{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"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},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"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":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1901.09321","title":"Fixup Initialization: Residual Learning Without Normalization","created":"2019-01-27","cited_by_count":198},{"id":"2209.05433","title":"FP8 Formats for Deep Learning","created":"2022-09-12","cited_by_count":196},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"1812.08011","title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","created":"2018-12-19","cited_by_count":164},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161},{"id":"2009.12812","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","created":"2020-09-27","cited_by_count":148},{"id":"2004.07320","title":"Training with Quantization Noise for Extreme Model Compression","created":"2020-04-15","cited_by_count":145},{"id":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101},{"id":"1912.12607","title":"Towards Unified INT8 Training for Convolutional Neural Network","created":"2019-12-29","cited_by_count":79},{"id":"2304.09871","title":"A Theory on Adam Instability in Large-Scale Machine Learning","created":"2023-04-19","cited_by_count":56},{"id":"2101.05615","title":"FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference","created":"2021-01-13","cited_by_count":41},{"id":"1804.01526","title":"Training DNNs with Hybrid Block Floating Point","created":"2018-04-04","cited_by_count":40},{"id":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31},{"id":"2102.04782","title":"Distribution Adaptive INT8 Quantization for Training CNNs","created":"2021-02-09","cited_by_count":28},{"id":"1905.12334","title":"Mixed Precision Training With 8-bit Floating Point","created":"2019-05-29","cited_by_count":23},{"id":"2001.05674","title":"Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks","created":"2020-01-16","cited_by_count":23},{"id":"2304.02034","title":"Effective Theory of Transformers at Initialization","created":"2023-04-04","cited_by_count":21},{"id":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17},{"id":"2112.14938","title":"Automatic Mixed-Precision Quantization Search of BERT","created":"2021-12-30","cited_by_count":16},{"id":"2302.01327","title":"Dual PatchNorm","created":"2023-02-02","cited_by_count":9}],"next_cursor":null}