Tag: distillation Paper Review: Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes (08 May 2023) All tags paperreview (94) deeplearning (90) cv (44) nlp (38) transformer (23) sota (14) llm (14) pretraining (13) blogpost (13) pytorch (9) imagesegmentation (9) objectdetection (7) career (7) datascience (6) video (5) selfsupervised (4) ner (4) gan (4) styletransfer (3) life (3) kaggle (3) imagecaptioning (3) augmentation (3) audio (3) attention (3) visual (2) tts (2) transferlearning (2) superresolution (2) stablediffusion (2) languagemodel (2) fewshotlearning (2) competition (2) cnn (2) classification (2) weaksupervision (1) unet (1) timeseries (1) tensorflow (1) tabular (1) speechrecognition (1) sentenceembeddings (1) semisupervised (1) robustness (1) robotics (1) relationextrction (1) relationextraction (1) realtime (1) ranking (1) promptengineering (1) objecttracking (1) objectdetecion (1) nlg (1) nas (1) multimodal (1) motivation (1) motiontracking (1) mlp (1) mentoring (1) memoryoptimization (1) languages (1) jigsaw (1) instructlearning (1) inferencespeed (1) imagetextmatching (1) imagerestoration (1) imageinpainting (1) imagegeneration (1) graphneuralnets (1) gpt (1) fail (1) entitylinking (1) endtoend (1) efficiency (1) distillation (1) diffusionmodels (1) diffusion (1) curriculumlreaning (1) contrastivelearning (1) coco (1) chatbot (1) books (1) bert (1) asr (1) annotation (1) anchorfree (1) alignment (1) advice (1) activationfunction (1)