InTDS ArchivebyRohit Pillai·Jan 4, 2021CODIR: Train smaller, faster NLP modelsA unique approach to knowledge distillation
InTDS ArchivebyRohit Pillai·Dec 16, 2020SpanFact: Fix your factually incorrect summariesA suite of models that fixes inaccuracies in summaries of large text
InTDS ArchivebyRohit Pillai·Sep 17, 2020HERO: You’ll never have to watch long videos againA model that understands a video and its subtitles to help you speed through it
InThe StartupbyRohit Pillai·Sep 16, 2020FILTER: Understand Foreign Languages BetterA technique that promotes a deeper understanding and linkage between the same text in different languages
InTDS ArchivebyRohit Pillai·Aug 22, 2020DiscoBERT: A BERT that shortens your reading timeA Discourse Aware BERT that improves summary generation
InThe StartupbyRohit Pillai·Aug 7, 2020Distill-BERT: Using BERT for Smarter Text GenerationGenerate better stories, essays, answers and more using BERT’s knowledge
InTDS ArchivebyRohit Pillai·Jul 13, 2020VILLA: A Generic Adversarial Training technique for Vision-and-LanguageThe first multimodal adversarial training technique for image and text models
InThe StartupbyRohit Pillai·May 15, 2020BachGAN: Let your imagination run freeCreate real images with just boxes!
InThe StartupbyRohit Pillai·May 3, 2020VIOLIN: Do you really understand videos?A new task and dataset that requires multi-modal understanding of videos and text
InTDS ArchivebyRohit Pillai·Mar 5, 2020UNITERLearning a joint representation of image and text that everything can useA response icon1A response icon1