← Search

Kanishk Singh

3 accepted papers

2024

TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings

EMNLP 2024finding

The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style transfer methods generally rely on the few-shot capabilities of large language models or on complex controllable text generat…

2023

Learning to Follow Object-Centric Image Editing Instructions Faithfully

EMNLP 2023long findings

Natural language instructions are a powerful interface for editing the outputs of text-to-image diffusion models. However, several challenges need to be addressed: 1) underspecification (the need to model the implicit meaning of instructions) 2) grounding (the need to localize where the edit has to…

Cited by 0SourcecodeScholar
2022

CounterGeDi: A Controllable Approach to Generate Polite, Detoxified and Emotional Counterspeech

IJCAI 2022poster

Recently, many studies have tried to create generation models to assist counter speakers by providing counterspeech suggestions for combating the explosive proliferation of online hate. However, since these suggestions are from a vanilla generation model, they might not include the appropriate prope…