{"total":69,"rows":[{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79,"area":null},{"id":"2311.17950","title":"Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching","created":"2023-11-29","cited_by_count":69,"area":null},{"id":"2303.01416","title":"3D generation on ImageNet","created":"2023-03-02","cited_by_count":47,"area":null},{"id":"2112.00260","title":"Ranking Distance Calibration for Cross-Domain Few-Shot Learning","created":"2021-12-01","cited_by_count":27,"area":null},{"id":"2305.10758","title":"Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework","created":"2023-05-18","cited_by_count":24,"area":null},{"id":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","cited_by_count":21,"area":null},{"id":"2203.09510","title":"DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection","created":"2022-03-17","cited_by_count":20,"area":null},{"id":"2207.01426","title":"Dynamic Contrastive Distillation for Image-Text Retrieval","created":"2022-07-04","cited_by_count":14,"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":"2502.15016","title":"TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2405.14736","title":"GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost","created":"2024-05-23","cited_by_count":9,"area":null},{"id":"2405.19902","title":"Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2401.03246","title":"SeqNAS: Neural Architecture Search for Event Sequence Classification","created":"2024-01-06","cited_by_count":8,"area":null},{"id":"2507.04636","title":"Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Framework","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2109.11105","title":"Distiller: A Systematic Study of Model Distillation Methods in Natural Language Processing","created":"2021-09-23","cited_by_count":7,"area":null},{"id":"2605.23645","title":"Learning Through Noise: Why Subliminal Learning Works and When It Fails","created":"2026-05-22","cited_by_count":7,"area":null},{"id":"2212.10147","title":"Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2303.01213","title":"DSD$^2$: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?","created":"2023-03-02","cited_by_count":6,"area":null},{"id":"2406.10325","title":"Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment","created":"2024-06-14","cited_by_count":5,"area":null},{"id":"2501.07236","title":"CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2509.25837","title":"Distillation of Large Language Models via Concrete Score Matching","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2206.07277","title":"A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2302.06114","title":"A Comprehensive Survey on Graph Summarization with Graph Neural Networks","created":"2023-02-13","cited_by_count":4,"area":null},{"id":"2306.02433","title":"Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2406.09717","title":"UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2409.14122","title":"Efficient and Effective Model Extraction","created":"2024-09-21","cited_by_count":4,"area":null},{"id":"2410.20035","title":"Training the Untrainable: Introducing Inductive Bias via Representational Alignment","created":"2024-10-26","cited_by_count":4,"area":null},{"id":"2305.16532","title":"Counterfactual Explainer Framework for Deep Reinforcement Learning Models Using Policy Distillation","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2402.13122","title":"Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2504.09814","title":"DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2110.09163","title":"A Dimensionality Reduction Approach for Convolutional Neural Networks","created":"2021-10-18","cited_by_count":2,"area":null},{"id":"2411.02558","title":"Enhancing Risk Assessment in Transformers with Loss-at-Risk Functions","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2508.03628","title":"LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2508.07795","title":"Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfake","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2207.07793","title":"Towards the Desirable Decision Boundary by Moderate-Margin Adversarial Training","created":"2022-07-16","cited_by_count":1,"area":null},{"id":"2209.11304","title":"Colonoscopy Landmark Detection using Vision Transformers","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2403.05050","title":"DyRoNet: Dynamic Routing and Low-Rank Adapters for Autonomous Driving Streaming Perception","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2403.16112","title":"Opportunities and challenges in the application of large artificial intelligence models in radiology","created":"2024-03-24","cited_by_count":1,"area":null},{"id":"2404.15999","title":"BeSound: Bluetooth-Based Position Estimation Enhancing with Cross-Modality Distillation","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2406.02745","title":"Measuring Stochastic Data Complexity with Boltzmann Influence Functions","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2406.10232","title":"Object criticality for safer navigation","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2406.19814","title":"Extract More from Less: Efficient Fine-Grained Visual Recognition in Low-Data Regimes","created":"2024-06-28","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":"2412.20002","title":"Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking","created":"2024-12-28","cited_by_count":1,"area":null},{"id":"2502.08692","title":"Efficient Split Learning LSTM Models for FPGA-based Edge IoT Devices","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2503.06291","title":"IteRABRe: Iterative Recovery-Aided Block Reduction","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2505.16991","title":"An Effective Training Framework for Light-Weight Automatic Speech Recognition Models","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2509.19743","title":"Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive Evaluation","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2203.13932","title":"A Cross-Domain Approach for Continuous Impression Recognition from Dyadic Audio-Visual-Physio Signals","created":"2022-03-25","cited_by_count":0,"area":null},{"id":"2211.15023","title":"AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2301.09164","title":"Unifying Synergies between Self-supervised Learning and Dynamic Computation","created":"2023-01-22","cited_by_count":0,"area":null},{"id":"2308.16596","title":"The Quest of Finding the Antidote to Sparse Double Descent","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2409.12720","title":"FAST GDRNPP: Improving the Speed of State-of-the-Art 6D Object Pose Estimation","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2411.06836","title":"Spatially Constrained Transformer with Efficient Global Relation Modelling for Spatio-Temporal Prediction","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2411.12098","title":"Federated Contrastive Learning of Graph-Level Representations","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2503.07294","title":"From $\\mathcal{O}(n^{2})$ to $\\mathcal{O}(n)$ Parameters: Quantum Self-Attention in Vision Transformers for Biomedical Image Classification","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2505.18166","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2508.01251","title":"Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2508.08942","title":"Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2508.16648","title":"LatentFlow: Cross-Frequency Experimental Flow Reconstruction from Sparse Pressure via Latent Mapping","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2512.04198","title":"Network of Theseus (like the ship)","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.14012","title":"MATE: Matryoshka Audio-Text Embeddings for Open-Vocabulary Keyword Spotting","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.17512","title":"One-Shot Federated Clustering of Non-Independent Completely Distributed Data","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.05367","title":"RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.12369","title":"Human Knowledge Integrated Multi-modal Learning for Single Source Domain Generalization","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2606.03069","title":"ROBUST-WT: Robust Uncertainty-aware Segmentation Transform via Whitening and Training Enhancements","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.15107","title":"Global Federated Learning Strategies for Building Efficient Personalized Models","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.29027","title":"Explainable Multi-Loss Distillation Framework for Efficient and Interpretable Shrimp Disease Text Classification","created":"2026-08-29","cited_by_count":0,"area":null}],"next_cursor":null}