logo
|
Blog

    Kim Hojin

    About Deep Learning/Machine Learning, Start-up.
    X(https://x.com/DanielKim_a)
    See Allpaperspersonal thoughtsdeeplearning
    Myself

    Myself

    Aug 12, 2023
    personal thoughts
    VQ and FSQ

    VQ and FSQ

    김호진's avatar
    Dec 13, 2025
    deeplearning
    CosyVoice v3 Paper review

    CosyVoice v3 Paper review

    CosyVoice v3 Paper review
    김호진's avatar
    Dec 07, 2025
    papers
    CosyVoice v1, v2 논문 리뷰

    CosyVoice v1, v2 논문 리뷰

    CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
    김호진's avatar
    Aug 17, 2025
    papers
    SupertonicTTS: Towards Highly Scalable and Efficient Text-to-Speech System

    SupertonicTTS: Towards Highly Scalable and Efficient Text-to-Speech System

    Supertone 논문을 읽어보았다.
    김호진's avatar
    Jul 28, 2025
    papers
    Myself

    Myself

    Aug 12, 2023
    personal thoughts
    VQ and FSQ

    VQ and FSQ

    김호진's avatar
    Dec 13, 2025
    deeplearning
    CosyVoice v3 Paper review

    CosyVoice v3 Paper review

    CosyVoice v3 Paper review
    김호진's avatar
    Dec 07, 2025
    papers
    CosyVoice v1, v2 논문 리뷰

    CosyVoice v1, v2 논문 리뷰

    CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
    김호진's avatar
    Aug 17, 2025
    papers
    SupertonicTTS: Towards Highly Scalable and Efficient Text-to-Speech System

    SupertonicTTS: Towards Highly Scalable and Efficient Text-to-Speech System

    Supertone 논문을 읽어보았다.
    김호진's avatar
    Jul 28, 2025
    papers
    Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

    Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

    김호진's avatar
    Jul 19, 2025
    papers
    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
    LTX-Video

    LTX-Video

    ltx-video paper review 논문
    김호진's avatar
    Jul 05, 2025
    papers
    Optimism

    Optimism

    Jul 03, 2025
    personal thoughts
    Seedance technical report 리뷰

    Seedance technical report 리뷰

    Seedance 테크니컬 리포트 리뷰
    김호진's avatar
    Jun 19, 2025
    papers
    DC-AE : AutoEncoder used at SANA

    DC-AE : AutoEncoder used at SANA

    DEEP COMPRESSION AUTOENCODER FOR EFFICIENT HIGH-RESOLUTION DIFFUSION MODELS 논문 리뷰
    김호진's avatar
    Jun 08, 2025
    papers
    Flow matching 논문 리뷰 및 설명

    Flow matching 논문 리뷰 및 설명

    가장 아래에 요약 버전이 있습니다.
    김호진's avatar
    Jun 06, 2025
    papers
    Ezaudio

    Ezaudio

    Ezaudio논문을 읽고
    김호진's avatar
    May 30, 2025
    papers
    Stable Diffusion 3

    Stable Diffusion 3

    Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
    김호진's avatar
    May 28, 2025
    papers
    KV Caching for LLM inference speed

    KV Caching for LLM inference speed

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

    DPO

    Direct Preference Optimization: Your Language Model is Secretly a Reward Model을 읽고
    김호진's avatar
    May 22, 2025
    papers
    SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

    SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

    SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training 논문 리뷰
    김호진's avatar
    May 08, 2025
    papers
    HART : EFFICIENT VISUAL GENERATION WITH HYBRID AUTOREGRESSIVE TRANSFORMER

    HART : EFFICIENT VISUAL GENERATION WITH HYBRID AUTOREGRESSIVE TRANSFORMER

    HART : EFFICIENT VISUAL GENERATION WITH HYBRID AUTOREGRESSIVE TRANSFORMER 논문 리뷰
    김호진's avatar
    May 04, 2025
    papers
    Learning to Act without Actions

    Learning to Act without Actions

    김호진's avatar
    May 04, 2025
    papers
    DIFFUSION MODELS ARE REAL-TIME GAME ENGINES

    DIFFUSION MODELS ARE REAL-TIME GAME ENGINES

    DIFFUSION MODELS ARE REAL-TIME GAME ENGINES
    김호진's avatar
    May 04, 2025
    papers
    ONE STEP DIFFUSION VIA SHORTCUT MODELS

    ONE STEP DIFFUSION VIA SHORTCUT MODELS

    ONE STEP DIFFUSION VIA SHORTCUT MODELS 논문 리뷰
    김호진's avatar
    May 04, 2025
    papers
    이번주에 읽고 생각한 것들(25.05.04)

    이번주에 읽고 생각한 것들(25.05.04)

    김호진's avatar
    May 04, 2025
    personal thoughts
    Common Diffusion Noise Schedules and Sample Steps are Flawed

    Common Diffusion Noise Schedules and Sample Steps are Flawed

    Common Diffusion Noise Schedules and Sample Steps are Flawed 논문 리뷰
    김호진's avatar
    Oct 29, 2024
    papers
    SANA: EFFICIENT HIGH-RESOLUTION IMAGE SYNTHESIS WITH LINEAR DIFFUSION TRANSFORMERS 논문 리뷰

    SANA: EFFICIENT HIGH-RESOLUTION IMAGE SYNTHESIS WITH LINEAR DIFFUSION TRANSFORMERS 논문 리뷰

    SANA by NVIDIA paper review 논문 리뷰
    김호진's avatar
    Oct 24, 2024
    papers
    High-Fidelity Audio Compression with Improved RVQGAN(DAC)

    High-Fidelity Audio Compression with Improved RVQGAN(DAC)

    DAC를 읽었다.
    김호진's avatar
    Oct 02, 2024
    papers
    High-Resolution Image Synthesis with Latent Diffusion Models

    High-Resolution Image Synthesis with Latent Diffusion Models

    High-Resolution Image Synthesis with Latent Diffusion Models 논문 읽기
    김호진's avatar
    Oct 01, 2024
    papers
    Stable audio

    Stable audio

    stable audio 논문 paper 리뷰
    김호진's avatar
    Sep 29, 2024
    papers
    AnimateDiff : ANIMATE YOUR PERSONALIZED TEXT-TO-IMAGE DIFFUSION MODELS WITHOUT SPECIFIC TUNING

    AnimateDiff : ANIMATE YOUR PERSONALIZED TEXT-TO-IMAGE DIFFUSION MODELS WITHOUT SPECIFIC TUNING

    animateDiff 논문 paper
    김호진's avatar
    Sep 27, 2024
    papers
    GAN

    GAN

    GAN 읽기
    김호진's avatar
    Sep 25, 2024
    papers
    VAE 논문 개인적인 리뷰

    VAE 논문 개인적인 리뷰

    김호진's avatar
    Sep 24, 2024
    InstantDrag: Improving Interactivity in Drag-based Image Editing

    InstantDrag: Improving Interactivity in Drag-based Image Editing

    InstantDrag: Improving Interactivity in Drag-based Image Editing 논문 리뷰
    김호진's avatar
    Sep 22, 2024
    papers
    SimCSE: Simple Contrastive Learning of Sentence Embeddings

    SimCSE: Simple Contrastive Learning of Sentence Embeddings

    SimCSE 논문 리뷰
    김호진's avatar
    Sep 19, 2024
    Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation

    Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation

    Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation paper review, 논문 리뷰
    김호진's avatar
    Sep 10, 2024
    papers
    Autoregressive Image Generation without Vector Quantization

    Autoregressive Image Generation without Vector Quantization

    Autoregressive Image Generation without Vector Quantization 논문 리뷰
    김호진's avatar
    Aug 13, 2024
    papers
    Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

    Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

    cycle3D 논문 리뷰
    김호진's avatar
    Aug 12, 2024
    LRM: Large Reconstruction Model for Single Image to 3D

    LRM: Large Reconstruction Model for Single Image to 3D

    LRM 3d paper review
    김호진's avatar
    Aug 08, 2024
    papers
    Efficient Geometry-aware 3D Generative Adversarial Networks

    Efficient Geometry-aware 3D Generative Adversarial Networks

    Efficient Geometry-aware 3D Generative Adversarial Networks 리뷰 for tri-plane understanding
    김호진's avatar
    Aug 08, 2024
    papers
    3D Gaussian Splatting for Real-Time Radiance Field Rendering

    3D Gaussian Splatting for Real-Time Radiance Field Rendering

    3DGS 논문 리뷰
    김호진's avatar
    Aug 05, 2024
    papers
    LANGUAGE MODEL BEATS DIFFUSION — TOKENIZER IS KEY TO VISUAL GENERATION

    LANGUAGE MODEL BEATS DIFFUSION — TOKENIZER IS KEY TO VISUAL GENERATION

    MAGVIT2 논문 리뷰
    김호진's avatar
    Aug 01, 2024
    papers
    VideoPoet: A Large Language Model for Zero-Shot Video Generation

    VideoPoet: A Large Language Model for Zero-Shot Video Generation

    videopoet 논문 리뷰
    김호진's avatar
    Jul 30, 2024
    papers
    Generative Modeling by Estimating Gradients of the Data Distribution

    Generative Modeling by Estimating Gradients of the Data Distribution

    Generative Modeling by Estimating Gradients of the Data Distribution 양송 블로그 리뷰
    김호진's avatar
    Jul 24, 2024
    papers
    VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

    VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

    VASA-1 논문 리뷰
    김호진's avatar
    Jul 23, 2024
    papers
    Rich Human Feedback for Text-to-Image Generation

    Rich Human Feedback for Text-to-Image Generation

    Rich Human Feedback for Text-to-Image Generation 논문 리뷰
    김호진's avatar
    Jul 21, 2024
    papers
    The Platonic Representation Hypothesis

    The Platonic Representation Hypothesis

    The Platonic Representation Hypothesis 논문 리뷰
    김호진's avatar
    Jul 21, 2024
    papers
    ViVid-1-to-3 paper reveiw

    ViVid-1-to-3 paper reveiw

    ViVid-1-to-3 논문 리뷰
    김호진's avatar
    Jul 18, 2024
    papers
    Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction [review]

    Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction [review]

    VAR paper
    Jul 16, 2024
    papers
    [논문 리뷰] Efficient Diffusion Training via Min-SNR Weighting Strategy

    [논문 리뷰] Efficient Diffusion Training via Min-SNR Weighting Strategy

    Min-SNR-감마 : 논문 리뷰
    Oct 09, 2023
    Retrieval Augmented Generation at Planet Scale 아티클

    Retrieval Augmented Generation at Planet Scale 아티클

    논문은 아니고, RAG 관련 글에 대한 번역
    Sep 14, 2023
    papers

    Kim Hojin

    RSS·Powered by Inblog