{"total":73,"rows":[{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2212.01548","title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","created":"2022-12-03","cited_by_count":102,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2211.13976","title":"Expanding Small-Scale Datasets with Guided Imagination","created":"2022-11-25","cited_by_count":62,"area":null},{"id":"2203.08124","title":"Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective","created":"2022-03-15","cited_by_count":57,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2305.20028","title":"A Study of Bayesian Neural Network Surrogates for Bayesian Optimization","created":"2023-05-31","cited_by_count":50,"area":null},{"id":"2405.16043","title":"Theoretical Analysis of Weak-to-Strong Generalization","created":"2024-05-25","cited_by_count":48,"area":null},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47,"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":"2309.16286","title":"Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning","created":"2023-09-28","cited_by_count":40,"area":null},{"id":"2202.00155","title":"Fortuitous Forgetting in Connectionist Networks","created":"2022-02-01","cited_by_count":39,"area":null},{"id":"2203.12515","title":"A Survey on Cross-Lingual Summarization","created":"2022-03-23","cited_by_count":38,"area":null},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2110.11024","title":"Watermarking Graph Neural Networks based on Backdoor Attacks","created":"2021-10-21","cited_by_count":25,"area":null},{"id":"2306.02210","title":"GPT-FL: Generative Pre-trained Model-Assisted Federated Learning","created":"2023-06-03","cited_by_count":24,"area":null},{"id":"2306.16612","title":"GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps","created":"2023-06-29","cited_by_count":23,"area":null},{"id":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2407.19389","title":"FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction","created":"2024-07-28","cited_by_count":21,"area":null},{"id":"2404.03626","title":"Training LLMs over Neurally Compressed Text","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2311.01149","title":"ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model","created":"2023-11-02","cited_by_count":16,"area":null},{"id":"2203.03047","title":"Recent Advances in Neural Text Generation: A Task-Agnostic Survey","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2211.12933","title":"Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket","created":"2022-11-23","cited_by_count":14,"area":null},{"id":"2210.06711","title":"Weighted Distillation with Unlabeled Examples","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2411.07182","title":"Revisiting Ensembling in One-Shot Federated Learning","created":"2024-11-11","cited_by_count":13,"area":null},{"id":"2502.05075","title":"Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2305.01645","title":"Distill or Annotate? Cost-Efficient Fine-Tuning of Compact Models","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2108.00065","title":"Model Preserving Compression for Neural Networks","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2207.10314","title":"Semi-Supervised Learning of Optical Flow by Flow Supervisor","created":"2022-07-21","cited_by_count":9,"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":"2406.15480","title":"On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2207.14561","title":"Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization","created":"2022-07-29","cited_by_count":8,"area":null},{"id":"2506.02362","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2207.11191","title":"Self-Supervised-RCNN for Medical Image Segmentation with Limited Data Annotation","created":"2022-07-17","cited_by_count":7,"area":null},{"id":"2402.13007","title":"Improve Cross-Architecture Generalization on Dataset Distillation","created":"2024-02-20","cited_by_count":7,"area":null},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"area":null},{"id":"2305.07180","title":"Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2305.14109","title":"Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2505.17222","title":"Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Prompts","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2409.14122","title":"Efficient and Effective Model Extraction","created":"2024-09-21","cited_by_count":4,"area":null},{"id":"2410.01483","title":"Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2501.15693","title":"Beyond Benchmarks: On The False Promise of AI Regulation","created":"2025-01-26","cited_by_count":4,"area":null},{"id":"2502.00382","title":"Masked Generative Nested Transformers with Decode Time Scaling","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2506.03784","title":"When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2402.11305","title":"On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2511.08322","title":"Mitigating Negative Flips via Margin Preserving Training","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2302.01440","title":"Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications","created":"2023-02-02","cited_by_count":2,"area":null},{"id":"2312.10087","title":"Revisiting the Entropy Semiring for Neural Speech Recognition","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2406.00061","title":"STAT: Shrinking Transformers After Training","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2508.01074","title":"Evading Data Provenance in Deep Neural Networks","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2509.24005","title":"Does Weak-to-strong Generalization Happen under Spurious Correlations?","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.08095","title":"Beyond Real Data: Synthetic Data through the Lens of Regularization","created":"2025-10-09","cited_by_count":2,"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":"2303.10386","title":"Channel-Aware Distillation Transformer for Depth Estimation on Nano Drones","created":"2023-03-18","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":"2502.08518","title":"FedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2504.19602","title":"Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2308.01098","title":"Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2404.16168","title":"The Over-Certainty Phenomenon in Modern Test-Time Adaptation Algorithms","created":"2024-04-24","cited_by_count":0,"area":null},{"id":"2406.00410","title":"Posterior Label Smoothing for Node Classification","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2507.10059","title":"GeLaCo: An Evolutionary Approach to Layer Compression","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2508.01475","title":"$R^2$-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2508.16860","title":"TriagerX: Dual Transformers for Bug Triaging Tasks with Content and Interaction Based Rankings","created":"2025-08-23","cited_by_count":0,"area":null},{"id":"2603.07551","title":"Speech Generation Speaker Poisoning: Capability Erasure in Zero-Shot Text-to-Speech","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.22839","title":"From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2608.18399","title":"What Does Attention Transfer Transfer? Attention Structure and Robustness in Vision Transformers","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.30553","title":"Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.14413","title":"Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}