{"total":388,"rows":[{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2312.00863","title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","created":"2023-12-01","cited_by_count":188,"area":null},{"id":"2304.14402","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","created":"2023-04-27","cited_by_count":124,"area":null},{"id":"2211.16231","title":"Curriculum Temperature for Knowledge Distillation","created":"2022-11-29","cited_by_count":112,"area":"distill"},{"id":"2403.01427","title":"Logit Standardization in Knowledge Distillation","created":"2024-03-03","cited_by_count":102,"area":"distill"},{"id":"2310.19444","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","created":"2023-10-30","cited_by_count":78,"area":"distill"},{"id":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77,"area":null},{"id":"2303.13802","title":"Decoupled Multimodal Distilling for Emotion Recognition","created":"2023-03-24","cited_by_count":76,"area":"distill"},{"id":"2403.02781","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","created":"2024-03-05","cited_by_count":72,"area":"mllm"},{"id":"2303.13005","title":"From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels","created":"2023-03-23","cited_by_count":69,"area":"distill"},{"id":"2311.17950","title":"Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching","created":"2023-11-29","cited_by_count":69,"area":null},{"id":"2304.12777","title":"Class Attention Transfer Based Knowledge Distillation","created":"2023-04-25","cited_by_count":61,"area":"distill"},{"id":"2305.13948","title":"Decoupled Kullback-Leibler Divergence Loss","created":"2023-05-23","cited_by_count":58,"area":"distill"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2305.15712","title":"Knowledge Diffusion for Distillation","created":"2023-05-25","cited_by_count":53,"area":"diffusion"},{"id":"2306.11369","title":"CrossKD: Cross-Head Knowledge Distillation for Object Detection","created":"2023-06-20","cited_by_count":52,"area":"distill"},{"id":"2302.05071","title":"EVC: Towards Real-Time Neural Image Compression with Mask Decay","created":"2023-02-10","cited_by_count":49,"area":null},{"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":"2404.11958","title":"Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation","created":"2024-04-18","cited_by_count":43,"area":"distill"},{"id":"2207.02039","title":"PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient","created":"2022-07-05","cited_by_count":41,"area":"distill"},{"id":"2309.16286","title":"Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning","created":"2023-09-28","cited_by_count":40,"area":null},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38,"area":"mllm"},{"id":"2402.11148","title":"Knowledge Distillation Based on Transformed Teacher Matching","created":"2024-02-17","cited_by_count":37,"area":"distill"},{"id":"2402.18528","title":"Gradient Reweighting: Towards Imbalanced Class-Incremental Learning","created":"2024-02-28","cited_by_count":37,"area":null},{"id":"2208.12256","title":"Masked Autoencoders Enable Efficient Knowledge Distillers","created":"2022-08-25","cited_by_count":36,"area":"distill"},{"id":"2209.02432","title":"ViTKD: Practical Guidelines for ViT feature knowledge distillation","created":"2022-09-06","cited_by_count":34,"area":"distill"},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2404.16456","title":"Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities","created":"2024-04-25","cited_by_count":32,"area":"distill"},{"id":"2505.20662","title":"AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29,"area":"distill"},{"id":"2308.07146","title":"CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation","created":"2023-08-14","cited_by_count":29,"area":"mllm"},{"id":"2503.23751","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks","created":"2025-03-31","cited_by_count":28,"area":"safety"},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26,"area":"distill"},{"id":"2308.13305","title":"Dynamic Residual Classifier for Class Incremental Learning","created":"2023-08-25","cited_by_count":26,"area":null},{"id":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"area":"distill"},{"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":"2305.12129","title":"Lifting the Curse of Capacity Gap in Distilling Language Models","created":"2023-05-20","cited_by_count":25,"area":"moe"},{"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":"2403.05894","title":"Frequency Attention for Knowledge Distillation","created":"2024-03-09","cited_by_count":24,"area":"distill"},{"id":"2307.09158","title":"Class-relation Knowledge Distillation for Novel Class Discovery","created":"2023-07-18","cited_by_count":23,"area":"distill"},{"id":"2304.01279","title":"Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation","created":"2023-04-03","cited_by_count":22,"area":"moe"},{"id":"2310.00258","title":"NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation","created":"2023-09-30","cited_by_count":22,"area":"distill"},{"id":"2501.16937","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","created":"2025-01-28","cited_by_count":22,"area":"distill"},{"id":"2510.24021","title":"SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs","created":"2025-10-28","cited_by_count":22,"area":"distill"},{"id":"2304.11832","title":"Function-Consistent Feature Distillation","created":"2023-04-24","cited_by_count":21,"area":"distill"},{"id":"2305.12954","title":"Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?","created":"2023-05-22","cited_by_count":21,"area":"diffusion"},{"id":"2306.10687","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","created":"2023-06-19","cited_by_count":20,"area":"distill"},{"id":"2308.10297","title":"DomainAdaptor: A Novel Approach to Test-time Adaptation","created":"2023-08-20","cited_by_count":20,"area":null},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20,"area":null},{"id":"2406.07876","title":"Small Scale Data-Free Knowledge Distillation","created":"2024-06-12","cited_by_count":20,"area":"distill"},{"id":"2411.19946","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","created":"2024-11-29","cited_by_count":20,"area":null},{"id":"2204.05957","title":"Localization Distillation for Object Detection","created":"2022-04-12","cited_by_count":19,"area":"distill"},{"id":"2308.06689","title":"Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training","created":"2023-08-13","cited_by_count":19,"area":null},{"id":"2308.10306","title":"Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation","created":"2023-08-20","cited_by_count":19,"area":null},{"id":"2412.08139","title":"Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation","created":"2024-12-11","cited_by_count":19,"area":"distill"},{"id":"2304.11379","title":"LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation","created":"2023-04-22","cited_by_count":18,"area":null},{"id":"2305.17007","title":"Improving Knowledge Distillation via Regularizing Feature Norm and Direction","created":"2023-05-26","cited_by_count":18,"area":"distill"},{"id":"2307.08500","title":"Cumulative Spatial Knowledge Distillation for Vision Transformers","created":"2023-07-17","cited_by_count":18,"area":"distill"},{"id":"2309.02870","title":"Rethinking Momentum Knowledge Distillation in Online Continual Learning","created":"2023-09-06","cited_by_count":18,"area":"distill"},{"id":"2310.07265","title":"Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation","created":"2023-10-11","cited_by_count":18,"area":"distill"},{"id":"2407.03056","title":"Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation","created":"2024-07-03","cited_by_count":18,"area":"mllm"},{"id":"2211.09768","title":"D$^3$ETR: Decoder Distillation for Detection Transformer","created":"2022-11-17","cited_by_count":17,"area":"distill"},{"id":"2401.11824","title":"Rethinking Centered Kernel Alignment in Knowledge Distillation","created":"2024-01-22","cited_by_count":17,"area":"distill"},{"id":"2210.00944","title":"Attention Distillation: self-supervised vision transformer students need more guidance","created":"2022-10-03","cited_by_count":16,"area":"distill"},{"id":"2208.09828","title":"I Know What You Do Not Know: Knowledge Graph Embedding via Co-distillation Learning","created":"2022-08-21","cited_by_count":15,"area":null},{"id":"2403.07705","title":"Robust Synthetic-to-Real Transfer for Stereo Matching","created":"2024-03-12","cited_by_count":15,"area":null},{"id":"2404.08564","title":"Federated Distillation: A Survey","created":"2024-04-02","cited_by_count":15,"area":null},{"id":"2402.03119","title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","created":"2024-02-05","cited_by_count":14,"area":"distill"},{"id":"2402.04841","title":"Data-efficient Large Vision Models through Sequential Autoregression","created":"2024-02-07","cited_by_count":14,"area":null},{"id":"2208.12681","title":"Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective","created":"2022-08-26","cited_by_count":13,"area":"distill"},{"id":"2211.08071","title":"KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","created":"2022-11-15","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":"2503.16707","title":"Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding","created":"2025-03-20","cited_by_count":13,"area":"mllm"},{"id":"2210.09609","title":"SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP","created":"2022-10-18","cited_by_count":12,"area":"distill"},{"id":"2301.00131","title":"Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching","created":"2022-12-31","cited_by_count":12,"area":null},{"id":"2302.05666","title":"Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels","created":"2023-02-11","cited_by_count":12,"area":"distill"},{"id":"2303.09977","title":"Semantic Scene Completion with Cleaner Self","created":"2023-03-17","cited_by_count":12,"area":null},{"id":"2303.17285","title":"Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection","created":"2023-03-30","cited_by_count":12,"area":null},{"id":"2308.00520","title":"NormKD: Normalized Logits for Knowledge Distillation","created":"2023-08-01","cited_by_count":12,"area":"distill"},{"id":"2308.06453","title":"Multi-Label Knowledge Distillation","created":"2023-08-12","cited_by_count":12,"area":"distill"},{"id":"2407.04208","title":"AMD: Automatic Multi-step Distillation of Large-scale Vision Models","created":"2024-07-05","cited_by_count":12,"area":null},{"id":"2210.03923","title":"Sparse Teachers Can Be Dense with Knowledge","created":"2022-10-08","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":"2305.15781","title":"VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale","created":"2023-05-25","cited_by_count":11,"area":"distill"},{"id":"2402.17316","title":"Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation","created":"2024-02-27","cited_by_count":11,"area":null},{"id":"2403.11817","title":"HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation","created":"2024-03-18","cited_by_count":11,"area":"distill"},{"id":"2403.19539","title":"De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts","created":"2024-03-28","cited_by_count":11,"area":"distill"},{"id":"2407.14153","title":"De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation","created":"2024-07-19","cited_by_count":11,"area":null},{"id":"2411.06786","title":"ScaleKD: Strong Vision Transformers Could Be Excellent Teachers","created":"2024-11-11","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":"2601.08301","title":"ReCo-KD: Region- and Context-Aware Knowledge Distillation for Efficient 3D Medical Image Segmentation","created":"2026-01-13","cited_by_count":11,"area":"distill"},{"id":"2307.02092","title":"Make A Long Image Short: Adaptive Token Length for Vision Transformers","created":"2023-07-05","cited_by_count":10,"area":null},{"id":"2402.19144","title":"Weakly Supervised Monocular 3D Detection with a Single-View Image","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2403.01238","title":"On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving","created":"2024-03-02","cited_by_count":10,"area":"driving"},{"id":"2404.00936","title":"A Comprehensive Review of Knowledge Distillation in Computer Vision","created":"2024-04-01","cited_by_count":10,"area":"distill"},{"id":"2208.10139","title":"Rethinking Knowledge Distillation via Cross-Entropy","created":"2022-08-22","cited_by_count":9,"area":"distill"},{"id":"2210.15865","title":"Completely Heterogeneous Federated Learning","created":"2022-10-28","cited_by_count":9,"area":null},{"id":"2309.11276","title":"Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Information","created":"2023-09-20","cited_by_count":9,"area":null}],"next_cursor":"100"}