https://daniel.inblog.io About Deep Learning/Machine Learning, Start-up.X(https://x.com/DanielKim_a) Sat, 05 Aug 2023 05:10:35 GMT inblog Sat, 13 Dec 2025 07:08:46 GMT https://image.inblog.dev?url=https%3A%2F%2Fsource.inblog.dev%2Fog_image%2F2024-07-16T23%3A50%3A11.740Z-09972d63-5324-4c4a-82f3-30e2f8edee81&w=1920&q=85 https://daniel.inblog.io https://daniel.inblog.io/85223 Sat, 13 Dec 2025 07:13:10 GMT https://daniel.inblog.io/85223 deeplearning 김호진 https://daniel.inblog.io/cosyvoice-v3-paper-review-83738 CosyVoice v3 Paper review Sun, 07 Dec 2025 12:40:42 GMT https://daniel.inblog.io/cosyvoice-v3-paper-review-83738 papers 김호진 https://daniel.inblog.io/cosyvoice-v1-v2-논문-리뷰-66161 CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizerbased on Supervised Semantic Tokens Sun, 17 Aug 2025 13:25:24 GMT https://daniel.inblog.io/cosyvoice-v1-v2-논문-리뷰-66161 papers 김호진 https://daniel.inblog.io/supertonictts-towards-highly-scalable-and-efficient-texttospeech-system-63566 Supertone 논문을 읽어보았다. Mon, 28 Jul 2025 03:51:36 GMT https://daniel.inblog.io/supertonictts-towards-highly-scalable-and-efficient-texttospeech-system-63566 papers 김호진 https://daniel.inblog.io/reconstruction-vs-generation-taming-optimization-dilemma-in-latent-diffusion-models-62776 null Sat, 19 Jul 2025 05:20:03 GMT https://daniel.inblog.io/reconstruction-vs-generation-taming-optimization-dilemma-in-latent-diffusion-models-62776 papers 김호진 https://daniel.inblog.io/mean-flows-for-onestep-generative-modeling-62342 논문을 읽고 Tue, 15 Jul 2025 11:31:06 GMT https://daniel.inblog.io/mean-flows-for-onestep-generative-modeling-62342 deeplearning 김호진 https://daniel.inblog.io/representation-alignmentfor-generation-training-diffusion-transformers-is-easier-than-you-think-62091 논문을 읽고 Sun, 13 Jul 2025 04:49:06 GMT https://daniel.inblog.io/representation-alignmentfor-generation-training-diffusion-transformers-is-easier-than-you-think-62091 deeplearning 김호진 https://daniel.inblog.io/ltxvideo-61457 ltx-video paper review 논문 Sat, 05 Jul 2025 11:45:38 GMT https://daniel.inblog.io/ltxvideo-61457 papers 김호진 https://daniel.inblog.io/optimism-60973 null Thu, 03 Jul 2025 02:51:44 GMT https://daniel.inblog.io/optimism-60973 personal thoughts https://daniel.inblog.io/seedance-technical-report-리뷰-59377 Seedance 테크니컬 리포트 리뷰 Thu, 19 Jun 2025 00:13:54 GMT https://daniel.inblog.io/seedance-technical-report-리뷰-59377 papers 김호진 https://daniel.inblog.io/dcae-autoencoder-used-at-sana-58187 DEEP COMPRESSION AUTOENCODER FOR EFFICIENT HIGH-RESOLUTION DIFFUSION MODELS 논문 리뷰 Sun, 08 Jun 2025 07:56:29 GMT https://daniel.inblog.io/dcae-autoencoder-used-at-sana-58187 papers 김호진 https://daniel.inblog.io/flow-matching-논문-리뷰-및-설명-58101 가장 아래에 요약 버전이 있습니다. Fri, 06 Jun 2025 04:36:47 GMT https://daniel.inblog.io/flow-matching-논문-리뷰-및-설명-58101 papers 김호진 https://daniel.inblog.io/ezaudio-57370 Ezaudio논문을 읽고 Fri, 30 May 2025 05:20:31 GMT https://daniel.inblog.io/ezaudio-57370 papers 김호진 https://daniel.inblog.io/stable-diffusion-3-56804 Scaling Rectified Flow Transformers for High-Resolution Image Synthesis Wed, 28 May 2025 07:28:32 GMT https://daniel.inblog.io/stable-diffusion-3-56804 papers 김호진 https://daniel.inblog.io/kv-caching-for-llm-inference-speed-56486 논문은 아니고 메모 Mon, 26 May 2025 01:03:33 GMT https://daniel.inblog.io/kv-caching-for-llm-inference-speed-56486 deeplearning 김호진 https://daniel.inblog.io/dpo-56213 Direct Preference Optimization: Your Language Model is Secretly a Reward Model을 읽고 Thu, 22 May 2025 11:38:18 GMT https://daniel.inblog.io/dpo-56213 papers 김호진 https://daniel.inblog.io/sft-memorizes-rl-generalizes-a-comparative-study-of-foundation-model-posttraining-54280 SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training 논문 리뷰 Thu, 08 May 2025 07:46:45 GMT https://daniel.inblog.io/sft-memorizes-rl-generalizes-a-comparative-study-of-foundation-model-posttraining-54280 papers 김호진 https://daniel.inblog.io/hart-efficient-visual-generation-with-hybrid-autoregressive-transformer-53978 HART : EFFICIENT VISUAL GENERATION WITH HYBRID AUTOREGRESSIVE TRANSFORMER 논문 리뷰 Sun, 04 May 2025 07:53:26 GMT https://daniel.inblog.io/hart-efficient-visual-generation-with-hybrid-autoregressive-transformer-53978 papers 김호진 https://daniel.inblog.io/learning-to-act-without-actions-53977 null Sun, 04 May 2025 07:52:09 GMT https://daniel.inblog.io/learning-to-act-without-actions-53977 papers 김호진 https://daniel.inblog.io/diffusion-models-are-realtime-game-engines-53976 DIFFUSION MODELS ARE REAL-TIME GAME ENGINES Sun, 04 May 2025 07:50:59 GMT https://daniel.inblog.io/diffusion-models-are-realtime-game-engines-53976 papers 김호진 https://daniel.inblog.io/one-step-diffusion-via-shortcut-models-53974 ONE STEP DIFFUSION VIA SHORTCUT MODELS 논문 리뷰 Sun, 04 May 2025 07:45:40 GMT https://daniel.inblog.io/one-step-diffusion-via-shortcut-models-53974 papers 김호진 https://daniel.inblog.io/이번주에-읽고-생각한-것들250504-53970 null Sun, 04 May 2025 05:11:09 GMT https://daniel.inblog.io/이번주에-읽고-생각한-것들250504-53970 personal thoughts 김호진 https://daniel.inblog.io/common-diffusion-noise-schedules-and-sample-steps-are-flawed-33386 Common Diffusion Noise Schedules and Sample Steps are Flawed 논문 리뷰 Tue, 29 Oct 2024 10:13:00 GMT https://daniel.inblog.io/common-diffusion-noise-schedules-and-sample-steps-are-flawed-33386 papers 김호진 https://daniel.inblog.io/sana-efficient-highresolution-image-synthesis-with-linear-diffusion-transformers-33065 SANA by NVIDIA paper review 논문 리뷰 Thu, 24 Oct 2024 01:06:27 GMT https://daniel.inblog.io/sana-efficient-highresolution-image-synthesis-with-linear-diffusion-transformers-33065 papers 김호진 https://daniel.inblog.io/highfidelity-audio-compression-with-improved-rvqgandac-30660 DAC를 읽었다. Wed, 02 Oct 2024 14:09:21 GMT https://daniel.inblog.io/highfidelity-audio-compression-with-improved-rvqgandac-30660 papers 김호진 https://daniel.inblog.io/highresolution-image-synthesis-with-latent-diffusion-models-30578 High-Resolution Image Synthesis with Latent Diffusion Models 논문 읽기 Tue, 01 Oct 2024 09:08:24 GMT https://daniel.inblog.io/highresolution-image-synthesis-with-latent-diffusion-models-30578 papers 김호진 https://daniel.inblog.io/stable-audio-30482 stable audio 논문 paper 리뷰 Sun, 29 Sep 2024 12:52:14 GMT https://daniel.inblog.io/stable-audio-30482 papers 김호진 https://daniel.inblog.io/animatediff-animate-your-personalized-texttoimage-diffusion-models-without-specific-tuning-30431 animateDiff 논문 paper Fri, 27 Sep 2024 12:47:46 GMT https://daniel.inblog.io/animatediff-animate-your-personalized-texttoimage-diffusion-models-without-specific-tuning-30431 papers 김호진 https://daniel.inblog.io/gan-30229 GAN 읽기 Wed, 25 Sep 2024 07:50:59 GMT https://daniel.inblog.io/gan-30229 papers 김호진 https://daniel.inblog.io/vae-논문-개인적인-리뷰-30230 null Tue, 24 Sep 2024 04:26:25 GMT https://daniel.inblog.io/vae-논문-개인적인-리뷰-30230 김호진 https://daniel.inblog.io/instantdrag-improving-interactivity-in-dragbased-image-editing-30079 InstantDrag: Improving Interactivity in Drag-based Image Editing 논문 리뷰 Sun, 22 Sep 2024 08:25:23 GMT https://daniel.inblog.io/instantdrag-improving-interactivity-in-dragbased-image-editing-30079 papers 김호진 https://daniel.inblog.io/simcse-simple-contrastive-learning-of-sentence-embeddings-29957 SimCSE 논문 리뷰 Thu, 19 Sep 2024 13:31:48 GMT https://daniel.inblog.io/simcse-simple-contrastive-learning-of-sentence-embeddings-29957 김호진 https://daniel.inblog.io/positive-negative-and-neutral-modeling-implicit-feedback-in-sessionbased-news-recommendation-29158 Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation paper review, 논문 리뷰 Tue, 10 Sep 2024 13:58:26 GMT https://daniel.inblog.io/positive-negative-and-neutral-modeling-implicit-feedback-in-sessionbased-news-recommendation-29158 papers 김호진 https://daniel.inblog.io/autoregressive-image-generation-without-vector-quantization-26465 Autoregressive Image Generation without Vector Quantization 논문 리뷰 Tue, 13 Aug 2024 14:25:00 GMT https://daniel.inblog.io/autoregressive-image-generation-without-vector-quantization-26465 papers 김호진 https://daniel.inblog.io/cycle3d-highquality-and-consistent-imageto3d-generation-via-generationreconstruction-cycle-26109 cycle3D 논문 리뷰 Mon, 12 Aug 2024 01:57:00 GMT https://daniel.inblog.io/cycle3d-highquality-and-consistent-imageto3d-generation-via-generationreconstruction-cycle-26109 김호진 https://daniel.inblog.io/lrm-large-reconstruction-model-for-single-image-to-3d-25764 LRM 3d paper review Thu, 08 Aug 2024 03:20:00 GMT https://daniel.inblog.io/lrm-large-reconstruction-model-for-single-image-to-3d-25764 papers 김호진 https://daniel.inblog.io/efficient-geometryaware-3d-generative-adversarial-networks-25745 Efficient Geometry-aware 3D Generative Adversarial Networks 리뷰 for tri-plane understanding Thu, 08 Aug 2024 01:20:00 GMT https://daniel.inblog.io/efficient-geometryaware-3d-generative-adversarial-networks-25745 papers 김호진 https://daniel.inblog.io/3d-gaussian-splatting-for-realtime-radiance-field-rendering-25309 3DGS 논문 리뷰 Mon, 05 Aug 2024 07:18:00 GMT https://daniel.inblog.io/3d-gaussian-splatting-for-realtime-radiance-field-rendering-25309 papers 김호진 https://daniel.inblog.io/language-model-beats-diffusion-tokenizer-is-key-to-visual-generation-25088 MAGVIT2 논문 리뷰 Thu, 01 Aug 2024 13:53:00 GMT https://daniel.inblog.io/language-model-beats-diffusion-tokenizer-is-key-to-visual-generation-25088 papers 김호진 https://daniel.inblog.io/videopoet-a-large-language-model-for-zeroshot-video-generation-24939 videopoet 논문 리뷰 Tue, 30 Jul 2024 05:07:00 GMT https://daniel.inblog.io/videopoet-a-large-language-model-for-zeroshot-video-generation-24939 papers 김호진 https://daniel.inblog.io/generative-modeling-by-estimating-gradients-of-the-data-distribution-24659 Generative Modeling by Estimating Gradients of the Data Distribution 양송 블로그 리뷰 Wed, 24 Jul 2024 23:26:00 GMT https://daniel.inblog.io/generative-modeling-by-estimating-gradients-of-the-data-distribution-24659 papers 김호진 https://daniel.inblog.io/vasa1-lifelike-audiodriven-talking-faces-generated-in-real-time-24596 VASA-1 논문 리뷰 Tue, 23 Jul 2024 00:45:00 GMT https://daniel.inblog.io/vasa1-lifelike-audiodriven-talking-faces-generated-in-real-time-24596 papers 김호진 https://daniel.inblog.io/rich-human-feedback-for-texttoimage-generation-24500 Rich Human Feedback for Text-to-Image Generation 논문 리뷰 Sun, 21 Jul 2024 04:48:00 GMT https://daniel.inblog.io/rich-human-feedback-for-texttoimage-generation-24500 papers 김호진 https://daniel.inblog.io/the-platonic-representation-hypothesis-24490 The Platonic Representation Hypothesis 논문 리뷰 Sun, 21 Jul 2024 02:33:00 GMT https://daniel.inblog.io/the-platonic-representation-hypothesis-24490 papers 김호진 https://daniel.inblog.io/vivid1to3d-24373 ViVid-1-to-3 논문 리뷰 Thu, 18 Jul 2024 12:05:00 GMT https://daniel.inblog.io/vivid1to3d-24373 papers 김호진 https://daniel.inblog.io/visual-autoregressive-modeling-scalable-image-generation-via-nextscale-prediction-review-2136 VAR paper Tue, 16 Jul 2024 23:45:00 GMT https://daniel.inblog.io/visual-autoregressive-modeling-scalable-image-generation-via-nextscale-prediction-review-2136 papers https://daniel.inblog.io/논문-리뷰-efficient-diffusion-training-via-minsnr-weighting-strategy-2740 Min-SNR-감마 : 논문 리뷰 Mon, 09 Oct 2023 10:51:02 GMT https://daniel.inblog.io/논문-리뷰-efficient-diffusion-training-via-minsnr-weighting-strategy-2740 https://daniel.inblog.io/retrieval-augmented-generation-at-planet-scale-아티클-2135 논문은 아니고, RAG 관련 글에 대한 번역 Thu, 14 Sep 2023 09:58:50 GMT https://daniel.inblog.io/retrieval-augmented-generation-at-planet-scale-아티클-2135 papers https://daniel.inblog.io/llava-논문-읽으면서-생각들-1893 [paper] LLaVA : Visual Instruction Tuning Thu, 31 Aug 2023 15:58:50 GMT https://daniel.inblog.io/llava-논문-읽으면서-생각들-1893 papers https://daniel.inblog.io/일주일간의-생각들-1845 null Tue, 29 Aug 2023 16:24:32 GMT https://daniel.inblog.io/일주일간의-생각들-1845 personal thoughts https://daniel.inblog.io/논문-multipersona-llm-1560 [논문] Multi-persona LLM, UNLEASHING COGNITIVE SYNERGY IN LARGE LANGUAGE MODELS: A TASK SOLVING AGENT THROUGH MULTI-PERSONA SELF-COLLABORATION Sat, 19 Aug 2023 03:04:44 GMT https://daniel.inblog.io/논문-multipersona-llm-1560 papers https://daniel.inblog.io/나를-완성시키는-말-1374 null Sat, 12 Aug 2023 09:50:10 GMT https://daniel.inblog.io/나를-완성시키는-말-1374 personal thoughts https://daniel.inblog.io/하루는-72시간이다-1373 사고방식 Sat, 12 Aug 2023 09:47:45 GMT https://daniel.inblog.io/하루는-72시간이다-1373 personal thoughts https://daniel.inblog.io/speedup-llm-inference-inference-최적화-방법-1368 LLM을 Inference할 때 최적화하는 방법에 관하여 Fri, 11 Aug 2023 16:05:44 GMT https://daniel.inblog.io/speedup-llm-inference-inference-최적화-방법-1368 papers https://daniel.inblog.io/1282 About suffering Mon, 07 Aug 2023 15:39:51 GMT https://daniel.inblog.io/1282 personal thoughts https://daniel.inblog.io/1218 Patterns for Building LLM-based Systems이라는 긴 아티클을 읽고 중요하다고 생각되는 부분만 뽑아서 정리한 내용 Sat, 05 Aug 2023 06:05:22 GMT https://daniel.inblog.io/1218 papers https://daniel.inblog.io/LORA LoRA에 관해서. 읽고 간단하게 작성 논문 : https://arxiv.org/abs/2106.09685 Sat, 05 Aug 2023 05:59:16 GMT https://daniel.inblog.io/LORA papers