{"total":158,"rows":[{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388,"area":"distill"},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341,"area":"mllm"},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2306.04140","title":"Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions","created":"2023-06-07","cited_by_count":125,"area":null},{"id":"2212.04500","title":"Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning","created":"2022-12-08","cited_by_count":90,"area":"distill"},{"id":"2302.13001","title":"Better Generative Replay for Continual Federated Learning","created":"2023-02-25","cited_by_count":55,"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":"2206.06067","title":"Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation","created":"2022-06-13","cited_by_count":41,"area":"distill"},{"id":"2203.06768","title":"Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse","created":"2022-03-13","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":"2210.05801","title":"Linkless Link Prediction via Relational Distillation","created":"2022-10-11","cited_by_count":39,"area":null},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38,"area":"distill"},{"id":"2106.03310","title":"Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model","created":"2021-06-07","cited_by_count":37,"area":"distill"},{"id":"2304.08386","title":"Progressive Visual Prompt Learning with Contrastive Feature Re-formation","created":"2023-04-17","cited_by_count":36,"area":null},{"id":"2110.15210","title":"Towards Model Agnostic Federated Learning Using Knowledge Distillation","created":"2021-10-28","cited_by_count":31,"area":"distill"},{"id":"2210.03312","title":"Distillation-Resistant Watermarking for Model Protection in NLP","created":"2022-10-07","cited_by_count":30,"area":"safety"},{"id":"2107.02629","title":"Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation","created":"2021-07-06","cited_by_count":29,"area":"distill"},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2204.13346","title":"UniTE: Unified Translation Evaluation","created":"2022-04-28","cited_by_count":28,"area":null},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27,"area":"distill"},{"id":"2401.08732","title":"Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information","created":"2024-01-16","cited_by_count":25,"area":"distill"},{"id":"2204.02744","title":"Universal Representations: A Unified Look at Multiple Task and Domain Learning","created":"2022-04-06","cited_by_count":23,"area":null},{"id":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"id":"2202.09852","title":"Cross-Task Knowledge Distillation in Multi-Task Recommendation","created":"2022-02-20","cited_by_count":22,"area":"distill"},{"id":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"id":"2210.15427","title":"Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2301.13304","title":"Understanding Self-Distillation in the Presence of Label Noise","created":"2023-01-30","cited_by_count":21,"area":"distill"},{"id":"2407.20584","title":"Pruning Large Language Models with Semi-Structural Adaptive Sparse Training","created":"2024-07-30","cited_by_count":20,"area":null},{"id":"2208.08741","title":"Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification","created":"2022-08-18","cited_by_count":19,"area":"distill"},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19,"area":"distill"},{"id":"2501.16352","title":"Mixture of Experts (MoE): A Big Data Perspective","created":"2025-01-18","cited_by_count":18,"area":"moe"},{"id":"2106.02654","title":"Churn Reduction via Distillation","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16,"area":"distill"},{"id":"2410.04638","title":"Provable Weak-to-Strong Generalization via Benign Overfitting","created":"2024-10-06","cited_by_count":16,"area":"distill"},{"id":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15,"area":null},{"id":"2407.04600","title":"Understanding the Gains from Repeated Self-Distillation","created":"2024-07-05","cited_by_count":15,"area":"distill"},{"id":"2407.06754","title":"Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challenges","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2410.18779","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2208.10010","title":"NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs","created":"2022-08-22","cited_by_count":14,"area":null},{"id":"2310.05632","title":"Binary Classification with Confidence Difference","created":"2023-10-09","cited_by_count":13,"area":null},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2407.18041","title":"How to Train the Teacher Model for Effective Knowledge Distillation","created":"2024-07-25","cited_by_count":13,"area":"distill"},{"id":"2205.01915","title":"Generalized Knowledge Distillation via Relationship Matching","created":"2022-05-04","cited_by_count":12,"area":"distill"},{"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":"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":"2203.13452","title":"PCA-Based Knowledge Distillation Towards Lightweight and Content-Style Balanced Photorealistic Style Transfer Models","created":"2022-03-25","cited_by_count":11,"area":"distill"},{"id":"2305.17581","title":"Knowledge Distillation Performs Partial Variance Reduction","created":"2023-05-27","cited_by_count":11,"area":"distill"},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2501.16559","title":"LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation","created":"2025-01-27","cited_by_count":11,"area":"diffusion"},{"id":"2107.09305","title":"Follow Your Path: a Progressive Method for Knowledge Distillation","created":"2021-07-20","cited_by_count":10,"area":"distill"},{"id":"2206.03970","title":"Narrowing the Coordinate-frame Gap in Behavior Prediction Models: Distillation for Efficient and Accurate Scene-centric Motion Forecasting","created":"2022-06-08","cited_by_count":10,"area":null},{"id":"2506.14457","title":"Dataset distillation for memorized data: Soft labels can leak held-out teacher knowledge","created":"2025-06-17","cited_by_count":10,"area":null},{"id":"2508.05232","title":"Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs","created":"2025-08-07","cited_by_count":10,"area":null},{"id":"2406.10861","title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","created":"2024-06-16","cited_by_count":9,"area":"distill"},{"id":"2503.13834","title":"See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias","created":"2025-03-18","cited_by_count":9,"area":null},{"id":"2505.13111","title":"Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation","created":"2025-05-19","cited_by_count":9,"area":"distill"},{"id":"2302.08155","title":"Learning From Biased Soft Labels","created":"2023-02-16","cited_by_count":8,"area":"distill"},{"id":"2306.01997","title":"UADB: Unsupervised Anomaly Detection Booster","created":"2023-06-03","cited_by_count":8,"area":null},{"id":"2405.13014","title":"QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models","created":"2024-05-14","cited_by_count":8,"area":null},{"id":"2506.15115","title":"Towards Reliable Forgetting: A Survey on Machine Unlearning Verification","created":"2025-06-18","cited_by_count":8,"area":"safety"},{"id":"2203.08412","title":"CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2307.08436","title":"DOT: A Distillation-Oriented Trainer","created":"2023-07-17","cited_by_count":7,"area":"distill"},{"id":"2307.11030","title":"Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering","created":"2023-07-20","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":"2407.12543","title":"Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2411.01547","title":"Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment","created":"2024-11-03","cited_by_count":7,"area":"distill"},{"id":"2502.06619","title":"Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification","created":"2025-02-10","cited_by_count":7,"area":"diffusion"},{"id":"2107.04708","title":"Lifelong Twin Generative Adversarial Networks","created":"2021-07-09","cited_by_count":6,"area":null},{"id":"2302.12091","title":"Random Teachers are Good Teachers","created":"2023-02-23","cited_by_count":6,"area":"distill"},{"id":"2308.14286","title":"Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection","created":"2023-08-28","cited_by_count":6,"area":"distill"},{"id":"2502.00843","title":"VLM-Assisted Continual learning for Visual Question Answering in Self-Driving","created":"2025-02-02","cited_by_count":6,"area":"mllm"},{"id":"2508.12235","title":"CC-Time: Cross-Model and Cross-Modality Time Series Forecasting","created":"2025-08-17","cited_by_count":6,"area":null},{"id":"2207.06613","title":"T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXit","created":"2022-07-14","cited_by_count":5,"area":"inference"},{"id":"2409.11786","title":"Efficient Low-Resolution Face Recognition via Bridge Distillation","created":"2024-09-18","cited_by_count":5,"area":null},{"id":"2506.03857","title":"Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation","created":"2025-06-04","cited_by_count":5,"area":"distill"},{"id":"2110.06830","title":"CONetV2: Efficient Auto-Channel Size Optimization for CNNs","created":"2021-10-13","cited_by_count":4,"area":"distill"},{"id":"2212.02304","title":"Matching DNN Compression and Cooperative Training with Resources and Data Availability","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2305.00738","title":"FCA: Taming Long-tailed Federated Medical Image Classification by Classifier Anchoring","created":"2023-05-01","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":"2405.13078","title":"Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch","created":"2024-05-21","cited_by_count":4,"area":"distill"},{"id":"2411.00691","title":"Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2504.17177","title":"A Genealogy of Foundation Models in Remote Sensing","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2507.15911","title":"Local Dense Logit Relations for Enhanced Knowledge Distillation","created":"2025-07-21","cited_by_count":4,"area":"distill"},{"id":"2601.20687","title":"Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models","created":"2026-01-28","cited_by_count":4,"area":"alignment"},{"id":"2312.08700","title":"RdimKD: Generic Distillation Paradigm by Dimensionality Reduction","created":"2023-12-14","cited_by_count":3,"area":"distill"},{"id":"2402.15586","title":"Distilling Adversarial Robustness Using Heterogeneous Teachers","created":"2024-02-23","cited_by_count":3,"area":"distill"},{"id":"2402.17983","title":"3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding","created":"2024-02-28","cited_by_count":3,"area":"distill"},{"id":"2404.14822","title":"CNN2GNN: How to Bridge CNN with GNN","created":"2024-04-23","cited_by_count":3,"area":null},{"id":"2504.13219","title":"Scaling Laws for Data-Efficient Visual Transfer Learning","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2505.13899","title":"Causes and Consequences of Representational Similarity in Machine Learning Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2507.00012","title":"Towards Undistillable Models by Minimizing Conditional Mutual Information","created":"2025-06-13","cited_by_count":3,"area":"distill"},{"id":"2510.20673","title":"Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2602.05646","title":"Empowering Time Series Analysis with Large-Scale Multimodal Pretraining","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2605.08873","title":"CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2605.23857","title":"Strong Teacher Not Needed? On Distillation in LLM Pretraining","created":"2026-05-22","cited_by_count":3,"area":"distill"},{"id":"2108.12001","title":"Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks","created":"2021-08-26","cited_by_count":2,"area":null},{"id":"2111.12963","title":"Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2209.05732","title":"R\\'{e}nyi Divergence Deep Mutual Learning","created":"2022-09-13","cited_by_count":2,"area":null},{"id":"2303.08360","title":"Knowledge Distillation from Single to Multi Labels: an Empirical Study","created":"2023-03-15","cited_by_count":2,"area":"distill"},{"id":"2402.14922","title":"Practical Insights into Knowledge Distillation for Pre-Trained Models","created":"2024-02-22","cited_by_count":2,"area":"distill"}],"next_cursor":"100"}