Architectures

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models ICML 2021 Pivot Based Transfer Learning for Neural Machine Translation: CFILT IITB @ WMT 2021 Triangular MT EMNLP 2021 Pixel Codec Avatars CVPR 2021 Pixel Difference Networks for Efficient Edge Detection ICCV 2021 pixelNeRF: Neural Radiance Fields From One or Few Images CVPR 2021 Pixel-Perfect Structure-From-Motion With Featuremetric Refinement ICCV 2021 PixelTransformer: Sample Conditioned Signal Generation ICML 2021 Plan2Scene: Converting Floorplans to 3D Scenes CVPR 2021 PlaneTR: Structure-Guided Transformers for 3D Plane Recovery ICCV 2021 Planning from Pixels in Atari with Learned Symbolic Representations AAAI 2021 Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks AAAI 2021 Plan-then-Generate: Controlled Data-to-Text Generation via Planning EMNLP 2021 PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context ACL 2021 PLUGIn: A simple algorithm for inverting generative models with recovery guarantees NeurIPS 2021 PLUR: A Unifying, Graph-Based View of Program Learning, Understanding, and Repair NeurIPS 2021 PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS Interspeech 2021 PnP-DETR: Towards Efficient Visual Analysis With Transformers ICCV 2021 PoGO-Net: Pose Graph Optimization With Graph Neural Networks ICCV 2021 Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos CVPR 2021 Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding IJCAI 2021 Point Cloud Semantic Scene Completion from RGB-D Images AAAI 2021 Point Cloud Upsampling via Disentangled Refinement CVPR 2021 Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation ACL 2021 PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery IJCAI 2021 PoinTr: Diverse Point Cloud Completion With Geometry-Aware Transformers ICCV 2021