Knowledge Distillation

Safe Distillation Box AAAI 2022 Samsung R&D Institute Poland Participation in WMT 2022 EMNLP 2022 Samsung Research Philippines - Datasaur AI’s Submission for the WMT22 Large Scale Multilingual Translation Task EMNLP 2022 Self-supervised Models are Good Teaching Assistants for Vision Transformers ICML 2022 Semi-Supervised Domain Adaptation via Sample-to-Sample Self-Distillation WACV 2022 Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation CVPR 2022 Slimmable Domain Adaptation CVPR 2022 SMASH: Improving SMAll Language Models’ Few-SHot Ability with Prompt-Based Distillation EMNLP 2022 Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm ACL 2022 Sparse Teachers Can Be Dense with Knowledge EMNLP 2022 Spatial-Channel Token Distillation for Vision MLPs ICML 2022 Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation Interspeech 2022 Structured Pruning Learns Compact and Accurate Models ACL 2022 Symbolic Distillation for Learned TCP Congestion Control NeurIPS 2022 Symbolic Knowledge Distillation: from General Language Models to Commonsense Models NAACL 2022 TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation COLING 2022 Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection CVPR 2022 Teach Less, Learn More: On the Undistillable Classes in Knowledge Distillation NeurIPS 2022 TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge ACL 2022 The NiuTrans Machine Translation Systems for WMT22 EMNLP 2022 The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022 ACL 2022 Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation EMNLP 2022 ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection EMNLP 2022 Towards Efficient 3D Object Detection with Knowledge Distillation NeurIPS 2022 Transferring Knowledge from Structure-aware Self-attention Language Model to Sequence-to-Sequence Semantic Parsing COLING 2022