Blog(1)

• Text-Aware Adapter for Few-Shot Keyword Spotting

  Keyword spotting (KWS) is a technique for detecting pre-defined keywords in audio streams.

Research Areas(0)

Publications(4)

• Compress & Cache: Vision token compression for efficient generation and retrieval

  AuthorAdrian Bulat, Yassine Ouali, Georgios Tzimiropoulos

  PublishedNeural Information Processing Systems (NeurIPS)

  Date2025-12-03

• Neural Fine-Tuning Search for Few-Shot Learning

  AuthorDa Li, Timothy Hospedales

  PublishedInternational Conference on Learning Representation (ICLR)

  Date2024-05-07

• HOP to the Next Tasks and Domains for Continual Learning in NLP

  AuthorUmberto Michieli, Mete Ozay

  PublishedNational Conference on Artificial Intelligence (AAAI)

  Date2024-03-24

View More

News(3)

• [Blog] GalaxyEdit: Large Scale Image Editing Dataset with Enhanced Diffusion Adapter

  Have you ever wished you could easily add or remove objects in your photos—like adding a candle on the top of your birthday cake, or removing that background person from your photo?

• [Blog] Efficient Compositional Multi-tasking for On-device Large Language Models

  Adapter parameters [2] provide a mechanism to modify the behaviour of machine learning models and have gained significant popularity in the context of large language models (LLMs) and generative AI.

• [Blog] Text-Aware Adapter for Few-Shot Keyword Spotting

  Keyword spotting (KWS) is a technique for detecting pre-defined keywords in audio streams.

Others(0)