Universal Image Segmentation is not a new concept. Past attempts to unify image segmentation in the last decades include scene parsing, panoptic segmentation, and, more recently, new panoptic architectures. We propose OneFormer, a universal image segmentation framework that unifies segmentation with a multi-task train-once design.

In this paper, we revisited the core design ideas of stateof-the-art deep inpainting networks. We propose an intuitive and effective inpainting architecture that augments the powerful comodulated StyleGAN2 generator with the high receptiveness ability of FFC to achieve equally good performance on both textures and structures.

Embodied Instruction Following (EIF) is a challenging problem requiring an agent to infer a sequence of actions to achieve a goal environment state from complex language and visual inputs. We propose a generalised Language Guided Meta-Controller (LMC) for better language grounding in the large action space of the embodied agent. We additionally propose an auxiliary reasoning loss to improve the ‘conceptual grounding’ of the agent. Our empirical validation shows that our approach outperforms strong baselines on the Execution from Dialogue History (EDH) benchmark from the TEACh benchmark.

In this paper, we address the problem of offensive language detection on Twitter, while also detecting the type and the target of the offence. We propose a novel approach called SyLSTM, which integrates syntactic features in the form of the dependency parse tree of a sentence and semantic features in the form of word embeddings into a deep learning architecture using a Graph Convolutional Network. Results show that the proposed approach significantly outperforms the state-of-the-art BERT model with orders of magnitude fewer number of parameters.

Pre-trained neural Language Models (PTLM), such as CodeBERT, are recently used in software engineering as models pre-trained on large source code corpora. Although adapters are known to facilitate adapting to many downstream tasks compared to fine-tuning the model that require retraining all of the models’ parameters – which owes to the adapters’ plug and play nature and being parameter efficient – their usage in software engineering is not explored.