{"total":87,"rows":[{"id":"2102.01063","title":"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition","created":"2021-02-01","cited_by_count":73,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2203.15610","title":"LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT","created":"2022-03-29","cited_by_count":50,"area":null},{"id":"2202.07105","title":"A Survey on Model Compression and Acceleration for Pretrained Language Models","created":"2022-02-15","cited_by_count":45,"area":null},{"id":"2103.01353","title":"There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge","created":"2021-03-01","cited_by_count":44,"area":"distill"},{"id":"2206.00388","title":"Transfer without Forgetting","created":"2022-06-01","cited_by_count":44,"area":null},{"id":"2109.05427","title":"Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification","created":"2021-09-12","cited_by_count":43,"area":null},{"id":"2207.05273","title":"Cross-Architecture Knowledge Distillation","created":"2022-07-12","cited_by_count":41,"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":"2302.09632","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","created":"2023-02-19","cited_by_count":25,"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":"2203.12758","title":"Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models","created":"2022-03-23","cited_by_count":19,"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":"2306.10014","title":"Coaching a Teachable Student","created":"2023-06-16","cited_by_count":19,"area":"distill"},{"id":"2106.04563","title":"XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2309.02870","title":"Rethinking Momentum Knowledge Distillation in Online Continual Learning","created":"2023-09-06","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":"2306.06629","title":"GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model","created":"2023-06-11","cited_by_count":15,"area":"distill"},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2505.17604","title":"Adaptive Semantic Token Communication for Transformer-based Edge Inference","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2605.07721","title":"Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models","created":"2026-05-08","cited_by_count":14,"area":"inference"},{"id":"2209.11204","title":"Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training","created":"2022-09-22","cited_by_count":11,"area":null},{"id":"2211.11014","title":"Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer Encoders","created":"2022-11-20","cited_by_count":11,"area":"distill"},{"id":"2301.12005","title":"EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval","created":"2023-01-27","cited_by_count":11,"area":"distill"},{"id":"2306.14818","title":"Accelerating Molecular Graph Neural Networks via Knowledge Distillation","created":"2023-06-26","cited_by_count":11,"area":"distill"},{"id":"2405.02330","title":"Adaptive Semantic Token Selection for AI-native Goal-oriented Communications","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2205.11152","title":"Cross-lingual Lifelong Learning","created":"2022-05-23","cited_by_count":9,"area":null},{"id":"2501.16663","title":"Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning","created":"2025-01-28","cited_by_count":9,"area":"safety"},{"id":"2205.02340","title":"Knowledge Distillation of Russian Language Models with Reduction of Vocabulary","created":"2022-05-04","cited_by_count":7,"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":"2101.07086","title":"Model Compression for Domain Adaptation through Causal Effect Estimation","created":"2021-01-18","cited_by_count":6,"area":null},{"id":"2303.07477","title":"Efficient Self-supervised Continual Learning with Progressive Task-correlated Layer Freezing","created":"2023-03-13","cited_by_count":6,"area":null},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2406.14709","title":"Factual Dialogue Summarization via Learning from Large Language Models","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2407.18288","title":"Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT","created":"2024-07-25","cited_by_count":6,"area":"distill"},{"id":"2409.15298","title":"Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model","created":"2024-09-04","cited_by_count":6,"area":null},{"id":"2107.08039","title":"Representation Consolidation for Training Expert Students","created":"2021-07-16","cited_by_count":5,"area":"distill"},{"id":"2211.15774","title":"Decentralized Learning with Multi-Headed Distillation","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2309.07668","title":"ChromaDistill: Colorizing Monochrome Radiance Fields with Knowledge Distillation","created":"2023-09-14","cited_by_count":5,"area":null},{"id":"2408.14146","title":"TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines","created":"2024-08-26","cited_by_count":5,"area":"distill"},{"id":"2107.05377","title":"A Flexible Multi-Task Model for BERT Serving","created":"2021-07-12","cited_by_count":4,"area":null},{"id":"2403.04400","title":"Exploring Continual Learning of Compositional Generalization in NLI","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2103.15871","title":"Industry Scale Semi-Supervised Learning for Natural Language Understanding","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2205.10490","title":"Aligning Logits Generatively for Principled Black-Box Knowledge Distillation","created":"2022-05-21","cited_by_count":3,"area":"distill"},{"id":"2301.12609","title":"Knowledge Distillation $\\approx$ Label Smoothing: Fact or Fallacy?","created":"2023-01-30","cited_by_count":3,"area":"distill"},{"id":"2406.05276","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2606.00105","title":"Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning","created":"2026-05-26","cited_by_count":3,"area":"mllm"},{"id":"2103.07600","title":"Student-Teacher Learning from Clean Inputs to Noisy Inputs","created":"2021-03-13","cited_by_count":2,"area":null},{"id":"2112.05638","title":"DistilCSE: Effective Knowledge Distillation For Contrastive Sentence Embeddings","created":"2021-12-10","cited_by_count":2,"area":"distill"},{"id":"2302.11812","title":"Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers","created":"2023-02-23","cited_by_count":2,"area":null},{"id":"2306.01076","title":"Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding","created":"2023-06-01","cited_by_count":2,"area":null},{"id":"2410.06846","title":"Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity","created":"2024-10-09","cited_by_count":2,"area":"ssm"},{"id":"2503.17494","title":"Efficient Knowledge Distillation via Curriculum Extraction","created":"2025-03-21","cited_by_count":2,"area":"distill"},{"id":"2509.23373","title":"Graph Your Own Prompt","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2510.14053","title":"Position: Require Frontier AI Labs To Release Small \"Analog\" Models","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2602.22601","title":"$\\phi$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models","created":"2026-02-26","cited_by_count":2,"area":"mllm"},{"id":"2112.11480","title":"On the Compression of Natural Language Models","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2208.06825","title":"Teacher Guided Training: An Efficient Framework for Knowledge Transfer","created":"2022-08-14","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":"2210.13605","title":"GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2306.10058","title":"EM-Network: Oracle Guided Self-distillation for Sequence Learning","created":"2023-06-14","cited_by_count":1,"area":"distill"},{"id":"2311.13169","title":"SiGeo: Sub-One-Shot NAS via Information Theory and Geometry of Loss Landscape","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2407.02775","title":"MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models","created":"2024-07-03","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":"2412.03513","title":"Enhancing CLIP Conceptual Embedding through Knowledge Distillation","created":"2024-12-04","cited_by_count":1,"area":"distill"},{"id":"2508.13500","title":"LLM-Enhanced Linear Autoencoders for Recommendation","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2509.22621","title":"IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2109.08627","title":"Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2111.12495","title":"Altering Backward Pass Gradients improves Convergence","created":"2021-11-24","cited_by_count":0,"area":null},{"id":"2111.14014","title":"Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation","created":"2021-11-28","cited_by_count":0,"area":null},{"id":"2112.11447","title":"Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix","created":"2021-12-21","cited_by_count":0,"area":"distill"},{"id":"2211.17059","title":"Hint-dynamic Knowledge Distillation","created":"2022-11-30","cited_by_count":0,"area":"distill"},{"id":"2303.10966","title":"Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning","created":"2023-03-20","cited_by_count":0,"area":null},{"id":"2306.06625","title":"Are Intermediate Layers and Labels Really Necessary? A General Language Model Distillation Method","created":"2023-06-11","cited_by_count":0,"area":"distill"},{"id":"2310.00896","title":"Organized Event Participant Prediction Enhanced by Social Media Retweeting Data","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2409.07584","title":"DS-ViT: Dual-Stream Vision Transformer for Cross-Task Distillation in Alzheimer's Early Diagnosis","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2410.08634","title":"GAI-Enabled Explainable Personalized Federated Semi-Supervised Learning","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2504.20000","title":"Knowledge Distillation of Domain-adapted LLMs for Question-Answering in Telecom","created":"2025-04-28","cited_by_count":0,"area":"distill"},{"id":"2505.10822","title":"Distilled Circuits: A Mechanistic Study of Internal Restructuring in Knowledge Distillation","created":"2025-05-16","cited_by_count":0,"area":"distill"},{"id":"2508.02840","title":"Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization","created":"2025-07-30","cited_by_count":0,"area":"distill"},{"id":"2508.16124","title":"Domain Adaptation via Feature Refinement","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2601.04956","title":"TEA: Temporal Adaptive Satellite Image Semantic Segmentation","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2605.09311","title":"Teaching Molecular Dynamics to a Non-Autoregressive Ionic Transport Predictor","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2608.18244","title":"Bidirectional representational alignment between biological and artificial neural networks","created":"2026-08-18","cited_by_count":0,"area":null}],"next_cursor":null}