{"total":69,"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":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2402.11148","title":"Knowledge Distillation Based on Transformed Teacher Matching","created":"2024-02-17","cited_by_count":37,"area":"distill"},{"id":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"area":"distill"},{"id":"2407.16154","title":"DDK: Distilling Domain Knowledge for Efficient Large Language Models","created":"2024-07-23","cited_by_count":26,"area":"distill"},{"id":"2406.13555","title":"BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation","created":"2024-06-19","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":"2401.11824","title":"Rethinking Centered Kernel Alignment in Knowledge Distillation","created":"2024-01-22","cited_by_count":17,"area":"distill"},{"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":"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":"2406.07862","title":"Self-Distillation Learning Based on Temporal-Spatial Consistency for Spiking Neural Networks","created":"2024-06-12","cited_by_count":9,"area":"distill"},{"id":"2312.07255","title":"GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction","created":"2023-12-12","cited_by_count":8,"area":null},{"id":"2401.06826","title":"Direct Distillation between Different Domains","created":"2024-01-12","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":"2404.14109","title":"CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective","created":"2024-04-22","cited_by_count":7,"area":"distill"},{"id":"2411.01547","title":"Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment","created":"2024-11-03","cited_by_count":7,"area":"distill"},{"id":"2404.13322","title":"MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities","created":"2024-04-20","cited_by_count":6,"area":null},{"id":"2502.20760","title":"VRM: Knowledge Distillation via Virtual Relation Matching","created":"2025-02-28","cited_by_count":6,"area":"distill"},{"id":"2403.13512","title":"Scale Decoupled Distillation","created":"2024-03-20","cited_by_count":5,"area":"distill"},{"id":"2404.17184","title":"Low-Rank Knowledge Decomposition for Medical Foundation Models","created":"2024-04-26","cited_by_count":5,"area":null},{"id":"2412.16493","title":"Cross-View Consistency Regularisation for Knowledge Distillation","created":"2024-12-21","cited_by_count":5,"area":"distill"},{"id":"2409.11018","title":"Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation","created":"2024-09-17","cited_by_count":4,"area":"ssm"},{"id":"2504.00606","title":"Sample-level Adaptive Knowledge Distillation for Action Recognition","created":"2025-04-01","cited_by_count":4,"area":"distill"},{"id":"2505.15133","title":"DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer","created":"2025-05-21","cited_by_count":4,"area":"distill"},{"id":"2506.23285","title":"Competitive Distillation: A Simple Learning Strategy for Improving Visual Classification","created":"2025-06-29","cited_by_count":4,"area":"distill"},{"id":"2507.15911","title":"Local Dense Logit Relations for Enhanced Knowledge Distillation","created":"2025-07-21","cited_by_count":4,"area":"distill"},{"id":"2507.21844","title":"Cross-Architecture Distillation Made Simple with Redundancy Suppression","created":"2025-07-29","cited_by_count":4,"area":"distill"},{"id":"2601.20687","title":"Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models","created":"2026-01-28","cited_by_count":4,"area":"alignment"},{"id":"2406.13225","title":"Communication-Efficient Federated Knowledge Graph Embedding with Entity-Wise Top-K Sparsification","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2409.17823","title":"Enhancing Logits Distillation with Plug\\&Play Kendall's $\\tau$ Ranking Loss","created":"2024-09-26","cited_by_count":3,"area":"distill"},{"id":"2505.22027","title":"Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles","created":"2025-05-28","cited_by_count":3,"area":"distill"},{"id":"2402.11401","title":"GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation","created":"2024-02-17","cited_by_count":2,"area":"distill"},{"id":"2409.04778","title":"LoCa: Logit Calibration for Knowledge Distillation","created":"2024-09-07","cited_by_count":2,"area":"distill"},{"id":"2410.06561","title":"Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching","created":"2024-10-09","cited_by_count":2,"area":"distill"},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2506.18244","title":"Dual-Forward Path Teacher Knowledge Distillation: Bridging the Capacity Gap Between Teacher and Student","created":"2025-06-23","cited_by_count":2,"area":"distill"},{"id":"2510.07924","title":"Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers","created":"2025-10-09","cited_by_count":2,"area":"distill"},{"id":"2511.06848","title":"Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers","created":"2025-11-10","cited_by_count":2,"area":"distill"},{"id":"2406.08226","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","created":"2024-06-12","cited_by_count":1,"area":"distill"},{"id":"2408.05748","title":"Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation","created":"2024-08-11","cited_by_count":1,"area":"distill"},{"id":"2408.05952","title":"Optimizing Vision Transformers with Data-Free Knowledge Transfer","created":"2024-08-12","cited_by_count":1,"area":"distill"},{"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":"2408.11478","title":"LAKD-Activation Mapping Distillation Based on Local Learning","created":"2024-08-21","cited_by_count":1,"area":"distill"},{"id":"2409.01679","title":"Adaptive Explicit Knowledge Transfer for Knowledge Distillation","created":"2024-09-03","cited_by_count":1,"area":"distill"},{"id":"2409.18565","title":"Harmonizing knowledge Transfer in Neural Network with Unified Distillation","created":"2024-09-27","cited_by_count":1,"area":"distill"},{"id":"2410.14741","title":"CAKD: A Correlation-Aware Knowledge Distillation Framework Based on Decoupling Kullback-Leibler Divergence","created":"2024-10-17","cited_by_count":1,"area":"distill"},{"id":"2410.21085","title":"KA$^2$ER: Knowledge Adaptive Amalgamation of ExpeRts for Medical Images Segmentation","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2509.12633","title":"CIARD: Cyclic Iterative Adversarial Robustness Distillation","created":"2025-09-16","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":"2606.25488","title":"Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning","created":"2026-06-24","cited_by_count":1,"area":"distill"},{"id":"2403.14494","title":"Learning to Project for Cross-Task Knowledge Distillation","created":"2024-03-21","cited_by_count":0,"area":"distill"},{"id":"2404.19639","title":"ESP-Zero: Unsupervised enhancement of zero-shot classification for Extremely Sparse Point cloud","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2409.02020","title":"Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique","created":"2024-09-03","cited_by_count":0,"area":"distill"},{"id":"2410.04140","title":"Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher","created":"2024-10-05","cited_by_count":0,"area":"distill"},{"id":"2505.06995","title":"KDC-Diff: A Latent-Aware Diffusion Model with Knowledge Retention for Memory-Efficient Image Generation","created":"2025-05-11","cited_by_count":0,"area":"diffusion"},{"id":"2505.08170","title":"MoKD: Multi-Task Optimization for Knowledge Distillation","created":"2025-05-13","cited_by_count":0,"area":"distill"},{"id":"2507.12780","title":"Compact Vision Transformer by Reduction of Kernel Complexity","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2509.12553","title":"iCD: A Implicit Clustering Distillation Mathod for Structural Information Mining","created":"2025-09-16","cited_by_count":0,"area":"distill"},{"id":"2510.06254","title":"Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training","created":"2025-10-04","cited_by_count":0,"area":"distill"},{"id":"2511.10942","title":"Heterogeneous Complementary Distillation","created":"2025-11-14","cited_by_count":0,"area":"distill"},{"id":"2512.04625","title":"Rethinking Decoupled Knowledge Distillation: A Predictive Distribution Perspective","created":"2025-12-04","cited_by_count":0,"area":"distill"},{"id":"2601.12312","title":"CurConMix+: A Unified Spatio-Temporal Framework for Hierarchical Surgical Workflow Understanding","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2602.04699","title":"Annotation Free Spacecraft Detection and Segmentation using Vision Language Models","created":"2026-02-04","cited_by_count":0,"area":"mllm"},{"id":"2602.19822","title":"Efficient endometrial carcinoma screening via cross-modal synthesis and gradient distillation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2606.03052","title":"What Do Students Learn? A Feature-Level Analysis of Dark Knowledge","created":"2026-06-02","cited_by_count":0,"area":"distill"},{"id":"2606.06864","title":"LRMIL: Efficient Low-Resolution Multiple Instance Learning via High-Resolution Knowledge Distillation for Whole Slide Image Classification","created":"2026-06-05","cited_by_count":0,"area":"distill"},{"id":"2608.03100","title":"Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition","created":"2026-08-04","cited_by_count":0,"area":"distill"},{"id":"2609.08090","title":"RevalExo: A Functional Daily-Activity Benchmark for Inertial and Visual Locomotion Mode Recognition in Older Adults and Clinical Cohorts","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.13199","title":"Discovering and Preserving Category Correlation Knowledge via Adaptive Reciprocal Knowledge Distillation","created":"2026-08-14","cited_by_count":0,"area":"distill"}],"next_cursor":null}