{"total":190,"rows":[{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2505.02387","title":"RM-R1: Reward Modeling as Reasoning","created":"2025-05-05","cited_by_count":154,"area":"lr"},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2212.01548","title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","created":"2022-12-03","cited_by_count":102,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2210.07686","title":"Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation","created":"2022-10-14","cited_by_count":62,"area":"distill"},{"id":"2211.13976","title":"Expanding Small-Scale Datasets with Guided Imagination","created":"2022-11-25","cited_by_count":62,"area":null},{"id":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61,"area":"mllm"},{"id":"2203.08124","title":"Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective","created":"2022-03-15","cited_by_count":57,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2112.01528","title":"A Fast Knowledge Distillation Framework for Visual Recognition","created":"2021-12-02","cited_by_count":50,"area":"distill"},{"id":"2305.20028","title":"A Study of Bayesian Neural Network Surrogates for Bayesian Optimization","created":"2023-05-31","cited_by_count":50,"area":null},{"id":"2405.16043","title":"Theoretical Analysis of Weak-to-Strong Generalization","created":"2024-05-25","cited_by_count":48,"area":null},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47,"area":"distill"},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2309.16286","title":"Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning","created":"2023-09-28","cited_by_count":40,"area":null},{"id":"2202.00155","title":"Fortuitous Forgetting in Connectionist Networks","created":"2022-02-01","cited_by_count":39,"area":null},{"id":"2203.12515","title":"A Survey on Cross-Lingual Summarization","created":"2022-03-23","cited_by_count":38,"area":null},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2208.10160","title":"PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation","created":"2022-08-22","cited_by_count":31,"area":"distill"},{"id":"2404.10346","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","created":"2024-04-16","cited_by_count":31,"area":"lr"},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27,"area":"distill"},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26,"area":"distill"},{"id":"2110.11024","title":"Watermarking Graph Neural Networks based on Backdoor Attacks","created":"2021-10-21","cited_by_count":25,"area":null},{"id":"2305.05010","title":"Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation","created":"2023-05-08","cited_by_count":25,"area":"distill"},{"id":"2401.08732","title":"Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information","created":"2024-01-16","cited_by_count":25,"area":"distill"},{"id":"2206.08491","title":"Revisiting Self-Distillation","created":"2022-06-17","cited_by_count":24,"area":"distill"},{"id":"2306.02210","title":"GPT-FL: Generative Pre-trained Model-Assisted Federated Learning","created":"2023-06-03","cited_by_count":24,"area":null},{"id":"2306.16612","title":"GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps","created":"2023-06-29","cited_by_count":23,"area":null},{"id":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2301.13304","title":"Understanding Self-Distillation in the Presence of Label Noise","created":"2023-01-30","cited_by_count":21,"area":"distill"},{"id":"2407.19389","title":"FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction","created":"2024-07-28","cited_by_count":21,"area":null},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19,"area":"distill"},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2404.03626","title":"Training LLMs over Neurally Compressed Text","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16,"area":"distill"},{"id":"2311.01149","title":"ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model","created":"2023-11-02","cited_by_count":16,"area":null},{"id":"2410.04638","title":"Provable Weak-to-Strong Generalization via Benign Overfitting","created":"2024-10-06","cited_by_count":16,"area":"distill"},{"id":"2503.16870","title":"Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs","created":"2025-03-21","cited_by_count":16,"area":"distill"},{"id":"2203.03047","title":"Recent Advances in Neural Text Generation: A Task-Agnostic Survey","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2210.05920","title":"Boosting Graph Neural Networks via Adaptive Knowledge Distillation","created":"2022-10-12","cited_by_count":14,"area":"distill"},{"id":"2211.12933","title":"Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket","created":"2022-11-23","cited_by_count":14,"area":null},{"id":"2402.03119","title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","created":"2024-02-05","cited_by_count":14,"area":"distill"},{"id":"2210.06711","title":"Weighted Distillation with Unlabeled Examples","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2407.18041","title":"How to Train the Teacher Model for Effective Knowledge Distillation","created":"2024-07-25","cited_by_count":13,"area":"distill"},{"id":"2411.07182","title":"Revisiting Ensembling in One-Shot Federated Learning","created":"2024-11-11","cited_by_count":13,"area":null},{"id":"2109.14960","title":"Prune Your Model Before Distill It","created":"2021-09-30","cited_by_count":12,"area":"distill"},{"id":"2207.12980","title":"Efficient One Pass Self-distillation with Zipf's Label Smoothing","created":"2022-07-26","cited_by_count":12,"area":"distill"},{"id":"2302.00444","title":"Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection","created":"2023-02-01","cited_by_count":12,"area":"distill"},{"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":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2305.10893","title":"Student-friendly Knowledge Distillation","created":"2023-05-18","cited_by_count":11,"area":"distill"},{"id":"2503.18244","title":"CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation","created":"2025-03-23","cited_by_count":11,"area":"distill"},{"id":"2302.03806","title":"SLaM: Student-Label Mixing for Distillation with Unlabeled Examples","created":"2023-02-08","cited_by_count":10,"area":"distill"},{"id":"2311.08640","title":"Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation","created":"2023-11-15","cited_by_count":10,"area":"distill"},{"id":"2512.10150","title":"Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning","created":"2025-12-10","cited_by_count":10,"area":"alignment"},{"id":"2108.00065","title":"Model Preserving Compression for Neural Networks","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2207.10314","title":"Semi-Supervised Learning of Optical Flow by Flow Supervisor","created":"2022-07-21","cited_by_count":9,"area":null},{"id":"2210.01213","title":"Robust Active Distillation","created":"2022-10-03","cited_by_count":9,"area":"distill"},{"id":"2404.13518","title":"Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion","created":"2024-04-21","cited_by_count":9,"area":"safety"},{"id":"2405.14736","title":"GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost","created":"2024-05-23","cited_by_count":9,"area":null},{"id":"2406.15480","title":"On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2505.13111","title":"Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation","created":"2025-05-19","cited_by_count":9,"area":"distill"},{"id":"2207.14561","title":"Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization","created":"2022-07-29","cited_by_count":8,"area":null},{"id":"2305.09651","title":"Tailoring Instructions to Student's Learning Levels Boosts Knowledge Distillation","created":"2023-05-16","cited_by_count":8,"area":"distill"},{"id":"2409.12111","title":"Applications of Knowledge Distillation in Remote Sensing: A Survey","created":"2024-09-18","cited_by_count":8,"area":"distill"},{"id":"2506.02362","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2206.06661","title":"Toward Student-Oriented Teacher Network Training For Knowledge Distillation","created":"2022-06-14","cited_by_count":7,"area":"distill"},{"id":"2207.11191","title":"Self-Supervised-RCNN for Medical Image Segmentation with Limited Data Annotation","created":"2022-07-17","cited_by_count":7,"area":null},{"id":"2208.13648","title":"Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy","created":"2022-08-29","cited_by_count":7,"area":"distill"},{"id":"2212.12965","title":"BD-KD: Balancing the Divergences for Online Knowledge Distillation","created":"2022-12-25","cited_by_count":7,"area":"distill"},{"id":"2307.08436","title":"DOT: A Distillation-Oriented Trainer","created":"2023-07-17","cited_by_count":7,"area":"distill"},{"id":"2402.13007","title":"Improve Cross-Architecture Generalization on Dataset Distillation","created":"2024-02-20","cited_by_count":7,"area":null},{"id":"2404.14109","title":"CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective","created":"2024-04-22","cited_by_count":7,"area":"distill"},{"id":"2505.15442","title":"On the Generalization vs Fidelity Paradox in Knowledge Distillation","created":"2025-05-21","cited_by_count":7,"area":"distill"},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"area":null},{"id":"2302.12091","title":"Random Teachers are Good Teachers","created":"2023-02-23","cited_by_count":6,"area":"distill"},{"id":"2305.07180","title":"Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2305.14109","title":"Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2308.14286","title":"Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection","created":"2023-08-28","cited_by_count":6,"area":"distill"},{"id":"2312.17473","title":"FerKD: Surgical Label Adaptation for Efficient Distillation","created":"2023-12-29","cited_by_count":5,"area":"distill"},{"id":"2407.13254","title":"Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation","created":"2024-07-18","cited_by_count":5,"area":"distill"},{"id":"2407.20299","title":"Dataset Distillation for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":5,"area":"offlinerl"},{"id":"2505.17222","title":"Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2507.07015","title":"MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation","created":"2025-07-09","cited_by_count":5,"area":"distill"},{"id":"2110.09674","title":"Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation","created":"2021-10-19","cited_by_count":4,"area":"distill"},{"id":"2309.14162","title":"Data Upcycling Knowledge Distillation for Image Super-Resolution","created":"2023-09-25","cited_by_count":4,"area":"distill"},{"id":"2404.02424","title":"Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration","created":"2024-04-03","cited_by_count":4,"area":"lr"},{"id":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"id":"2407.14768","title":"Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation","created":"2024-07-20","cited_by_count":4,"area":"distill"},{"id":"2409.14122","title":"Efficient and Effective Model Extraction","created":"2024-09-21","cited_by_count":4,"area":null},{"id":"2410.01483","title":"Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2410.08407","title":"What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias","created":"2024-10-10","cited_by_count":4,"area":"distill"}],"next_cursor":"100"}