{"total":49,"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":"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":"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":"2106.04563","title":"XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation","created":"2021-06-08","cited_by_count":18,"area":null},{"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":"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":"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":"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":"2409.15298","title":"Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model","created":"2024-09-04","cited_by_count":6,"area":null},{"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":"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":"2406.05276","title":"VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2103.07600","title":"Student-Teacher Learning from Clean Inputs to Noisy Inputs","created":"2021-03-13","cited_by_count":2,"area":null},{"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":"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":"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":"2210.13605","title":"GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction","created":"2022-10-24","cited_by_count":1,"area":null},{"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":"2408.08250","title":"Computer Vision Model Compression Techniques for Embedded Systems: A Survey","created":"2024-08-15","cited_by_count":1,"area":null},{"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":"2303.10966","title":"Towards Reliable Neural Machine Translation with Consistency-Aware Meta-Learning","created":"2023-03-20","cited_by_count":0,"area":null},{"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":"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}