{"total":122,"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":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77,"area":null},{"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":"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":"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":"2402.18528","title":"Gradient Reweighting: Towards Imbalanced Class-Incremental Learning","created":"2024-02-28","cited_by_count":37,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2505.20662","title":"AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2308.13305","title":"Dynamic Residual Classifier for Class Incremental Learning","created":"2023-08-25","cited_by_count":26,"area":null},{"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":"2411.19946","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","created":"2024-11-29","cited_by_count":20,"area":null},{"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":"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":"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":"2402.04841","title":"Data-efficient Large Vision Models through Sequential Autoregression","created":"2024-02-07","cited_by_count":14,"area":null},{"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":"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":"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":"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":"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":"2407.14153","title":"De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation","created":"2024-07-19","cited_by_count":11,"area":null},{"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":"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},{"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":"2405.15170","title":"Label-efficient Semantic Scene Completion with Scribble Annotations","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2305.18830","title":"Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2308.11874","title":"Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch","created":"2023-08-23","cited_by_count":8,"area":null},{"id":"2308.00291","title":"Fundus-Enhanced Disease-Aware Distillation Model for Retinal Disease Classification from OCT Images","created":"2023-08-01","cited_by_count":7,"area":null},{"id":"2402.19145","title":"A SAM-guided Two-stream Lightweight Model for Anomaly Detection","created":"2024-02-29","cited_by_count":7,"area":null},{"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":"2307.14781","title":"Contrastive Knowledge Amalgamation for Unsupervised Image Classification","created":"2023-07-27","cited_by_count":6,"area":null},{"id":"2404.13322","title":"MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities","created":"2024-04-20","cited_by_count":6,"area":null},{"id":"2409.18026","title":"ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning","created":"2024-09-26","cited_by_count":6,"area":null},{"id":"2503.02154","title":"AugFL: Augmenting Federated Learning with Pretrained Models","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2505.16778","title":"Single Domain Generalization for Few-Shot Counting via Universal Representation Matching","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2304.02263","title":"Towards Efficient Task-Driven Model Reprogramming with Foundation Models","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2407.15794","title":"Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video","created":"2024-07-22","cited_by_count":5,"area":null},{"id":"2408.14770","title":"Text-guided Foundation Model Adaptation for Long-Tailed Medical Image Classification","created":"2024-08-27","cited_by_count":5,"area":null},{"id":"2209.15525","title":"Slimmable Networks for Contrastive Self-supervised Learning","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2211.06816","title":"Long-Range Zero-Shot Generative Deep Network Quantization","created":"2022-11-13","cited_by_count":4,"area":null},{"id":"2305.19688","title":"VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2023-05-31","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":"2311.15200","title":"SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification","created":"2023-11-26","cited_by_count":4,"area":null},{"id":"2401.05014","title":"Source-Free Cross-Modal Knowledge Transfer by Unleashing the Potential of Task-Irrelevant Data","created":"2024-01-10","cited_by_count":4,"area":null},{"id":"2404.09210","title":"FedDistill: Global Model Distillation for Local Model De-Biasing in Non-IID Federated Learning","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"2506.21080","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2510.11090","title":"Source-Free Object Detection with Detection Transformer","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2402.11305","title":"On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2404.14822","title":"CNN2GNN: How to Bridge CNN with GNN","created":"2024-04-23","cited_by_count":3,"area":null},{"id":"2409.14538","title":"Towards Model-Agnostic Dataset Condensation by Heterogeneous Models","created":"2024-09-22","cited_by_count":3,"area":null},{"id":"2507.22094","title":"Scaling and Distilling Transformer Models for sEMG","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2304.05753","title":"Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results","created":"2023-04-12","cited_by_count":2,"area":null},{"id":"2307.16363","title":"BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration","created":"2023-07-31","cited_by_count":2,"area":null},{"id":"2308.06948","title":"MixBCT: Towards Self-Adapting Backward-Compatible Training","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2408.03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2412.10091","title":"Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identification","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2503.14097","title":"SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2507.12426","title":"DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2507.16296","title":"Cross-Modal Distillation For Widely Differing Modalities","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2603.01412","title":"UETrack: A Unified and Efficient Framework for Single Object Tracking","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2210.01600","title":"Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2212.11091","title":"Exploring Content Relationships for Distilling Efficient GANs","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2310.03032","title":"Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2403.14430","title":"Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2404.06756","title":"CrimeAlarm: Towards Intensive Intent Dynamics in Fine-grained Crime Prediction","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2405.08593","title":"Open-Vocabulary Object Detection via Neighboring Region Attention Alignment","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2406.06653","title":"DKDL-Net: A Lightweight Bearing Fault Detection Model via Decoupled Knowledge Distillation and Low-Rank Adaptation Fine-tuning","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2407.18821","title":"Deep Companion Learning: Enhancing Generalization Through Historical Consistency","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2408.08250","title":"Computer Vision Model Compression Techniques for Embedded Systems: A Survey","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2411.10961","title":"Map-Free Trajectory Prediction with Map Distillation and Hierarchical Encoding","created":"2024-11-17","cited_by_count":1,"area":null},{"id":"2501.01983","title":"ECG-guided individual identification via PPG","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2505.03819","title":"Focus on Likely Classes for Test-Time Prediction","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2508.03002","title":"Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.19743","title":"Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive Evaluation","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2602.04260","title":"Decoupled Hierarchical Distillation for Multimodal Emotion Recognition","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.08851","title":"Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.29498","title":"Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2605.31124","title":"QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.04733","title":"LP-SFT: Keeping Plausible Alternatives Alive in Supervised Fine-Tuning","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2305.00620","title":"Refined Response Distillation for Class-Incremental Player Detection","created":"2023-05-01","cited_by_count":0,"area":null},{"id":"2308.01098","title":"Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2401.12997","title":"Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion","created":"2024-01-19","cited_by_count":0,"area":null},{"id":"2403.12690","title":"LNPT: Label-free Network Pruning and Training","created":"2024-03-19","cited_by_count":0,"area":null},{"id":"2405.20084","title":"Estimating Human Poses Across Datasets: A Unified Skeleton and Multi-Teacher Distillation Approach","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2409.06904","title":"Applied Federated Model Personalisation in the Industrial Domain: A Comparative Study","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2411.06023","title":"Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification","created":"2024-11-09","cited_by_count":0,"area":null}],"next_cursor":"100"}