#Zero-shot

Explore GoLLIE, a Large Language Model designed to excel in zero-shot information extraction through adherence to annotation guidelines. This model supports creating dynamic annotation schemas and goes beyond existing knowledge with detailed definitions. GoLLIE's improved performance is available to the public on the HuggingFace Hub, with comprehensive instructions for installation, usage, and dataset generation, aiding customization in information extraction tasks.

ZMM-TTS is a framework that utilizes self-supervised discrete speech representations for multilingual and multispeaker text-to-speech synthesis. The model integrates text-based and speech-based self-supervised learning models to improve speech naturalness and speaker similarity in high-resource languages. It effectively performs zero-shot speech synthesis in low-resource languages, providing high intelligibility and speaker resemblance without prior data. Discover the pre-trained models for six languages and the MM6 dataset, created for balanced multilingual training. Explore speech synthesis in different languages with ZMM-TTS.

Discover GenerSpeech, a text-to-speech model designed for high-fidelity zero-shot style transfer with out-of-domain voices. Featuring advanced multi-level style transfer and generalization capabilities, it supports various datasets with available pretrained models. Access guidelines for seamless inference and data preparation to efficiently implement and train models, all while adhering to ethical standards.

Using pre-trained diffusion models, this tool provides quick zero-shot video editing based on text prompts, delivering high-quality results without extra training. Its noise shuffling technique keeps videos temporally consistent and efficiently manages any video length. This solution supports versatile edits, from local changes to shape transformations, across varied scenes with dynamic and complex activities.

Explore the curated list of Language-Model-as-a-Service (LMaaS) papers designed for NLP researchers. Understand how pre-trained large language models, such as GPT-3, are provided as services, focusing on deployment efficiencies and tuning methods that don't require access to model parameters. Investigate strategies like text prompts, in-context learning, black-box optimization, and feature-based learning for task-specific customization. Suitable for researchers aiming to enhance LLM utility across varied applications and foster flexible research in linguistic fields.