{"total":259,"rows":[{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561,"area":null},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528,"area":null},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2312.06709","title":"AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One","created":"2023-12-10","cited_by_count":169,"area":null},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132,"area":null},{"id":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","cited_by_count":122,"area":null},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2307.12732","title":"CLIP-KD: An Empirical Study of CLIP Model Distillation","created":"2023-07-24","cited_by_count":87,"area":"distill"},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64,"area":null},{"id":"2209.03942","title":"Data Feedback Loops: Model-driven Amplification of Dataset Biases","created":"2022-09-08","cited_by_count":60,"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":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53,"area":null},{"id":"2112.01528","title":"A Fast Knowledge Distillation Framework for Visual Recognition","created":"2021-12-02","cited_by_count":50,"area":"distill"},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39,"area":null},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39,"area":"alignment"},{"id":"2307.12574","title":"A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation","created":"2023-07-24","cited_by_count":33,"area":"distill"},{"id":"2205.14443","title":"A Closer Look at Self-Supervised Lightweight Vision Transformers","created":"2022-05-28","cited_by_count":31,"area":null},{"id":"2303.11098","title":"Understanding the Role of the Projector in Knowledge Distillation","created":"2023-03-20","cited_by_count":31,"area":"distill"},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","cited_by_count":30,"area":null},{"id":"2209.11459","title":"TeST: Test-time Self-Training under Distribution Shift","created":"2022-09-23","cited_by_count":29,"area":null},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29,"area":"distill"},{"id":"2308.11957","title":"CED: Consistent ensemble distillation for audio tagging","created":"2023-08-23","cited_by_count":29,"area":"distill"},{"id":"2303.18232","title":"DIME-FM: DIstilling Multimodal and Efficient Foundation Models","created":"2023-03-31","cited_by_count":28,"area":"mllm"},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28,"area":"distill"},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27,"area":"distill"},{"id":"2211.04772","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","created":"2022-11-09","cited_by_count":27,"area":"distill"},{"id":"2401.02458","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","created":"2024-01-04","cited_by_count":27,"area":null},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26,"area":"distill"},{"id":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"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":"2110.08890","title":"Network Augmentation for Tiny Deep Learning","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2405.02951","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","created":"2024-05-05","cited_by_count":24,"area":null},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2106.10494","title":"Teacher's pet: understanding and mitigating biases in distillation","created":"2021-06-19","cited_by_count":21,"area":"distill"},{"id":"2201.05131","title":"SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation","created":"2022-01-13","cited_by_count":21,"area":"distill"},{"id":"2301.13304","title":"Understanding Self-Distillation in the Presence of Label Noise","created":"2023-01-30","cited_by_count":21,"area":"distill"},{"id":"2305.06024","title":"A Survey on the Robustness of Computer Vision Models against Common Corruptions","created":"2023-05-10","cited_by_count":21,"area":null},{"id":"2410.01680","title":"PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation","created":"2024-10-02","cited_by_count":21,"area":"distill"},{"id":"2508.20691","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","created":"2025-08-28","cited_by_count":21,"area":"distill"},{"id":"2202.07940","title":"Meta Knowledge Distillation","created":"2022-02-16","cited_by_count":20,"area":"distill"},{"id":"2409.08813","title":"Your Weak LLM is Secretly a Strong Teacher for Alignment","created":"2024-09-13","cited_by_count":20,"area":"alignment"},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19,"area":"distill"},{"id":"2310.17653","title":"Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model","created":"2023-10-26","cited_by_count":19,"area":null},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2203.07159","title":"On the benefits of knowledge distillation for adversarial robustness","created":"2022-03-14","cited_by_count":18,"area":"distill"},{"id":"2304.01973","title":"ERM++: An Improved Baseline for Domain Generalization","created":"2023-04-04","cited_by_count":18,"area":null},{"id":"2305.17007","title":"Improving Knowledge Distillation via Regularizing Feature Norm and Direction","created":"2023-05-26","cited_by_count":18,"area":"distill"},{"id":"2402.01729","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2407.03056","title":"Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation","created":"2024-07-03","cited_by_count":18,"area":"mllm"},{"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":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"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":"2212.13554","title":"NeRN -- Learning Neural Representations for Neural Networks","created":"2022-12-27","cited_by_count":14,"area":null},{"id":"2301.02903","title":"Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching","created":"2023-01-07","cited_by_count":14,"area":null},{"id":"2402.03119","title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","created":"2024-02-05","cited_by_count":14,"area":"distill"},{"id":"2302.02108","title":"Knowledge Distillation in Vision Transformers: A Critical Review","created":"2023-02-04","cited_by_count":13,"area":"distill"},{"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":"2410.11087","title":"Locality Alignment Improves Vision-Language Models","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2203.06760","title":"CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification","created":"2022-03-13","cited_by_count":12,"area":"distill"},{"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":"2210.09609","title":"SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP","created":"2022-10-18","cited_by_count":12,"area":"distill"},{"id":"2303.17285","title":"Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection","created":"2023-03-30","cited_by_count":12,"area":null},{"id":"2308.13093","title":"EgoBlur: Responsible Innovation in Aria","created":"2023-08-24","cited_by_count":12,"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":"2502.20126","title":"FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute","created":"2025-02-27","cited_by_count":12,"area":"diffusion"},{"id":"2112.06511","title":"Ex-Model: Continual Learning from a Stream of Trained Models","created":"2021-12-13","cited_by_count":11,"area":null},{"id":"2204.00656","title":"Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes","created":"2022-04-01","cited_by_count":11,"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":"2305.15781","title":"VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale","created":"2023-05-25","cited_by_count":11,"area":"distill"},{"id":"2411.06786","title":"ScaleKD: Strong Vision Transformers Could Be Excellent Teachers","created":"2024-11-11","cited_by_count":11,"area":"distill"},{"id":"2301.09451","title":"A Simple Recipe for Competitive Low-compute Self supervised Vision Models","created":"2023-01-23","cited_by_count":10,"area":"distill"},{"id":"2306.15110","title":"Deep Transfer Learning for Intelligent Vehicle Perception: a Survey","created":"2023-06-26","cited_by_count":10,"area":null},{"id":"2412.15004","title":"From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2210.01213","title":"Robust Active Distillation","created":"2022-10-03","cited_by_count":9,"area":"distill"},{"id":"2306.02368","title":"Revisiting Data-Free Knowledge Distillation with Poisoned Teachers","created":"2023-06-04","cited_by_count":9,"area":"safety"},{"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":"2411.12817","title":"What Makes a Good Dataset for Knowledge Distillation?","created":"2024-11-19","cited_by_count":9,"area":"distill"},{"id":"2507.01887","title":"MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants","created":"2025-07-02","cited_by_count":9,"area":"lr"},{"id":"2201.06945","title":"It's All in the Head: Representation Knowledge Distillation through Classifier Sharing","created":"2022-01-18","cited_by_count":8,"area":"distill"},{"id":"2204.03475","title":"Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2302.10494","title":"The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers","created":"2023-02-21","cited_by_count":8,"area":"distill"},{"id":"2305.19412","title":"Are Large Kernels Better Teachers than Transformers for ConvNets?","created":"2023-05-30","cited_by_count":8,"area":"distill"},{"id":"2406.03508","title":"Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders","created":"2024-06-05","cited_by_count":8,"area":"safety"},{"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":"2112.00725","title":"The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image","created":"2021-12-01","cited_by_count":7,"area":null},{"id":"2205.03824","title":"A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges","created":"2022-05-08","cited_by_count":7,"area":null},{"id":"2211.15215","title":"Progressive Learning without Forgetting","created":"2022-11-28","cited_by_count":7,"area":null},{"id":"2308.11807","title":"Towards an On-device Agent for Text Rewriting","created":"2023-08-22","cited_by_count":7,"area":"agents"},{"id":"2311.04251","title":"MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters","created":"2023-11-07","cited_by_count":7,"area":null},{"id":"2312.09716","title":"Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2401.00523","title":"Compressing Deep Image Super-resolution Models","created":"2023-12-31","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"}],"next_cursor":"100"}