logo
|
Blog

    Kim Hojin

    About Deep Learning/Machine Learning, Start-up.
    X(https://x.com/DanielKim_a)
    See Allpaperspersonal thoughtsdeeplearning
    The Smol Training Playbook:The Secrets to Building World-Class LLMs

    The Smol Training Playbook:The Secrets to Building World-Class LLMs

    Hugginface의 실용적인 아티클
    May 30, 2026
    deeplearning
    How to build & run on-device model

    How to build & run on-device model

    온디바이스 모델에 대한 이해와 어떻게 모델을 온디바이스화 할 수 있을지
    김호진's avatar
    May 25, 2026
    deeplearning
    VQ and FSQ

    VQ and FSQ

    김호진's avatar
    Dec 13, 2025
    deeplearning
    Mean Flows for One-step Generative Modeling

    Mean Flows for One-step Generative Modeling

    논문을 읽고
    김호진's avatar
    Jul 15, 2025
    deeplearning
    REPRESENTATION ALIGNMENTFOR GENERATION : TRAINING DIFFUSION TRANSFORMERS IS EASIER THAN YOU THINK

    REPRESENTATION ALIGNMENTFOR GENERATION : TRAINING DIFFUSION TRANSFORMERS IS EASIER THAN YOU THINK

    논문을 읽고
    김호진's avatar
    Jul 13, 2025
    deeplearning
    The Smol Training Playbook:The Secrets to Building World-Class LLMs

    The Smol Training Playbook:The Secrets to Building World-Class LLMs

    Hugginface의 실용적인 아티클
    May 30, 2026
    deeplearning
    How to build & run on-device model

    How to build & run on-device model

    온디바이스 모델에 대한 이해와 어떻게 모델을 온디바이스화 할 수 있을지
    김호진's avatar
    May 25, 2026
    deeplearning
    VQ and FSQ

    VQ and FSQ

    김호진's avatar
    Dec 13, 2025
    deeplearning
    Mean Flows for One-step Generative Modeling

    Mean Flows for One-step Generative Modeling

    논문을 읽고
    김호진's avatar
    Jul 15, 2025
    deeplearning
    REPRESENTATION ALIGNMENTFOR GENERATION : TRAINING DIFFUSION TRANSFORMERS IS EASIER THAN YOU THINK

    REPRESENTATION ALIGNMENTFOR GENERATION : TRAINING DIFFUSION TRANSFORMERS IS EASIER THAN YOU THINK

    논문을 읽고
    김호진's avatar
    Jul 13, 2025
    deeplearning
    KV Caching for LLM inference speed

    KV Caching for LLM inference speed

    논문은 아니고 메모
    김호진's avatar
    May 26, 2025
    deeplearning

    Kim Hojin

    RSS·Powered by Inblog