{"list":"other","total":45,"rows":[{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"1904.01802","title":"Correlation Congruence for Knowledge Distillation","created":"2019-04-03","cited_by_count":285},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"1511.05641","title":"Net2Net: Accelerating Learning via Knowledge Transfer","created":"2015-11-18","cited_by_count":250},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181},{"id":"1908.03930","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","created":"2019-08-11","cited_by_count":178},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88},{"id":"2103.13425","title":"Diverse Branch Block: Building a Convolution as an Inception-like Unit","created":"2021-03-24","cited_by_count":87},{"id":"2009.08825","title":"Densely Guided Knowledge Distillation using Multiple Teacher Assistants","created":"2020-09-18","cited_by_count":83},{"id":"2110.07143","title":"bert2BERT: Towards Reusable Pretrained Language Models","created":"2021-10-14","cited_by_count":70},{"id":"1710.10348","title":"Multi-level Residual Networks from Dynamical Systems View","created":"2017-10-27","cited_by_count":59},{"id":"2302.02210","title":"Oscillation-free Quantization for Low-bit Vision Transformers","created":"2023-02-04","cited_by_count":57},{"id":"1811.10495","title":"ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks","created":"2018-11-26","cited_by_count":53},{"id":"2305.15712","title":"Knowledge Diffusion for Distillation","created":"2023-05-25","cited_by_count":53},{"id":"1805.05551","title":"Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students","created":"2018-05-15","cited_by_count":50},{"id":"2008.01475","title":"Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap","created":"2020-08-04","cited_by_count":50},{"id":"2203.06211","title":"Staged Training for Transformer Language Models","created":"2022-03-11","cited_by_count":49},{"id":"1706.00388","title":"DiracNets: Training Very Deep Neural Networks Without Skip-Connections","created":"2017-06-01","cited_by_count":47},{"id":"2303.07336","title":"MP-Former: Mask-Piloted Transformer for Image Segmentation","created":"2023-03-13","cited_by_count":39},{"id":"2011.13635","title":"Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup","created":"2020-11-27","cited_by_count":31},{"id":"1909.11723","title":"Revisiting Knowledge Distillation via Label Smoothing Regularization","created":"2019-09-25","cited_by_count":29},{"id":"2006.12030","title":"DO-Conv: Depthwise Over-parameterized Convolutional Layer","created":"2020-06-22","cited_by_count":28},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23},{"id":"1907.09643","title":"Highlight Every Step: Knowledge Distillation via Collaborative Teaching","created":"2019-07-23","cited_by_count":21},{"id":"2109.03508","title":"RepNAS: Searching for Efficient Re-parameterizing Blocks","created":"2021-09-08","cited_by_count":11},{"id":"1912.04749","title":"Efficient Differentiable Neural Architecture Search with Meta Kernels","created":"2019-12-10","cited_by_count":6},{"id":"2110.10921","title":"CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization","created":"2021-10-21","cited_by_count":6}],"next_cursor":null}