{"total":66,"rows":[{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388,"area":"distill"},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2201.00766","title":"Class-Incremental Continual Learning into the eXtended DER-verse","created":"2022-01-03","cited_by_count":124,"area":"distill"},{"id":"2103.02340","title":"General Instance Distillation for Object Detection","created":"2021-03-03","cited_by_count":114,"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":"2110.12724","title":"Instance-Conditional Knowledge Distillation for Object Detection","created":"2021-10-25","cited_by_count":42,"area":"distill"},{"id":"2206.06067","title":"Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation","created":"2022-06-13","cited_by_count":41,"area":"distill"},{"id":"2207.09679","title":"Explaining Deepfake Detection by Analysing Image Matching","created":"2022-07-20","cited_by_count":34,"area":null},{"id":"2103.13811","title":"Student Network Learning via Evolutionary Knowledge Distillation","created":"2021-03-23","cited_by_count":30,"area":"distill"},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29,"area":"distill"},{"id":"2107.02629","title":"Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation","created":"2021-07-06","cited_by_count":29,"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":"2111.14353","title":"Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillation","created":"2021-11-29","cited_by_count":23,"area":"distill"},{"id":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"id":"2210.17332","title":"Teacher-Student Architecture for Knowledge Learning: A Survey","created":"2022-10-28","cited_by_count":23,"area":"distill"},{"id":"2301.13304","title":"Understanding Self-Distillation in the Presence of Label Noise","created":"2023-01-30","cited_by_count":21,"area":"distill"},{"id":"2208.08741","title":"Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification","created":"2022-08-18","cited_by_count":19,"area":"distill"},{"id":"2205.11678","title":"Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation","created":"2022-05-24","cited_by_count":18,"area":"distill"},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2206.03970","title":"Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting","created":"2022-06-08","cited_by_count":10,"area":null},{"id":"2307.05350","title":"Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat","created":"2023-07-07","cited_by_count":10,"area":null},{"id":"2311.13621","title":"EA-KD: Entropy-based Adaptive Knowledge Distillation","created":"2023-11-22","cited_by_count":8,"area":"distill"},{"id":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2310.13215","title":"Zone Evaluation: Revealing Spatial Bias in Object Detection","created":"2023-10-20","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":"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":"2302.14643","title":"Graph-based Knowledge Distillation: A survey and experimental evaluation","created":"2023-02-27","cited_by_count":6,"area":"distill"},{"id":"2303.09230","title":"Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval","created":"2023-03-16","cited_by_count":6,"area":"distill"},{"id":"2404.09326","title":"Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers","created":"2024-04-14","cited_by_count":6,"area":"distill"},{"id":"2412.15255","title":"Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation","created":"2024-12-15","cited_by_count":6,"area":"distill"},{"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":"2405.13078","title":"Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch","created":"2024-05-21","cited_by_count":4,"area":"distill"},{"id":"2205.00179","title":"Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization","created":"2022-04-30","cited_by_count":3,"area":null},{"id":"2410.22184","title":"Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets","created":"2024-10-29","cited_by_count":3,"area":"distill"},{"id":"2307.06631","title":"Frameless Graph Knowledge Distillation","created":"2023-07-13","cited_by_count":2,"area":"distill"},{"id":"2307.13698","title":"Exploring the Lottery Ticket Hypothesis with Explainability Methods: Insights into Sparse Network Performance","created":"2023-07-07","cited_by_count":2,"area":null},{"id":"2507.11099","title":"A Survey on Interpretability in Visual Recognition","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2605.01732","title":"EGAD: Entropy-Guided Adaptive Distillation for Token-Level Knowledge Transfer","created":"2026-05-03","cited_by_count":2,"area":null},{"id":"2103.12388","title":"Joint framework with deep feature distillation and adaptive focal loss for weakly supervised audio tagging and acoustic event detection","created":"2021-03-23","cited_by_count":1,"area":"distill"},{"id":"2103.14337","title":"Hands-on Guidance for Distilling Object Detectors","created":"2021-03-26","cited_by_count":1,"area":"distill"},{"id":"2109.02137","title":"Efficient Action Recognition Using Confidence Distillation","created":"2021-09-05","cited_by_count":1,"area":null},{"id":"2109.12507","title":"Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better","created":"2021-09-26","cited_by_count":1,"area":"distill"},{"id":"2112.01948","title":"Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning","created":"2021-12-03","cited_by_count":1,"area":null},{"id":"2210.09668","title":"On effects of Knowledge Distillation on Transfer Learning","created":"2022-10-18","cited_by_count":1,"area":"distill"},{"id":"2302.12360","title":"Practical Knowledge Distillation: Using DNNs to Beat DNNs","created":"2023-02-23","cited_by_count":1,"area":"distill"},{"id":"2305.06155","title":"Leveraging Synthetic Targets for Machine Translation","created":"2023-05-07","cited_by_count":1,"area":null},{"id":"2411.10693","title":"Multi-perspective Contrastive Logit Distillation","created":"2024-11-16","cited_by_count":1,"area":"distill"},{"id":"2102.00369","title":"Spectral Roll-off Points Variations: Exploring Useful Information in Feature Maps by Its Variations","created":"2021-01-31","cited_by_count":0,"area":null},{"id":"2106.09517","title":"Dynamic Knowledge Distillation With Noise Elimination for RGB-D Salient Object Detection","created":"2021-06-17","cited_by_count":0,"area":"distill"},{"id":"2110.04483","title":"Visualizing the embedding space to explain the effect of knowledge distillation","created":"2021-10-09","cited_by_count":0,"area":"distill"},{"id":"2205.14606","title":"A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks","created":"2022-05-29","cited_by_count":0,"area":null},{"id":"2304.11923","title":"Improving Knowledge Distillation via Transferring Learning Ability","created":"2023-04-24","cited_by_count":0,"area":"distill"},{"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":"2402.07119","title":"Two-Stage Multi-task Self-Supervised Learning for Medical Image Segmentation","created":"2024-02-11","cited_by_count":0,"area":null},{"id":"2403.14362","title":"Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM Semantics","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2403.18253","title":"Enhancing Metaphor Detection through Soft Labels and Target Word Prediction","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2406.17838","title":"InFiConD: Interactive No-code Fine-tuning with Concept-based Knowledge Distillation","created":"2024-06-25","cited_by_count":0,"area":"distill"},{"id":"2501.17813","title":"P-TAME: Explain Any Image Classifier with Trained Perturbations","created":"2025-01-29","cited_by_count":0,"area":null},{"id":"2502.16762","title":"A Transformer-in-Transformer Network Utilizing Knowledge Distillation for Image Recognition","created":"2025-02-24","cited_by_count":0,"area":"distill"},{"id":"2508.04539","title":"TopKD: Top-scaled Knowledge Distillation","created":"2025-08-06","cited_by_count":0,"area":"distill"},{"id":"2510.13182","title":"Information-Theoretic Criteria for Knowledge Distillation in Multimodal Learning","created":"2025-10-15","cited_by_count":0,"area":"distill"},{"id":"2605.01563","title":"Multi-Dataset Cross-Domain Knowledge Distillation for Unified Medical Image Segmentation, Classification, and Detection","created":"2026-05-02","cited_by_count":0,"area":"distill"},{"id":"2606.27729","title":"Learning 1-Bit LiDAR-based Localization with Auxiliary Objective","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.08776","title":"A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions","created":"2026-05-05","cited_by_count":0,"area":"distill"},{"id":"2607.29071","title":"Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.23752","title":"Too much of a good thing -- when knowledge distillation promotes overfitting, and how to avoid it","created":"2026-08-24","cited_by_count":0,"area":"distill"}],"next_cursor":null}