{"list":"other","total":93,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"2402.00159","title":"Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research","created":"2024-01-31","cited_by_count":483},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2003.02819","title":"Does label smoothing mitigate label noise?","created":"2020-03-05","cited_by_count":204},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182},{"id":"2009.11162","title":"Implicit Gradient Regularization","created":"2020-09-23","cited_by_count":146},{"id":"2404.05405","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","created":"2024-04-08","cited_by_count":144},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142},{"id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133},{"id":"2310.20707","title":"What's In My Big Data?","created":"2023-10-31","cited_by_count":129},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122},{"id":"2203.07259","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","created":"2022-03-14","cited_by_count":115},{"id":"2410.12954","title":"A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'","created":"2024-10-16","cited_by_count":115},{"id":"2005.04511","title":"Finding Universal Grammatical Relations in Multilingual BERT","created":"2020-05-09","cited_by_count":110},{"id":"2210.14707","title":"Is Out-of-Distribution Detection Learnable?","created":"2022-10-26","cited_by_count":109},{"id":"2302.11803","title":"A Comprehensive Survey on Source-free Domain Adaptation","created":"2023-02-23","cited_by_count":104},{"id":"2305.02765","title":"HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec","created":"2023-05-04","cited_by_count":97},{"id":"2301.13662","title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt","created":"2023-01-31","cited_by_count":92},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82},{"id":"2404.05090","title":"How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse","created":"2024-04-07","cited_by_count":79},{"id":"2010.03648","title":"A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks","created":"2020-10-07","cited_by_count":72},{"id":"2309.11523","title":"RMT: Retentive Networks Meet Vision Transformers","created":"2023-09-20","cited_by_count":68},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57},{"id":"2501.13381","title":"Do as We Do, Not as You Think: the Conformity of Large Language Models","created":"2025-01-23","cited_by_count":53},{"id":"2403.01241","title":"IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact","created":"2024-03-02","cited_by_count":52},{"id":"2402.16775","title":"A Comprehensive Evaluation of Quantization Strategies for Large Language Models","created":"2024-02-26","cited_by_count":48},{"id":"2501.12327","title":"VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model","created":"2025-01-21","cited_by_count":44},{"id":"2006.15815","title":"Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum","created":"2020-06-29","cited_by_count":40},{"id":"2306.04251","title":"Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks","created":"2023-06-07","cited_by_count":39},{"id":"2107.04835","title":"Noise Stability Regularization for Improving BERT Fine-tuning","created":"2021-07-10","cited_by_count":29},{"id":"2302.02334","title":"Revisiting Discriminative vs. Generative Classifiers: Theory and Implications","created":"2023-02-05","cited_by_count":29},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28},{"id":"2107.01163","title":"Unveiling the structure of wide flat minima in neural networks","created":"2021-07-02","cited_by_count":28},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","cited_by_count":27},{"id":"2011.11152","title":"On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective","created":"2020-11-23","cited_by_count":25},{"id":"2305.17476","title":"Toward Understanding Generative Data Augmentation","created":"2023-05-27","cited_by_count":25},{"id":"1907.07590","title":"Mitigating Uncertainty in Document Classification","created":"2019-07-17","cited_by_count":22},{"id":"2212.13563","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","created":"2022-12-27","cited_by_count":22},{"id":"2406.10056","title":"UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner","created":"2024-06-14","cited_by_count":22},{"id":"2112.08810","title":"Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images","created":"2021-12-16","cited_by_count":16},{"id":"2310.10699","title":"Reusing Pretrained Models by Multi-linear Operators for Efficient Training","created":"2023-10-16","cited_by_count":15},{"id":"2206.05658","title":"Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization","created":"2022-06-12","cited_by_count":12},{"id":"2404.17120","title":"Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs","created":"2024-04-26","cited_by_count":11},{"id":"2401.09192","title":"Preparing Lessons for Progressive Training on Language Models","created":"2024-01-17","cited_by_count":10},{"id":"2006.16205","title":"Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization","created":"2020-06-29","cited_by_count":9},{"id":"2303.04393","title":"Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignment","created":"2023-03-08","cited_by_count":9},{"id":"2305.04507","title":"FedZKP: Federated Model Ownership Verification with Zero-knowledge Proof","created":"2023-05-08","cited_by_count":9},{"id":"2404.07840","title":"On Training Data Influence of GPT Models","created":"2024-04-11","cited_by_count":9},{"id":"2405.13335","title":"Vision Transformer with Sparse Scan Prior","created":"2024-05-22","cited_by_count":6},{"id":"2408.08003","title":"Leveraging Web-Crawled Data for High-Quality Fine-Tuning","created":"2024-08-15","cited_by_count":5},{"id":"2303.06458","title":"ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation","created":"2023-03-11","cited_by_count":4},{"id":"2305.06085","title":"FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature","created":"2023-05-10","cited_by_count":4},{"id":"2007.02238","title":"News Sentiment Analysis","created":"2020-07-05","cited_by_count":2},{"id":"2408.08682","title":"LLM-PCGC: Large Language Model-based Point Cloud Geometry Compression","created":"2024-08-16","cited_by_count":2}],"next_cursor":null}