{"total":297,"rows":[{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","created":"2026-01-26","cited_by_count":455,"area":"lr"},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161,"area":null},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156,"area":"lr"},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122,"area":null},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119,"area":null},{"id":"2106.13799","title":"Assessing Generalization of SGD via Disagreement","created":"2021-06-25","cited_by_count":117,"area":null},{"id":"2310.05249","title":"In-Context Convergence of Transformers","created":"2023-10-08","cited_by_count":115,"area":null},{"id":"2410.24210","title":"TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling","created":"2024-10-31","cited_by_count":113,"area":null},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104,"area":"synth"},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93,"area":null},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"area":null},{"id":"2204.12703","title":"Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning","created":"2022-04-27","cited_by_count":81,"area":null},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77,"area":null},{"id":"2308.07686","title":"Boosting Multi-modal Model Performance with Adaptive Gradient Modulation","created":"2023-08-15","cited_by_count":73,"area":null},{"id":"2404.12715","title":"Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration","created":"2024-04-19","cited_by_count":67,"area":null},{"id":"2305.01233","title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning","created":"2023-05-02","cited_by_count":53,"area":null},{"id":"2106.07875","title":"S-LIME: Stabilized-LIME for Model Explanation","created":"2021-06-15","cited_by_count":52,"area":null},{"id":"2208.02813","title":"Towards Understanding Mixture of Experts in Deep Learning","created":"2022-08-04","cited_by_count":52,"area":"moe"},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2206.01717","title":"A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features","created":"2022-06-03","cited_by_count":49,"area":null},{"id":"2406.07515","title":"Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification","created":"2024-06-11","cited_by_count":45,"area":"synth"},{"id":"2106.11059","title":"Improving Multi-Modal Learning with Uni-Modal Teachers","created":"2021-06-21","cited_by_count":41,"area":null},{"id":"2207.05931","title":"Towards understanding how momentum improves generalization in deep learning","created":"2022-07-13","cited_by_count":40,"area":null},{"id":"2305.18891","title":"EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation","created":"2023-05-30","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":"2306.04949","title":"Robust Learning with Progressive Data Expansion Against Spurious Correlation","created":"2023-06-08","cited_by_count":39,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2302.00219","title":"Knowledge Distillation on Graphs: A Survey","created":"2023-02-01","cited_by_count":38,"area":"distill"},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37,"area":null},{"id":"2203.09747","title":"Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization","created":"2022-03-18","cited_by_count":35,"area":null},{"id":"2304.11327","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","created":"2023-04-22","cited_by_count":35,"area":null},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35,"area":"moe"},{"id":"2402.15607","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","created":"2024-02-23","cited_by_count":35,"area":null},{"id":"2209.05310","title":"On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models","created":"2022-09-12","cited_by_count":34,"area":null},{"id":"2303.04145","title":"Benign Overfitting for Two-layer ReLU Convolutional Neural Networks","created":"2023-03-07","cited_by_count":34,"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":"2305.16635","title":"Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing","created":"2023-05-26","cited_by_count":31,"area":null},{"id":"2107.10878","title":"Bagging, optimized dynamic mode decomposition (BOP-DMD) for robust, stable forecasting with spatial and temporal uncertainty-quantification","created":"2021-07-22","cited_by_count":30,"area":null},{"id":"2302.03773","title":"What Matters In The Structured Pruning of Generative Language Models?","created":"2023-02-07","cited_by_count":30,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2310.07269","title":"Why Does Sharpness-Aware Minimization Generalize Better Than SGD?","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2207.02598","title":"Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning","created":"2022-07-06","cited_by_count":26,"area":null},{"id":"2309.17230","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2508.04665","title":"Perch 2.0: The Bittern Lesson for Bioacoustics","created":"2025-08-06","cited_by_count":26,"area":null},{"id":"2305.05010","title":"Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation","created":"2023-05-08","cited_by_count":25,"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":"2206.08491","title":"Revisiting Self-Distillation","created":"2022-06-17","cited_by_count":24,"area":"distill"},{"id":"2210.05021","title":"The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2307.03407","title":"Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation","created":"2023-07-07","cited_by_count":24,"area":null},{"id":"2409.19610","title":"Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method","created":"2024-09-29","cited_by_count":22,"area":"mllm"},{"id":"2106.10494","title":"Teacher's pet: understanding and mitigating biases in distillation","created":"2021-06-19","cited_by_count":21,"area":"distill"},{"id":"2202.04598","title":"Reproducibility in Optimization: Theoretical Framework and Limits","created":"2022-02-09","cited_by_count":21,"area":null},{"id":"2203.02485","title":"Better Supervisory Signals by Observing Learning Paths","created":"2022-03-04","cited_by_count":21,"area":"distill"},{"id":"2305.17326","title":"Matrix Information Theory for Self-Supervised Learning","created":"2023-05-27","cited_by_count":21,"area":null},{"id":"2405.16646","title":"A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts","created":"2024-05-26","cited_by_count":21,"area":"moe"},{"id":"2306.16788","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","created":"2023-06-29","cited_by_count":20,"area":null},{"id":"2111.12172","title":"Multi-label Iterated Learning for Image Classification with Label Ambiguity","created":"2021-11-23","cited_by_count":19,"area":null},{"id":"2203.13344","title":"Linking Emergent and Natural Languages via Corpus Transfer","created":"2022-03-24","cited_by_count":19,"area":null},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19,"area":"distill"},{"id":"2303.08433","title":"The Benefits of Mixup for Feature Learning","created":"2023-03-15","cited_by_count":19,"area":null},{"id":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19,"area":null},{"id":"2203.01572","title":"Data Augmentation as Feature Manipulation","created":"2022-03-03","cited_by_count":18,"area":null},{"id":"2206.03826","title":"Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks","created":"2022-06-08","cited_by_count":18,"area":null},{"id":"2310.18935","title":"Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data","created":"2023-10-29","cited_by_count":18,"area":null},{"id":"2410.05101","title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","created":"2024-10-07","cited_by_count":17,"area":null},{"id":"2111.13280","title":"Efficient Self-Ensemble for Semantic Segmentation","created":"2021-11-26","cited_by_count":16,"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":"2307.07951","title":"MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning","created":"2023-07-16","cited_by_count":16,"area":"lr"},{"id":"2205.11845","title":"CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing","created":"2022-05-24","cited_by_count":15,"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":"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":"2502.04725","title":"Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?","created":"2025-02-07","cited_by_count":15,"area":"diffusion"},{"id":"2506.02557","title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models","created":"2025-06-03","cited_by_count":15,"area":"mllm"},{"id":"2111.12958","title":"Self-Distilled Self-Supervised Representation Learning","created":"2021-11-25","cited_by_count":14,"area":"distill"},{"id":"2210.05043","title":"Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2210.13512","title":"Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2210.15976","title":"BEBERT: Efficient and Robust Binary Ensemble BERT","created":"2022-10-28","cited_by_count":14,"area":null},{"id":"2406.01977","title":"What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding","created":"2024-06-04","cited_by_count":14,"area":null},{"id":"2511.07378","title":"Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization","created":"2025-11-10","cited_by_count":14,"area":"lr"},{"id":"2105.03048","title":"Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates","created":"2021-05-07","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":"2410.08194","title":"Features are fate: a theory of transfer learning in high-dimensional regression","created":"2024-10-10","cited_by_count":13,"area":null},{"id":"2507.21182","title":"SDD: Self-Degraded Defense against Malicious Fine-tuning","created":"2025-07-27","cited_by_count":13,"area":"alignment"},{"id":"2110.08220","title":"Combining Diverse Feature Priors","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2207.12980","title":"Efficient One Pass Self-distillation with Zipf's Label Smoothing","created":"2022-07-26","cited_by_count":12,"area":"distill"},{"id":"2306.13926","title":"Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons","created":"2023-06-24","cited_by_count":12,"area":null},{"id":"2402.00893","title":"MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts","created":"2024-01-31","cited_by_count":12,"area":"moe"},{"id":"2408.04301","title":"Tackling Noisy Clients in Federated Learning with End-to-end Label Correction","created":"2024-08-08","cited_by_count":12,"area":null},{"id":"2410.08503","title":"Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data","created":"2024-10-11","cited_by_count":12,"area":null},{"id":"2502.14218","title":"Rethinking Spiking Neural Networks from an Ensemble Learning Perspective","created":"2025-02-20","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}],"next_cursor":"100"}