Self-Supervised Learning

The Unsurprising Effectiveness of Pre-Trained Vision Models for Control ICML 2022 The ZevoMOS entry to VoiceMOS Challenge 2022 Interspeech 2022 Third-Party Aligner for Neural Word Alignments EMNLP 2022 Time Is MattEr: Temporal Self-supervision for Video Transformers ICML 2022 Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation EMNLP 2022 TLDR at SemEval-2022 Task 1: Using Transformers to Learn Dictionaries and Representations SemEval 2022 Torsional Diffusion for Molecular Conformer Generation NeurIPS 2022 To Smooth or Not? When Label Smoothing Meets Noisy Labels ICML 2022 Touch and Go: Learning from Human-Collected Vision and Touch NeurIPS 2022 Toward a realistic model of speech processing in the brain with self-supervised learning NeurIPS 2022 Toward Compositional Generalization in Object-Oriented World Modeling ICML 2022 Toward Low-Cost End-to-End Spoken Language Understanding Interspeech 2022 Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning ICLR 2022 Towards Contextually Sensitive Analysis of Memes: Meme Genealogy and Knowledge Base IJCAI 2022 Towards Joint Intent Detection and Slot Filling via Higher-order Attention IJCAI 2022 Towards Language-Free Training for Text-to-Image Generation CVPR 2022 Towards Learning (Dis)-Similarity of Source Code from Program Contrasts ACL 2022 Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective CVPR 2022 Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer NAACL 2022 Towards Robust k-Nearest-Neighbor Machine Translation EMNLP 2022 Towards Understanding the Data Dependency of Mixup-style Training ICLR 2022 Towards Unified Prompt Tuning for Few-shot Text Classification EMNLP 2022 Training and Evaluation of Deep Policies Using Reinforcement Learning and Generative Models JMLR 2022 Training and Inference on Any-Order Autoregressive Models the Right Way NeurIPS 2022 Training speaker recognition systems with limited data Interspeech 2022