count":36,"area":null},{"id":"2102.07346","title":"On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2301.01452","title":"The Predictive Forward-Forward Algorithm","created":"2023-01-04","cited_by_count":35,"area":null},{"id":"2102.09743","title":"Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques","created":"2021-02-19","cited_by_count":34,"area":null},{"id":"2109.02639","title":"On the Out-of-distribution Generalization of Probabilistic Image Modelling","created":"2021-09-04","cited_by_count":33,"area":null},{"id":"2206.06686","title":"Bandwidth Enables Generalization in Quantum Kernel Models","created":"2022-06-14","cited_by_count":32,"area":null},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2109.03775","title":"FedZKT: Zero-Shot Knowledge Transfer towards Resource-Constrained Federated Learning with Heterogeneous On-Device Models","created":"2021-09-08","cited_by_count":31,"area":null},{"id":"2111.05451","title":"Importance of Kernel Bandwidth in Quantum Machine Learning","created":"2021-11-09","cited_by_count":31,"area":null},{"id":"2206.08900","title":"Adapting the Linearised Laplace Model Evidence for Modern Deep Learning","created":"2022-06-17","cited_by_count":29,"area":null},{"id":"2305.15759","title":"DP-LDMs: Differentially Private Latent Diffusion Models","created":"2023-05-25","cited_by_count":29,"area":"diffusion"},{"id":"2102.12967","title":"A statistical framework for efficient out of distribution detection in deep neural networks","created":"2021-02-25","cited_by_count":28,"area":null},{"id":"2206.01816","title":"From $t$-SNE to UMAP with contrastive learning","created":"2022-06-03","cited_by_count":28,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2307.03217","title":"Quantification of Uncertainty with Adversarial Models","created":"2023-07-06","cited_by_count":28,"area":null},{"id":"2104.01374","title":"Interpretable Unsupervised Diversity Denoising and Artefact Removal","created":"2021-04-03","cited_by_count":26,"area":null},{"id":"2208.11726","title":"Wasserstein Task Embedding for Measuring Task Similarities","created":"2022-08-24","cited_by_count":25,"area":null},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2110.06399","title":"Dynamic Inference with Neural Interpreters","created":"2021-10-12","cited_by_count":24,"area":null},{"id":"2202.05613","title":"CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning","created":"2022-02-11","cited_by_count":24,"area":null},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23,"area":null},{"id":"2206.00830","title":"Progressive Purification for Instance-Dependent Partial Label Learning","created":"2022-06-02","cited_by_count":23,"area":null},{"id":"2206.13497","title":"Robustness Implies Generalization via Data-Dependent Generalization Bounds","created":"2022-06-27","cited_by_count":23,"area":null},{"id":"2208.09083","title":"Out-of-distribution Detection via Frequency-regularized Generative Models","created":"2022-08-18","cited_by_count":23,"area":null},{"id":"2108.07594","title":"Coalesced Multi-Output Tsetlin Machines with Clause Sharing","created":"2021-08-17","cited_by_count":22,"area":null},{"id":"2205.15704","title":"Mitigating Dataset Bias by Using Per-sample Gradient","created":"2022-05-31","cited_by_count":22,"area":null},{"id":"2406.02354","title":"Label-wise Aleatoric and Epistemic Uncertainty Quantification","created":"2024-06-04","cited_by_count":22,"area":null},{"id":"2409.08754","title":"Uncertainty Estimation by Density Aware Evidential Deep Learning","created":"2024-09-13","cited_by_count":22,"area":null},{"id":"2103.16194","title":"Differentiable Drawing and Sketching","created":"2021-03-30","cited_by_count":21,"area":null},{"id":"2106.06152","title":"On the Robustness of Average Losses for Partial-Label Learning","created":"2021-06-11","cited_by_count":20,"area":null},{"id":"2203.08504","title":"A Survey of Historical Document Image Datasets","created":"2022-03-16","cited_by_count":20,"area":null},{"id":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2312.17162","title":"Function-Space Regularization in Neural Networks: A Probabilistic Perspective","created":"2023-12-28","cited_by_count":20,"area":null},{"id":"2102.06879","title":"Learning from Similarity-Confidence Data","created":"2021-02-13","cited_by_count":19,"area":null},{"id":"2109.09282","title":"Unsupervised Continual Learning in Streaming Environments","created":"2021-09-20","cited_by_count":19,"area":null},{"id":"2110.05861","title":"Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2307.05772","title":"Random-Set Neural Networks (RS-NN)","created":"2023-07-11","cited_by_count":19,"area":null},{"id":"2401.00276","title":"Second-Order Uncertainty Quantification: Variance-Based Measures","created":"2023-12-30","cited_by_count":19,"area":null},{"id":"2302.07317","title":"Algorithm Selection for Deep Active Learning with Imbalanced Datasets","created":"2023-02-14","cited_by_count":18,"area":null},{"id":"2304.09762","title":"Practical Differentially Private and Byzantine-resilient Federated Learning","created":"2023-04-15","cited_by_count":18,"area":null},{"id":"2310.18677","title":"Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach","created":"2023-10-28","cited_by_count":18,"area":null},{"id":"2406.01461","title":"Hardness of Learning Neural Networks under the Manifold Hypothesis","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2406.16232","title":"Jacobian Descent for Multi-Objective Optimization","created":"2024-06-23","cited_by_count":18,"area":null},{"id":"2502.06018","title":"Kolmogorov-Arnold Fourier Networks","created":"2025-02-09","cited_by_count":18,"area":null},{"id":"2107.08785","title":"On Out-of-distribution Detection with Energy-based Models","created":"2021-07-03","cited_by_count":17,"area":null},{"id":"2202.12570","title":"Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization","created":"2022-02-25","cited_by_count":17,"area":null},{"id":"2103.15536","title":"Cloud2Curve: Generation and Vectorization of Parametric Sketches","created":"2021-03-29","cited_by_count":16,"area":null},{"id":"2106.03357","title":"Evaluating State-of-the-Art Classification Models Against Bayes Optimality","created":"2021-06-07","cited_by_count":16,"area":null},{"id":"2205.12755","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","created":"2022-05-25","cited_by_count":16,"area":null},{"id":"2106.10065","title":"Being a Bit Frequentist Improves Bayesian Neural Networks","created":"2021-06-18","cited_by_count":15,"area":null},{"id":"2202.08985","title":"Out of Distribution Data Detection Using Dropout Bayesian Neural Networks","created":"2022-02-18","cited_by_count":15,"area":null},{"id":"2410.00393","title":"Revisiting Essential and Nonessential Settings of Evidential Deep Learning","created":"2024-10-01","cited_by_count":15,"area":null},{"id":"2206.08476","title":"Zero-Shot AutoML with Pretrained Models","created":"2022-06-16","cited_by_count":14,"area":null},{"id":"2505.11883","title":"MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging","created":"2025-05-17","cited_by_count":14,"area":null},{"id":"2103.00243","title":"Searching for Robustness: Loss Learning for Noisy Classification Tasks","created":"2021-02-27","cited_by_count":13,"area":null},{"id":"2105.04471","title":"Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions","created":"2021-05-10","cited_by_count":13,"area":null},{"id":"2106.08453","title":"How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2112.05341","title":"Hyperdimensional Feature Fusion for Out-Of-Distribution Detection","created":"2021-12-10","cited_by_count":13,"area":null},{"id":"2310.05632","title":"Binary Classification with Confidence Difference","created":"2023-10-09","cited_by_count":13,"area":null},{"id":"2406.03280","title":"FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion","created":"2024-06-05","cited_by_count":13,"area":null},{"id":"2102.00678","title":"Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification","created":"2021-02-01","cited_by_count":12,"area":null},{"id":"2104.02555","title":"Fourier Image Transformer","created":"2021-04-06","cited_by_count":12,"area":null},{"id":"2203.09739","title":"Do Deep Networks Transfer Invariances Across Classes?","created":"2022-03-18","cited_by_count":12,"area":null},{"id":"2205.00420","title":"Uniform Manifold Approximation with Two-phase Optimization","created":"2022-05-01","cited_by_count":12,"area":null},{"id":"2205.10937","title":"muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems","created":"2022-05-22","cited_by_count":12,"area":null},{"id":"2305.18484","title":"Neural Fourier Transform: A General Approach to Equivariant Representation Learning","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2311.15990","title":"Should We Learn Most Likely Functions or Parameters?","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2106.14836","title":"Understanding Dynamics of Nonlinear Representation Learning and Its Application","created":"2021-06-28","cited_by_count":11,"area":null},{"id":"2107.07617","title":"Algorithmic insights on continual learning from fruit flies","created":"2021-07-15","cited_by_count":11,"area":null},{"id":"2112.10157","title":"Rethinking Importance Weighting for Transfer Learning","created":"2021-12-19","cited_by_count":11,"area":null},{"id":"2112.14869","title":"Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity","created":"2021-12-30","cited_by_count":11,"area":null},{"id":"2302.09344","title":"Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics","created":"2023-02-18","cited_by_count":11,"area":null},{"id":"2306.03116","title":"Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowds","created":"2023-06-05","cited_by_count":11,"area":null},{"id":"2411.01696","title":"Conformal Risk Minimization with Variance Reduction","created":"2024-11-03","cited_by_count":11,"area":null},{"id":"2508.03121","title":"RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging","created":"2025-08-05","cited_by_count":11,"area":null},{"id":"2203.00479","title":"Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Prior","created":"2022-02-28","cited_by_count":10,"area":null},{"id":"2206.03466","title":"Adversarial Reprogramming Revisited","created":"2022-06-07","cited_by_count":10,"area":null},{"id":"2302.00061","title":"Dynamic Flows on Curved Space Generated by Labeled Data","created":"2023-01-31","cited_by_count":10,"area":null},{"id":"2303.18187","title":"Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2308.00958","title":"Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks","created":"2023-08-02","cited_by_count":10,"area":null}],"next_cursor":"100"}