{"total":238,"rows":[{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395,"area":"agents"},{"id":"2311.17245","title":"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS","created":"2023-11-28","cited_by_count":436,"area":null},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388,"area":"distill"},{"id":"2101.05930","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","created":"2021-01-15","cited_by_count":324,"area":null},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208,"area":"distill"},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141,"area":"distill"},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134,"area":"distill"},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118,"area":null},{"id":"2103.02340","title":"General Instance Distillation for Object Detection","created":"2021-03-03","cited_by_count":114,"area":"distill"},{"id":"2103.14475","title":"Distilling Object Detectors via Decoupled Features","created":"2021-03-26","cited_by_count":106,"area":"distill"},{"id":"2308.13320","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","created":"2023-08-25","cited_by_count":96,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2203.17261","title":"R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis","created":"2022-03-31","cited_by_count":69,"area":null},{"id":"2204.12997","title":"DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers","created":"2022-04-27","cited_by_count":65,"area":"distill"},{"id":"2106.04570","title":"BERT Learns to Teach: Knowledge Distillation with Meta Learning","created":"2021-06-08","cited_by_count":61,"area":"distill"},{"id":"2102.07650","title":"Learning Student-Friendly Teacher Networks for Knowledge Distillation","created":"2021-02-12","cited_by_count":60,"area":"distill"},{"id":"2305.13948","title":"Decoupled Kullback-Leibler Divergence Loss","created":"2023-05-23","cited_by_count":58,"area":"distill"},{"id":"2507.02939","title":"Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting","created":"2025-06-27","cited_by_count":55,"area":"distill"},{"id":"2312.16475","title":"Federated Continual Learning via Knowledge Fusion: A Survey","created":"2023-12-27","cited_by_count":53,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47,"area":"distill"},{"id":"2107.13715","title":"Hierarchical Self-supervised Augmented Knowledge Distillation","created":"2021-07-29","cited_by_count":44,"area":"distill"},{"id":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44,"area":"distill"},{"id":"2103.16367","title":"Complementary Relation Contrastive Distillation","created":"2021-03-29","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":"2207.02039","title":"PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient","created":"2022-07-05","cited_by_count":41,"area":"distill"},{"id":"2207.05273","title":"Cross-Architecture Knowledge Distillation","created":"2022-07-12","cited_by_count":41,"area":"distill"},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2111.00674","title":"Distilling Object Detectors with Feature Richness","created":"2021-11-01","cited_by_count":38,"area":null},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38,"area":"distill"},{"id":"2106.03310","title":"Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model","created":"2021-06-07","cited_by_count":37,"area":"distill"},{"id":"2207.11518","title":"Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition","created":"2022-07-23","cited_by_count":36,"area":"distill"},{"id":"2208.12256","title":"Masked Autoencoders Enable Efficient Knowledge Distillers","created":"2022-08-25","cited_by_count":36,"area":"distill"},{"id":"2207.10026","title":"Locality Guidance for Improving Vision Transformers on Tiny Datasets","created":"2022-07-20","cited_by_count":33,"area":null},{"id":"2103.13811","title":"Student Network Learning via Evolutionary Knowledge Distillation","created":"2021-03-23","cited_by_count":30,"area":"distill"},{"id":"2205.15156","title":"Towards Efficient 3D Object Detection with Knowledge Distillation","created":"2022-05-30","cited_by_count":29,"area":"distill"},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29,"area":"distill"},{"id":"2403.05061","title":"RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features","created":"2024-03-08","cited_by_count":28,"area":"distill"},{"id":"2408.05088","title":"UNIC: Universal Classification Models via Multi-teacher Distillation","created":"2024-08-09","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":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"area":"distill"},{"id":"2301.01296","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","created":"2023-01-03","cited_by_count":24,"area":null},{"id":"2104.10510","title":"Balanced Knowledge Distillation for Long-tailed Learning","created":"2021-04-21","cited_by_count":23,"area":"distill"},{"id":"2204.11830","title":"Proto2Proto: Can you recognize the car, the way I do?","created":"2022-04-25","cited_by_count":23,"area":null},{"id":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"id":"2210.16103","title":"Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks","created":"2022-10-27","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":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","cited_by_count":22,"area":null},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22,"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":"2201.05131","title":"SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation","created":"2022-01-13","cited_by_count":21,"area":"distill"},{"id":"2203.05180","title":"Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability","created":"2022-03-10","cited_by_count":21,"area":"distill"},{"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":"2107.08591","title":"Double Similarity Distillation for Semantic Image Segmentation","created":"2021-07-19","cited_by_count":19,"area":null},{"id":"2108.12905","title":"Lipschitz Continuity Guided Knowledge Distillation","created":"2021-08-29","cited_by_count":19,"area":"distill"},{"id":"2112.00459","title":"Information Theoretic Representation Distillation","created":"2021-12-01","cited_by_count":19,"area":"distill"},{"id":"2206.05794","title":"SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network","created":"2022-06-12","cited_by_count":19,"area":null},{"id":"2210.12787","title":"Respecting Transfer Gap in Knowledge Distillation","created":"2022-10-23","cited_by_count":18,"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":"2411.02793","title":"Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning","created":"2024-11-05","cited_by_count":16,"area":null},{"id":"2107.00181","title":"Revisiting Knowledge Distillation: An Inheritance and Exploration Framework","created":"2021-07-01","cited_by_count":15,"area":"distill"},{"id":"2306.08075","title":"BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation","created":"2023-06-13","cited_by_count":15,"area":"distill"},{"id":"2402.17110","title":"Sinkhorn Distance Minimization for Knowledge Distillation","created":"2024-02-27","cited_by_count":15,"area":"distill"},{"id":"2109.03075","title":"Knowledge Distillation Using Hierarchical Self-Supervision Augmented Distribution","created":"2021-09-07","cited_by_count":13,"area":"distill"},{"id":"2111.06945","title":"Learning Interpretation with Explainable Knowledge Distillation","created":"2021-11-12","cited_by_count":13,"area":"distill"},{"id":"2303.17144","title":"DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving","created":"2023-03-30","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":"2205.14280","title":"Fast Object Placement Assessment","created":"2022-05-28","cited_by_count":12,"area":null},{"id":"2207.05345","title":"HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors","created":"2022-07-12","cited_by_count":12,"area":"distill"},{"id":"2212.09042","title":"Gait Recognition Using 3-D Human Body Shape Inference","created":"2022-12-18","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":"2105.04181","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","created":"2021-05-10","cited_by_count":11,"area":"distill"},{"id":"2305.10893","title":"Student-friendly Knowledge Distillation","created":"2023-05-18","cited_by_count":11,"area":"distill"},{"id":"2309.13220","title":"Poster: Self-Supervised Quantization-Aware Knowledge Distillation","created":"2023-09-22","cited_by_count":11,"area":"distill"},{"id":"2310.10429","title":"Exploiting User Comments for Early Detection of Fake News Prior to Users' Commenting","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2403.07854","title":"Distilling the Knowledge in Data Pruning","created":"2024-03-12","cited_by_count":11,"area":"distill"},{"id":"2411.06786","title":"ScaleKD: Strong Vision Transformers Could Be Excellent Teachers","created":"2024-11-11","cited_by_count":11,"area":"distill"},{"id":"2104.03164","title":"Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression","created":"2021-04-07","cited_by_count":10,"area":"distill"},{"id":"2210.04153","title":"Stimulative Training of Residual Networks: A Social Psychology Perspective of Loafing","created":"2022-10-09","cited_by_count":10,"area":null},{"id":"2111.05073","title":"MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps","created":"2021-11-09","cited_by_count":9,"area":null},{"id":"2205.06701","title":"Knowledge Distillation Meets Open-Set Semi-Supervised Learning","created":"2022-05-13","cited_by_count":9,"area":"distill"},{"id":"2209.03355","title":"Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation","created":"2022-09-07","cited_by_count":9,"area":"distill"},{"id":"2311.01441","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","created":"2023-11-02","cited_by_count":9,"area":"mllm"},{"id":"2405.15170","title":"Label-efficient Semantic Scene Completion with Scribble Annotations","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2406.09117","title":"PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation","created":"2024-06-13","cited_by_count":9,"area":"distill"},{"id":"2408.07703","title":"Knowledge Distillation with Refined Logits","created":"2024-08-14","cited_by_count":9,"area":"distill"},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2410.07133","title":"EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models","created":"2024-10-09","cited_by_count":9,"area":"mllm"},{"id":"2410.19503","title":"SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models","created":"2024-10-25","cited_by_count":9,"area":"distill"},{"id":"2108.05045","title":"Semi-Supervised Domain Generalizable Person Re-Identification","created":"2021-08-11","cited_by_count":8,"area":null},{"id":"2201.06945","title":"It's All in the Head: Representation Knowledge Distillation through Classifier Sharing","created":"2022-01-18","cited_by_count":8,"area":"distill"},{"id":"2305.19412","title":"Are Large Kernels Better Teachers than Transformers for ConvNets?","created":"2023-05-30","cited_by_count":8,"area":"distill"},{"id":"2403.08215","title":"LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving","created":"2024-03-13","cited_by_count":8,"area":"distill"},{"id":"2102.11638","title":"Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation","created":"2021-02-23","cited_by_count":7,"area":"distill"},{"id":"2206.06661","title":"Toward Student-Oriented Teacher Network Training For Knowledge Distillation","created":"2022-06-14","cited_by_count":7,"area":"distill"},{"id":"2301.01615","title":"StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection","created":"2023-01-04","cited_by_count":7,"area":null},{"id":"2304.01636","title":"Label-guided Attention Distillation for Lane Segmentation","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2305.05233","title":"DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizing","created":"2023-05-09","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"}],"next_cursor":"100"}