{"total":77,"rows":[{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108,"area":null},{"id":"2102.09517","title":"Essentials for Class Incremental Learning","created":"2021-02-18","cited_by_count":57,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2410.16713","title":"Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World","created":"2024-10-22","cited_by_count":52,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2106.06770","title":"What can linearized neural networks actually say about generalization?","created":"2021-06-12","cited_by_count":49,"area":null},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41,"area":null},{"id":"2110.02424","title":"Spectral Bias in Practice: The Role of Function Frequency in Generalization","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2111.14655","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2103.09154","title":"Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition","created":"2021-03-16","cited_by_count":30,"area":null},{"id":"2209.13476","title":"Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels","created":"2022-09-27","cited_by_count":30,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2204.08397","title":"Fast and Memory-Efficient Network Towards Efficient Image Super-Resolution","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2208.12807","title":"Towards Federated Learning against Noisy Labels via Local Self-Regularization","created":"2022-08-25","cited_by_count":26,"area":null},{"id":"2410.22812","title":"Universality of the $\\pi^2/6$ Pathway in Avoiding Model Collapse","created":"2024-10-30","cited_by_count":26,"area":null},{"id":"2105.09750","title":"Anchor-based Plain Net for Mobile Image Super-Resolution","created":"2021-05-20","cited_by_count":24,"area":null},{"id":"2108.04228","title":"Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition","created":"2021-07-21","cited_by_count":21,"area":null},{"id":"2109.13059","title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2111.12172","title":"Multi-label Iterated Learning for Image Classification with Label Ambiguity","created":"2021-11-23","cited_by_count":19,"area":null},{"id":"2206.04672","title":"Overcoming the Spectral Bias of Neural Value Approximation","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2203.14577","title":"Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?","created":"2022-03-28","cited_by_count":18,"area":null},{"id":"2106.02654","title":"Churn Reduction via Distillation","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2404.04286","title":"Bias Amplification in Language Model Evolution: An Iterated Learning Perspective","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2410.05101","title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","created":"2024-10-07","cited_by_count":17,"area":null},{"id":"2310.18777","title":"Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings","created":"2023-10-28","cited_by_count":15,"area":null},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2112.01653","title":"Learning Curves for Continual Learning in Neural Networks: Self-Knowledge Transfer and Forgetting","created":"2021-12-03","cited_by_count":14,"area":null},{"id":"2305.14783","title":"Disentangled Phonetic Representation for Chinese Spelling Correction","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2405.18756","title":"Provable Contrastive Continual Learning","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2110.08220","title":"Combining Diverse Feature Priors","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2502.05075","title":"Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2304.10113","title":"SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2507.10935","title":"GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization","created":"2025-07-15","cited_by_count":8,"area":null},{"id":"2112.08772","title":"Sharpness-Aware Minimization with Dynamic Reweighting","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2303.05093","title":"Improving Video Retrieval by Adaptive Margin","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2304.04858","title":"Simulated Annealing in Early Layers Leads to Better Generalization","created":"2023-04-10","cited_by_count":6,"area":null},{"id":"2211.15774","title":"Decentralized Learning with Multi-Headed Distillation","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2306.05278","title":"Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training","created":"2023-06-08","cited_by_count":5,"area":null},{"id":"2406.11206","title":"Retraining with Predicted Hard Labels Provably Increases Model Accuracy","created":"2024-06-17","cited_by_count":5,"area":null},{"id":"2411.01431","title":"Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision","created":"2024-11-03","cited_by_count":5,"area":null},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2204.02004","title":"Bimodal Distributed Binarized Neural Networks","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2205.00693","title":"Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding","created":"2022-05-02","cited_by_count":4,"area":null},{"id":"2309.08227","title":"VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2403.01326","title":"DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions","created":"2024-03-02","cited_by_count":4,"area":null},{"id":"2106.13913","title":"Midpoint Regularization: from High Uncertainty Training to Conservative Classification","created":"2021-06-26","cited_by_count":3,"area":null},{"id":"2207.12660","title":"Bilateral Self-unbiased Learning from Biased Implicit Feedback","created":"2022-07-26","cited_by_count":3,"area":null},{"id":"2309.11691","title":"RAI4IoE: Responsible AI for Enabling the Internet of Energy","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2306.00480","title":"Parallel Neurosymbolic Integration with Concordia","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2312.12783","title":"Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2401.17802","title":"Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning","created":"2024-01-31","cited_by_count":2,"area":null},{"id":"2405.10861","title":"Tailoring Vaccine Messaging with Common-Ground Opinions","created":"2024-05-17","cited_by_count":2,"area":null},{"id":"2411.19067","title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2606.03938","title":"q0: Primitives for Hyper-Epoch Pretraining","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2110.04274","title":"Kernel Interpolation as a Bayes Point Machine","created":"2021-10-08","cited_by_count":1,"area":null},{"id":"2505.15195","title":"Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.19159","title":"A Joint Learning Framework with Feature Reconstruction and Prediction for Incomplete Satellite Image Time Series in Agricultural Semantic Segmentation","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2609.26216","title":"Beyond Imitation: Auditing the Recoverability of Reasoning in Distilled Models","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2108.12522","title":"Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP","created":"2021-08-27","cited_by_count":0,"area":null},{"id":"2111.14829","title":"Nonparametric Topological Layers in Neural Networks","created":"2021-11-27","cited_by_count":0,"area":null},{"id":"2307.13290","title":"Modify Training Directions in Function Space to Reduce Generalization Error","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2312.11555","title":"CR-SFP: Learning Consistent Representation for Soft Filter Pruning","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2402.16361","title":"Layer-wise Regularized Dropout for Neural Language Models","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2410.22081","title":"Choosy Babies Need One Coach: Inducing Mode-Seeking Behavior in BabyLlama with Reverse KL Divergence","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2501.16329","title":"sDREAMER: Self-distilled Mixture-of-Modality-Experts Transformer for Automatic Sleep Staging","created":"2025-01-27","cited_by_count":0,"area":null},{"id":"2505.18166","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2601.11581","title":"Enhancing the QA Model through a Multi-domain Debiasing Framework","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2601.20773","title":"Smoothing the Black-Box: Signed-Distance Supervision for Black-Box Model Copying","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.29380","title":"TRACER: Persistent Regularization for Robust Multimodal Finetuning","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.12940","title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2608.11937","title":"Distillation of Foundation Models for Time-dependent PDEs","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":null}