{"total":260,"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":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388,"area":"distill"},{"id":"2104.09044","title":"Distilling Knowledge via Knowledge Review","created":"2021-04-19","cited_by_count":288,"area":"distill"},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208,"area":"distill"},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169,"area":null},{"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":"2102.00650","title":"Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective","created":"2021-02-01","cited_by_count":119,"area":"distill"},{"id":"2103.14475","title":"Distilling Object Detectors via Decoupled Features","created":"2021-03-26","cited_by_count":106,"area":"distill"},{"id":"2107.03358","title":"Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation","created":"2021-07-07","cited_by_count":104,"area":"distill"},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2102.02973","title":"Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching","created":"2021-02-05","cited_by_count":79,"area":"distill"},{"id":"2108.08258","title":"LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector","created":"2021-08-18","cited_by_count":70,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"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":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58,"area":"distill"},{"id":"2305.13948","title":"Decoupled Kullback-Leibler Divergence Loss","created":"2023-05-23","cited_by_count":58,"area":"distill"},{"id":"2108.02092","title":"Online Knowledge Distillation for Efficient Pose Estimation","created":"2021-08-04","cited_by_count":55,"area":"distill"},{"id":"2103.12369","title":"ReCU: Reviving the Dead Weights in Binary Neural Networks","created":"2021-03-23","cited_by_count":52,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2306.11369","title":"CrossKD: Cross-Head Knowledge Distillation for Object Detection","created":"2023-06-20","cited_by_count":52,"area":"distill"},{"id":"2111.12341","title":"EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation","created":"2021-11-24","cited_by_count":47,"area":"distill"},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47,"area":"distill"},{"id":"2103.08273","title":"Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation","created":"2021-03-15","cited_by_count":46,"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":"2207.05273","title":"Cross-Architecture Knowledge Distillation","created":"2022-07-12","cited_by_count":41,"area":"distill"},{"id":"2309.12530","title":"A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance","created":"2023-09-21","cited_by_count":40,"area":"mllm"},{"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":"2210.05801","title":"Linkless Link Prediction via Relational Distillation","created":"2022-10-11","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":"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":"2108.01958","title":"Learning Compatible Embeddings","created":"2021-08-04","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":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2104.04687","title":"Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining","created":"2021-04-10","cited_by_count":33,"area":null},{"id":"2303.03446","title":"Students Parrot Their Teachers: Membership Inference on Model Distillation","created":"2023-03-06","cited_by_count":33,"area":"safety"},{"id":"2109.01801","title":"Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation","created":"2021-09-04","cited_by_count":32,"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":"2103.13811","title":"Student Network Learning via Evolutionary Knowledge Distillation","created":"2021-03-23","cited_by_count":30,"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":"2303.18232","title":"DIME-FM: DIstilling Multimodal and Efficient Foundation Models","created":"2023-03-31","cited_by_count":28,"area":"mllm"},{"id":"2111.12624","title":"Self-slimmed Vision Transformer","created":"2021-11-24","cited_by_count":27,"area":null},{"id":"2210.15274","title":"Improved Feature Distillation via Projector Ensemble","created":"2022-10-27","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":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","cited_by_count":24,"area":"distill"},{"id":"2210.04208","title":"Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis","created":"2022-10-09","cited_by_count":24,"area":null},{"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":"2405.03008","title":"DVMSR: Distillated Vision Mamba for Efficient Super-Resolution","created":"2024-05-05","cited_by_count":24,"area":"ssm"},{"id":"2502.07942","title":"Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs","created":"2025-02-11","cited_by_count":24,"area":"agents"},{"id":"2210.17332","title":"Teacher-Student Architecture for Knowledge Learning: A Survey","created":"2022-10-28","cited_by_count":23,"area":"distill"},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22,"area":"distill"},{"id":"2210.13014","title":"Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks","created":"2022-10-24","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":"2106.14681","title":"PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation","created":"2021-06-25","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":"2305.12954","title":"Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?","created":"2023-05-22","cited_by_count":21,"area":"diffusion"},{"id":"2410.01680","title":"PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation","created":"2024-10-02","cited_by_count":21,"area":"distill"},{"id":"2202.07940","title":"Meta Knowledge Distillation","created":"2022-02-16","cited_by_count":20,"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":"2204.05957","title":"Localization Distillation for Object Detection","created":"2022-04-12","cited_by_count":19,"area":"distill"},{"id":"2306.10014","title":"Coaching a Teachable Student","created":"2023-06-16","cited_by_count":19,"area":"distill"},{"id":"2210.12787","title":"Respecting Transfer Gap in Knowledge Distillation","created":"2022-10-23","cited_by_count":18,"area":"distill"},{"id":"2301.13156","title":"SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition","created":"2023-01-30","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":"2412.09912","title":"All-in-One: Transferring Vision Foundation Models into Stereo Matching","created":"2024-12-13","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":"2208.03767","title":"Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer","created":"2022-08-07","cited_by_count":15,"area":null},{"id":"2306.08075","title":"BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation","created":"2023-06-13","cited_by_count":15,"area":"distill"},{"id":"2401.15489","title":"Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport","created":"2024-01-27","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":"2111.12958","title":"Self-Distilled Self-Supervised Representation Learning","created":"2021-11-25","cited_by_count":14,"area":"distill"},{"id":"2205.15531","title":"itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection","created":"2022-05-31","cited_by_count":14,"area":"distill"},{"id":"2207.12106","title":"Black-box Few-shot Knowledge Distillation","created":"2022-07-25","cited_by_count":14,"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":"2505.19504","title":"DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation","created":"2025-05-26","cited_by_count":14,"area":"distill"},{"id":"2110.09910","title":"FedHe: Heterogeneous Models and Communication-Efficient Federated Learning","created":"2021-10-19","cited_by_count":13,"area":null},{"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":"2206.14366","title":"Knowledge Distillation of Transformer-based Language Models Revisited","created":"2022-06-29","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":"2306.07646","title":"Enhanced Multimodal Representation Learning with Cross-modal KD","created":"2023-06-13","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":"2205.06701","title":"Knowledge Distillation Meets Open-Set Semi-Supervised Learning","created":"2022-05-13","cited_by_count":9,"area":"distill"},{"id":"2308.14852","title":"SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data","created":"2023-08-28","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"}],"next_cursor":"100"}