Skip to content

Robotics and Computer Vision Lab

AI in Sensing, AI in Perception, AI in Action

  • About
    • History
    • Photo
    • Admission
  • Members
  • Publications
    • Patents
  • X-Review
  • X-Diary
  • Peer Review

Profile

김 태주

About Posts
PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization
  • Posted on: 03/28/2021 –
  • Comments: 2 Comments
[CVPR 2021] Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
  • Posted on: 03/22/2021 –
  • Comments: No Comments
[3DV] Multi-Spectral Visual Odometry without Explicit Stereo Matching
  • Posted on: 03/08/2021 –
  • Comments: No Comments
저널 작성기 (RA-L with IROS2021)
  • Posted on: 02/28/2021 –
  • Comments: 1 Comment
[ICLR 2020]Network Deconvolution
  • Posted on: 01/18/2021 –
  • Comments: 2 Comments
[ICCV 2019] Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection
  • Posted on: 01/09/2021 –
  • Comments: 3 Comments
[ECCV2020] Improving Multispectral Pedestrian Detection
  • Posted on: 01/04/2021 –
  • Comments: No Comments
[NeurIPS 2017]”Attention is all you need” – Transformer
  • Posted on: 11/16/2020 –
  • Comments: 2 Comments
NLP- RNN, LSTM, Seq2Seq, Attention Mechanism
  • Posted on: 11/09/2020 –
  • Comments: No Comments
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
  • Posted on: 10/12/2020 –
  • Comments: 1 Comment
Newer Posts 1 2 … 11 12 13 14 15 Older Posts

Conference Deadline

NEW POST

  • [CoRL 2025(Oral)] SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition
  • [IROS 2025] Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels
  • [ArXiv 2025] VLA-0: Building State-of-the-Art VLAs with Zero Modification
  • [ICRA 2025] HeLiOS: Heterogeneous LiDAR Place Recognition via Overlap-based Learning and Local Spherical Transformer
  • [ICCV 2023] Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval

New Comment

  1. 김 태주 on [ArXiv 2025] VLA-0: Building State-of-the-Art VLAs with Zero Modification10/20/2025

    Q1. 액션을 텍스트로 반환하는 능력 자체는 논문에 있는 3가지 스킬로 어느정도 구현이 됐다고 생각하고, 이 논문의 핵심중에 하나인 것 같습니다.…

  2. 김 태주 on [ArXiv 2025] VLA-0: Building State-of-the-Art VLAs with Zero Modification10/20/2025

    Q1. 연속적인 행동 값을 정해진 정수 범위로 정규한다는 것이 궁금합니다. A1. 정확한 구현 방법에 대해서는 코드가 공개된 시점에서 밝혀질 것…

  3. 김 태주 on [ArXiv 2025] VLA-0: Building State-of-the-Art VLAs with Zero Modification10/20/2025

    Q1. 여기서 궁금한게 보통 vla 모델들의 입력으로 비디오 시퀀스가 아닌 단일 frame 이미지가 일반적으로 사용되나요? 현재 figure 예시처럼 ‘put the…

  4. 김 태주 on [CoRL 2025] Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames10/20/2025

    Q1. 2가지 타입에서 평가한다고 하셨는데, 2) Large Vision Model에 대한 정량적 혹은 정성적 결과는 따로 없는 지 궁금합니다. A1. 처음부터…

  5. 김 태주 on [arXiv 2025] OpenHelix: An Open-source Dual-System VLA Model for Robotic Manipulation10/20/2025

    Q1. 기존 dual-system VLA에서 MLLM이 시각적 정보(localization이나 dynamic한 변화)를 downstream에 잘 전달하지 못하는 것으로 이해했습니다. 관련해서 Fig. 5에 드러난 실험이…

  • Sign-in
  • RCV-Calendar
  • RCV-Github
  • Paper R/W
    • Arxiv
    • Deadline
    • Overleaf
  • Coding
    • OnlineJudge
    • Kaggle

포기하지 않는 강한 집념 만이 작은 차이를 만든다.

Design by SejongRCV