Blog(1)

• [CVPR 2023 Series #3] GENIE: Show Me the Data for Quantization

  Since the scale of the state-of-the-art AI models has become deeper, model compression also has been attracting more attention as a method to let models be deployed on edge devices without accessing cloud servers.

Research Areas(0)

Publications(23)

• Progressive Mixed-Precision Decoding for Efficient LLM Inference

  AuthorHao (Mark) Chen, Fuwen Tan, Alexandros Kouris, Royson Lee, Stylianos Venieris

  PublishedInternational Conference on Learning Representation (ICLR)

  Date2025-04-25

• QBB: Quantization with Binary Bases for LLMs

  AuthorAdrian Bulat, Yassine Ouali, Georgios Tzimiropoulos

  PublishedNeural Information Processing Systems (NeurIPS)

  Date2024-12-11

• Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers

  AuthorJunhan Kim, Chungman Lee, Eulrang Cho, Kyungphil Park, Ho-young Kim, Joonyoung Kim, Yongkweon Jeon

  PublishedNeural Information Processing Systems (NeurIPS)

  Date2024-12-11

View More

News(3)

• [Blog] A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization

  Research in Automatic Speech Recognition (ASR) continues to show that larger models yield better results. But while state-of-the-art networks continue to grow with billions of parameters, the difficulty of deploying these models on device also increases.

• [Blog] [CVPR 2023 Series #3] GENIE: Show Me the Data for Quantization

  Since the scale of the state-of-the-art AI models has become deeper, model compression also has been attracting more attention as a method to let models be deployed on edge devices without accessing cloud servers.

• [Blog] A Mixed Quantization Network for Efficient Mobile Inverse Tone Mapping

  At the British Machine Vision Conference (BMVC) 2021, we disseminated work on mobile inverse tone mapping. In this work, we tackled converting high resolution images to high dynamic range (HDR) images in real-time with a mobile-focused model which utilized low-bit quantization of its parameters in order to accelerate inference.

Others(0)