Made with inblog

바세린용자 (yongja)

Reinforcement Learning from Human Feedback 1,2장

Jun 27, 2026

Adaptive Keyframe Sampling for Long Video Understanding

Jun 21, 2026

EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use

Jun 07, 2026

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Game

May 11, 2026

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

Apr 20, 2026

OpenVLA: An Open-Source Vision-Language-Action Model

Apr 20, 2026

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Apr 12, 2026

MagicVideo: Efficient Video Generation With Latent Diffusion Models

Mar 29, 2026

Video Diffusion Models (VDM)

Mar 15, 2026

InstantID: Zero-shot Identity Preserving Generation in Seconds

Feb 01, 2026

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Jan 24, 2026

LoRA: Low-Rank Adaptation of Large Language Models

Jan 17, 2026

Textual Inversion: An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Jan 11, 2026

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

Jan 04, 2026

LDM: High-Resolution Image Synthesis with Latent Diffusion Models

Dec 21, 2025

VQ-VAE: Neural Discrete Representation Learning

Dec 14, 2025

컴퓨터비전

MAE와 MSE는 부호를 없애는데 어떻게 regression이 학습되는 걸까?

regression loss의 미분값에 대한 이해

Jun 29, 2024

딥러닝

왜 Re-Identification에서 GeM을 쓸까?

GeM Pooling VS Max Pooling vs Average Pooling

Jun 29, 2024

컴퓨터비전딥러닝

[Knowledge Distillation] Learning from a Teacher using Unlabeled Data

Unlabelling 데이터를 활용하여 Teacher보다 똑똑한 Student 만들기

Jun 02, 2024

컴퓨터비전경량화딥러닝

kjyong

Reinforcement Learning from Human Feedback 1,2장

Adaptive Keyframe Sampling for Long Video Understanding

EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Game

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

OpenVLA: An Open-Source Vision-Language-Action Model

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

MagicVideo: Efficient Video Generation With Latent Diffusion Models

Video Diffusion Models (VDM)

InstantID: Zero-shot Identity Preserving Generation in Seconds

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

LoRA: Low-Rank Adaptation of Large Language Models

Textual Inversion: An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

LDM: High-Resolution Image Synthesis with Latent Diffusion Models

VQ-VAE: Neural Discrete Representation Learning

MAE와 MSE는 부호를 없애는데 어떻게 regression이 학습되는 걸까?

왜 Re-Identification에서 GeM을 쓸까?

[Knowledge Distillation] Learning from a Teacher using Unlabeled Data

kjyong

Reinforcement Learning from Human Feedback 1,2장

Adaptive Keyframe Sampling for Long Video Understanding

EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use

CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Game

ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models

OpenVLA: An Open-Source Vision-Language-Action Model

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

MagicVideo: Efficient Video Generation With Latent Diffusion Models

Video Diffusion Models (VDM)

InstantID: Zero-shot Identity Preserving Generation in Seconds

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

LoRA: Low-Rank Adaptation of Large Language Models

Textual Inversion: An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

LDM: High-Resolution Image Synthesis with Latent Diffusion Models

VQ-VAE: Neural Discrete Representation Learning

MAE와 MSE는 부호를 없애는데 어떻게 regression이 학습되는 걸까?

왜 Re-Identification에서 GeM을 쓸까?

[Knowledge Distillation] Learning from a Teacher using Unlabeled Data