{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","cited_by_count":133},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68},{"id":"2305.15805","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","created":"2023-05-25","cited_by_count":67},{"id":"2203.06211","title":"Staged Training for Transformer Language Models","created":"2022-03-11","cited_by_count":49},{"id":"2306.12517","title":"FFCV: Accelerating Training by Removing Data Bottlenecks","created":"2023-06-21","cited_by_count":49},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37},{"id":"2310.16764","title":"ConvNets Match Vision Transformers at Scale","created":"2023-10-25","cited_by_count":16},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15},{"id":"2307.04526","title":"Self-Expanding Neural Networks","created":"2023-07-10","cited_by_count":14},{"id":"2308.06103","title":"Composable Function-preserving Expansions for Transformer Architectures","created":"2023-08-11","cited_by_count":13},{"id":"2307.10156","title":"Exploring Transformer Extrapolation","created":"2023-07-19","cited_by_count":8},{"id":"2210.01370","title":"Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling","created":"2022-10-04","cited_by_count":4}],"next_cursor":null}