- Видео 60
- Просмотров 15 021
MLV TV
Добавлен 21 ноя 2021
고려대학교 정보대학 컴퓨터학과 기계학습 및 비전 연구실.
김현우 교수님과 열정적인 학생들의 연구 이야기와 재미있는 연구실 생활 이야기들을 채워가고 있습니다.
연구실 홈페이지
mlv.korea.ac.kr/
김현우 교수님과 열정적인 학생들의 연구 이야기와 재미있는 연구실 생활 이야기들을 채워가고 있습니다.
연구실 홈페이지
mlv.korea.ac.kr/
[ECCV 2024 Oral] Presentation of DAVI in Milan
Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems
Sojin Lee*, Dogyun Park*, Inho Kong, Hyunwoo J. Kim
Paper: www.arxiv.org/pdf/2407.16125
GitHub: github.com/mlvlab/DAVI
Project: mlvlab.github.io/DAVI-project/
Presentation: ruclips.net/video/MT6T4D_6h5w/видео.html
(Abstract)
Recent studies on inverse problems have proposed posterior samplers that leverage the pre-trained diffusion models as powerful priors. These attempts have paved the way for using diffusion models in a wide range of inverse problems. However, the existing methods entail computationally demanding iterative sampling procedures and optimize a separate solution for each measurement, which leads to li...
Sojin Lee*, Dogyun Park*, Inho Kong, Hyunwoo J. Kim
Paper: www.arxiv.org/pdf/2407.16125
GitHub: github.com/mlvlab/DAVI
Project: mlvlab.github.io/DAVI-project/
Presentation: ruclips.net/video/MT6T4D_6h5w/видео.html
(Abstract)
Recent studies on inverse problems have proposed posterior samplers that leverage the pre-trained diffusion models as powerful priors. These attempts have paved the way for using diffusion models in a wide range of inverse problems. However, the existing methods entail computationally demanding iterative sampling procedures and optimize a separate solution for each measurement, which leads to li...
Просмотров: 92
Видео
![[ECCV 2024 Oral] Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems](http://i.ytimg.com/vi/MT6T4D_6h5w/mqdefault.jpg)
![[ECCV 2024 Oral] Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems](/img/tr.png)
[ECCV 2024 Oral] Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems
Просмотров 335Месяц назад
Sojin Lee*, Dogyun Park*, Inho Kong, Hyunwoo J. Kim Paper: www.arxiv.org/pdf/2407.16125 GitHub: github.com/mlvlab/DAVI Project: mlvlab.github.io/DAVI-project/ Timestamps: 0:00 Intro 0:11 Definition of Inverse Problems 0:51 Comparison with baselines - Inference Speed 1:45 Comparison with baselines - Inference & Optimization 2:29 Method 5:30 Experiments 5:49 Outro (Abstract) Recent studies on inv...
Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis (ICML, 2024)
Просмотров 2094 месяца назад
Juyeon Ko*, Inho Kong*, Dogyun Park, Hyunwoo J. Kim (Abstract) Semantic image synthesis (SIS) is a task to generate realistic images corresponding to semantic maps (labels). However, in real-world applications, SIS often encounters noisy user inputs. To address this, we propose Stochastic Conditional Diffusion Model (SCDM), which is a robust conditional diffusion model that features novel forwa...
Retrieval-Augmented Open-Vocabulary Object Detection (CVPR 2024)
Просмотров 2964 месяца назад
Jooyeon Kim*, Eulrang Cho*, Sehyung Kim, Hyunwoo J. Kim (Abstract) Open-vocabulary object detection (OVD) has been studied with Vision-Language Models (VLMs) to detect novel objects beyond the pre-trained categories. Previous approaches improve the generalization ability to expand the knowledge of the detector, using ‘positive’ pseudo-labels with additional ‘class’ names, e.g., sock, iPod, and ...
대학원생을 위한 유용한 맥 프로그램 추천
Просмотров 2 тыс.4 месяца назад
MLV에 입학하면 개인 데스크탑이 주어지는데요, 많은 학생들이 Mac mini를 사용하고 있답니다! 대학원생에게 유용하고 편리한 맥 프로그램은 어떤 것이 있을지 MLV TV에서 학생들에게 직접 물어봤습니다! #대학원 #대학원생 #앱추천 #MacBookPro #MacBookAir #MacMini
Prompt Learning via Meta-Regularization (CVPR 2024)
Просмотров 1465 месяцев назад
Prompt Learning via Meta-Regularization Jinyoung Park, Juyeon Ko, Hyunwoo J. Kim Computer Vision and Pattern Recognition (CVPR), 2024 (Abstract) Pre-trained vision-language models have shown impressive success on various computer vision tasks with their zero-shot generalizability. Recently, prompt learning approaches have been explored to efficiently and effectively adapt the vision-language mo...
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based VRD(CVPR'24)
Просмотров 845 месяцев назад
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection Jongha Kim*, Jihwan Park*, Jinyoung Park*, Jinyoung Kim, Sehyung Kim, Hyunwoo J. Kim Computer Vision and Pattern Recognition (CVPR), 2024 Visual Relationship Detection (VRD) has seen significant advancements with Transformer-based architectures recently. However, we identify two...
vid-TLDR: Training Free Token merging for Light-weight Video Transformer (CVPR 2024)
Просмотров 1185 месяцев назад
vid-TLDR: Training Free Token merging for Light-weight Video Transformer Joonmyung Choi*, Sanghyeok Lee*, Jaewon Chu, Minhyuk Choi, Hyunwoo J. Kim Computer Vision and Pattern Recognition (CVPR), 2024 (Abstract) Video Transformers have become the prevalent solution for various video downstream tasks with superior expressive power and flexibility. However, these video transformers suffer from hea...
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision (CVPR 2024)
Просмотров 1045 месяцев назад
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Sanghyeok Lee*, Joonmyung Choi*, Hyunwoo J. Kim Computer Vision and Pattern Recognition (CVPR), 2024 (Abstract) Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redunda...
[MLVlog] MLV의 봄 소풍
Просмотров 3156 месяцев назад
날씨 좋은 어느 봄날 인턴분들도 함께한 MLV의 소풍 영상입니다! 드론도 날리고 게임도 즐기는 MLV! #대학원 #대학원생 #소풍 #게임 #드론 #대학원브이로그
[MLVlog] MLV의 겨울방학
Просмотров 3228 месяцев назад
대학원생은 겨울방학을 어떻게 보낼까요? MLV TV 에서 MLV 의 겨울방학 모습을 담아봤습니다! #대학원 #대학원생일상 #대학원생 #대학원생브이로그
Advancing Bayesian Optimization via Learning Smooth Latent Spaces (NeurIPS 2023)
Просмотров 21711 месяцев назад
Advancing Bayesian Optimization via Learning Smooth Latent Spaces Seunghun Lee*, Jaewon Chu*, Sihyeon Kim*, Juyeon Ko, Hyunwoo J. Kim Advances in Neural Information Processing Systems (NeurIPS), 2023 (Abstract) Bayesian optimization is a powerful method for optimizing black-box functions with limited function evaluations. Recent works have shown that optimization in a latent space through deep ...
NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA (NeurIPS 2023)
Просмотров 17911 месяцев назад
NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA Hyeong Kyu Choi, Seunghun Lee, Jaewon Chu, Hyunwoo J. Kim Advances in Neural Information Processing Systems (NeurIPS), 2023 (Abstract) Multi-hop Knowledge Graph Question Answering (KGQA) is a task that involves retrieving nodes from a knowledge graph (KG) to answer natural language questions. Recent GNN-based approaches formulate this...
[한글설명] LLMs are Temporal and Causal Reasoners for VQA (EMNLP 2023)
Просмотров 29411 месяцев назад
EMNLP 2023 에 게재된 Large Language Models are Temporal and Causal Reasoners for Video Question Answering 논문의 한국어 발표 영상입니다. 발표자: 고도환 - Large Language Models are Temporal and Causal Reasoners for Video Question Answering Dohwan Ko*, Ji Soo Lee*, Woo-Young Kang, Byungseok Roh, Hyunwoo J. Kim Empirical Methods in Natural Language Processing (EMNLP), 2023
Unconstrained Pose Prior-Free Neural Radiance Field (NeurIPS 2023)
Просмотров 15511 месяцев назад
Unconstrained Pose Prior-Free Neural Radiance Field (NeurIPS 2023) Injae Kim*, Minhyuk Choi*, Hyunwoo J. Kim paper link : arxiv.org/pdf/2311.03784.pdf (Abstract) Neural Radiance Field (NeRF) has enabled novel view synthesis with high fidelity given images and camera poses. Subsequent works even succeeded in eliminating the necessity of pose priors by jointly optimizing NeRF and camera pose. How...
2022 MLV Lab Seminar - Vector-Quantized Diffusion Models
Просмотров 7311 месяцев назад
2022 MLV Lab Seminar - Vector-Quantized Diffusion Models
2022 MLV Lab Seminar - Neural Radiance Fields
Просмотров 5311 месяцев назад
2022 MLV Lab Seminar - Neural Radiance Fields
2022 MLV Lab Seminar - Convolutional Transformer
Просмотров 5711 месяцев назад
2022 MLV Lab Seminar - Convolutional Transformer
2022 MLV Lab Seminar - Generative Model is All You Need!
Просмотров 6611 месяцев назад
2022 MLV Lab Seminar - Generative Model is All You Need!
2022 MLV Lab Seminar - Video & Multi-modal Understanding
Просмотров 8211 месяцев назад
2022 MLV Lab Seminar - Video & Multi-modal Understanding
2022 MLV Lab Seminar - Human Object Interaction Detection
Просмотров 6611 месяцев назад
2022 MLV Lab Seminar - Human Object Interaction Detection
2022 MLV Lab Seminar - Augmented Neural ODEs
Просмотров 6611 месяцев назад
2022 MLV Lab Seminar - Augmented Neural ODEs
2022 MLV Lab Seminar - Data Augmentation on Point Clouds
Просмотров 4811 месяцев назад
2022 MLV Lab Seminar - Data Augmentation on Point Clouds
2022 MLV Lab Seminar - Introduction to GNNs
Просмотров 9511 месяцев назад
2022 MLV Lab Seminar - Introduction to GNNs
Large Language Models are Temporal and Causal Reasoners for Video Question Answering (EMNLP 2023)
Просмотров 20411 месяцев назад
Large Language Models are Temporal and Causal Reasoners for Video Question Answering (EMNLP 2023)
[한글설명] Open-vocabulary Video Question Answering (ICCV 2023)
Просмотров 171Год назад
[한글설명] Open-vocabulary Video Question Answering (ICCV 2023)
Read-only Prompt Optimization for Vision-Language Few-shot Learning (ICCV 2023)
Просмотров 135Год назад
Read-only Prompt Optimization for Vision-Language Few-shot Learning (ICCV 2023)
Open-Vocabulary Video Question Answering (ICCV 2023)
Просмотров 79Год назад
Open-Vocabulary Video Question Answering (ICCV 2023)
great work guys 😇
좋은영상 감사합니다. 디퓨전모델 공부하다보니 결국 VAE, GAN, Flow모델까지 다 공부해야하네요. 최신모델들은 결국 기존에 있던것들 다 끌어다 쓰다보니...
Great video! Any plans for future research to build on this?
2025년에도 보고있는사람?
JYP brought me here! 😃 I can't wait to apply SCDM to our product.
Finally! Ages-old ideas like hard negatives and sub-concepts brought back to life.
뭐야 이 슬픈 영상은 하 왜 몇년뒤에 와서 꿀팁 받아갈 것 같지?? 불안하네..
MLV TV 최고 🥰
Great!
Very nice presentation! It helped me understanding the normalizing flow.
😊00😊0
ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ
ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ 하입널프
1:58
Very wholesome
감사합니다. 구독 박고 가겠습니다!
great work!
great work!
2:10 Just do it for fun
great work!
great work!
인공지능을 잘 아시고 즐기시고 또 학생지도를 열심히 해주십니다. 교수님 학생분들 모두 훌륭하십니다. MLV Lab 화이팅!!
교수님 너무 멋지십니다!!
와! 너무 보기 좋아보여요!
와! 너무 보기 좋아보여요!
Slide is available at slideslive.com/38937234/selfsupervised-auxiliary-learning-with-metapaths-for-heterogeneous-graphs?ref=speaker-44805-latest