{"total":316,"rows":[{"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":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164,"area":null},{"id":"2103.04257","title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","created":"2021-03-07","cited_by_count":146,"area":null},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141,"area":"distill"},{"id":"2303.08233","title":"NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions","created":"2023-03-14","cited_by_count":135,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2403.01427","title":"Logit Standardization in Knowledge Distillation","created":"2024-03-03","cited_by_count":102,"area":"distill"},{"id":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","cited_by_count":73,"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":"2407.01885","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","created":"2024-07-02","cited_by_count":56,"area":"distill"},{"id":"2305.06360","title":"Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy","created":"2023-05-10","cited_by_count":51,"area":"safety"},{"id":"2103.01396","title":"DeepReDuce: ReLU Reduction for Fast Private Inference","created":"2021-03-02","cited_by_count":50,"area":null},{"id":"2112.01528","title":"A Fast Knowledge Distillation Framework for Visual Recognition","created":"2021-12-02","cited_by_count":50,"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":"2110.10394","title":"Deep Learning for HDR Imaging: State-of-the-Art and Future Trends","created":"2021-10-20","cited_by_count":45,"area":null},{"id":"2206.06487","title":"The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation","created":"2022-06-13","cited_by_count":44,"area":"distill"},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38,"area":"distill"},{"id":"2108.01958","title":"Learning Compatible Embeddings","created":"2021-08-04","cited_by_count":37,"area":null},{"id":"2404.16038","title":"A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming","created":"2024-01-30","cited_by_count":37,"area":null},{"id":"2307.12574","title":"A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation","created":"2023-07-24","cited_by_count":33,"area":"distill"},{"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":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","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":"2112.15278","title":"Data-Free Knowledge Transfer: A Survey","created":"2021-12-31","cited_by_count":31,"area":"distill"},{"id":"2308.14731","title":"Distilled GPT for Source Code Summarization","created":"2023-08-28","cited_by_count":31,"area":null},{"id":"2406.18937","title":"Federated Graph Semantic and Structural Learning","created":"2024-06-27","cited_by_count":30,"area":null},{"id":"2203.16172","title":"Self-Distillation from the Last Mini-Batch for Consistency Regularization","created":"2022-03-30","cited_by_count":29,"area":"distill"},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28,"area":"distill"},{"id":"2111.12624","title":"Self-slimmed Vision Transformer","created":"2021-11-24","cited_by_count":27,"area":null},{"id":"2103.14431","title":"Multimodal Knowledge Expansion","created":"2021-03-26","cited_by_count":26,"area":"distill"},{"id":"2208.12807","title":"Towards Federated Learning against Noisy Labels via Local Self-Regularization","created":"2022-08-25","cited_by_count":26,"area":null},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26,"area":"distill"},{"id":"2112.04185","title":"Transformaly -- Two (Feature Spaces) Are Better Than One","created":"2021-12-08","cited_by_count":25,"area":"distill"},{"id":"2108.06908","title":"Online Multi-Granularity Distillation for GAN Compression","created":"2021-08-16","cited_by_count":24,"area":null},{"id":"2408.08753","title":"PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders","created":"2024-08-16","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":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23,"area":null},{"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":"2210.17332","title":"Teacher-Student Architecture for Knowledge Learning: A Survey","created":"2022-10-28","cited_by_count":23,"area":"distill"},{"id":"2307.09158","title":"Class-relation Knowledge Distillation for Novel Class Discovery","created":"2023-07-18","cited_by_count":23,"area":"distill"},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2103.14473","title":"Distilling a Powerful Student Model via Online Knowledge Distillation","created":"2021-03-26","cited_by_count":22,"area":"distill"},{"id":"2204.07028","title":"Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation","created":"2022-04-14","cited_by_count":22,"area":null},{"id":"2311.11646","title":"Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning","created":"2023-11-20","cited_by_count":22,"area":null},{"id":"2504.09228","title":"Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking","created":"2025-04-12","cited_by_count":22,"area":null},{"id":"2301.01197","title":"Backdoor Attacks Against Dataset Distillation","created":"2023-01-03","cited_by_count":21,"area":null},{"id":"2304.11832","title":"Function-Consistent Feature Distillation","created":"2023-04-24","cited_by_count":21,"area":"distill"},{"id":"2310.14277","title":"A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application","created":"2023-10-22","cited_by_count":21,"area":null},{"id":"2303.14243","title":"DyLiN: Making Light Field Networks Dynamic","created":"2023-03-24","cited_by_count":20,"area":null},{"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":"2405.16108","title":"OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2206.01859","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","created":"2022-06-04","cited_by_count":19,"area":"distill"},{"id":"2207.13316","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","created":"2022-07-27","cited_by_count":19,"area":null},{"id":"2504.09039","title":"Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization","created":"2025-04-12","cited_by_count":19,"area":"diffusion"},{"id":"2207.08739","title":"Rethinking Data Augmentation for Robust Visual Question Answering","created":"2022-07-18","cited_by_count":18,"area":"distill"},{"id":"2310.07265","title":"Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation","created":"2023-10-11","cited_by_count":18,"area":"distill"},{"id":"2112.05005","title":"Mutual Adversarial Training: Learning together is better than going alone","created":"2021-12-09","cited_by_count":17,"area":null},{"id":"2202.13393","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","created":"2022-02-27","cited_by_count":17,"area":"distill"},{"id":"2301.00389","title":"FedICT: Federated Multi-task Distillation for Multi-access Edge Computing","created":"2023-01-01","cited_by_count":17,"area":"distill"},{"id":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"area":null},{"id":"2105.06143","title":"Boosting Light-Weight Depth Estimation Via Knowledge Distillation","created":"2021-05-13","cited_by_count":16,"area":"distill"},{"id":"2209.02178","title":"Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students","created":"2022-09-06","cited_by_count":16,"area":null},{"id":"2311.18237","title":"Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2106.00320","title":"Distribution Matching for Rationalization","created":"2021-06-01","cited_by_count":14,"area":null},{"id":"2209.00347","title":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","created":"2022-09-01","cited_by_count":14,"area":null},{"id":"2211.13133","title":"Structural Knowledge Distillation for Object Detection","created":"2022-11-23","cited_by_count":14,"area":"distill"},{"id":"2308.08463","title":"Learning to Distill Global Representation for Sparse-View CT","created":"2023-08-16","cited_by_count":14,"area":null},{"id":"2310.04999","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","created":"2023-10-08","cited_by_count":14,"area":"distill"},{"id":"2406.00474","title":"Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truth","created":"2024-06-01","cited_by_count":14,"area":null},{"id":"2203.15792","title":"Target and Task specific Source-Free Domain Adaptive Image Segmentation","created":"2022-03-29","cited_by_count":13,"area":null},{"id":"2309.16173","title":"Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation","created":"2023-09-28","cited_by_count":13,"area":"safety"},{"id":"2403.17369","title":"CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning","created":"2024-03-26","cited_by_count":13,"area":null},{"id":"2109.02426","title":"Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervision","created":"2021-09-03","cited_by_count":12,"area":null},{"id":"2203.11490","title":"SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images","created":"2022-03-22","cited_by_count":12,"area":"distill"},{"id":"2204.00771","title":"Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation","created":"2022-04-02","cited_by_count":12,"area":"distill"},{"id":"2210.17258","title":"Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples","created":"2022-10-31","cited_by_count":12,"area":"distill"},{"id":"2210.17449","title":"Globally Gated Deep Linear Networks","created":"2022-10-31","cited_by_count":12,"area":null},{"id":"2302.10681","title":"FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing","created":"2023-02-21","cited_by_count":12,"area":null},{"id":"2309.15413","title":"Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory","created":"2023-09-27","cited_by_count":12,"area":"distill"},{"id":"2402.06330","title":"Continual Learning on Graphs: A Survey","created":"2024-02-09","cited_by_count":12,"area":null},{"id":"2404.14827","title":"Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation","created":"2024-04-23","cited_by_count":12,"area":"distill"},{"id":"2102.13088","title":"Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation","created":"2021-02-25","cited_by_count":11,"area":"distill"},{"id":"2202.05659","title":"Tiny Object Tracking: A Large-scale Dataset and A Baseline","created":"2022-02-11","cited_by_count":11,"area":"distill"},{"id":"2203.05683","title":"Deep Multimodal Guidance for Medical Image Classification","created":"2022-03-10","cited_by_count":11,"area":null},{"id":"2210.07548","title":"Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection","created":"2022-10-14","cited_by_count":11,"area":null},{"id":"2212.07959","title":"Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls","created":"2022-12-15","cited_by_count":11,"area":null},{"id":"2306.14818","title":"Accelerating Molecular Graph Neural Networks via Knowledge Distillation","created":"2023-06-26","cited_by_count":11,"area":"distill"},{"id":"2312.05019","title":"Vision-based Learning for Drones: A Survey","created":"2023-12-08","cited_by_count":11,"area":null},{"id":"2408.09115","title":"GoodSAM++: Bridging Domain and Capacity Gaps via Segment Anything Model for Panoramic Semantic Segmentation","created":"2024-08-17","cited_by_count":11,"area":null},{"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":"2306.15110","title":"Deep Transfer Learning for Intelligent Vehicle Perception: a Survey","created":"2023-06-26","cited_by_count":10,"area":null},{"id":"2308.01698","title":"Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning","created":"2023-08-03","cited_by_count":10,"area":null},{"id":"2312.11489","title":"Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration","created":"2023-12-01","cited_by_count":10,"area":null},{"id":"2401.08139","title":"Transferring Core Knowledge via Learngenes","created":"2024-01-16","cited_by_count":10,"area":null},{"id":"2106.14014","title":"Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text","created":"2021-06-26","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"}],"next_cursor":"100"}