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
[arXiv 2025] OpenHelix: An Open-source Dual-System VLA Model for Robotic Manipulation
  • Posted on: 09/01/2025 –
  • Comments: 2 Comments
[arXiv 2025] DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
  • Posted on: 07/28/2025 –
  • Comments: No Comments
2025년 상반기를 마무리하며
  • Posted on: 07/21/2025 –
  • Comments: 4 Comments
[CoRL 2024] 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
  • Posted on: 07/14/2025 –
  • Comments: No Comments
[IROS 2024] ShapeGrasp: Zero-Shot Task-Oriented Grasping with Large Language Models through Geometric Decomposition
  • Posted on: 06/09/2025 –
  • Comments: 2 Comments
[arXiv 2025] Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
  • Posted on: 06/02/2025 –
  • Comments: No Comments
[arXiv 2025] Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware
  • Posted on: 05/26/2025 –
  • Comments: 2 Comments
[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
  • Posted on: 05/18/2025 –
  • Comments: 2 Comments
[arXiv 2025] π0.5: a Vision-Language-Action Model with Open-World Generalization
  • Posted on: 05/07/2025 –
  • Comments: No Comments
[arXiv 2025] FAST: Efficient Action Tokenization for Vision-Language-Action Models
  • Posted on: 04/28/2025 –
  • Comments: No Comments
1 2 … 14 15 Older Posts

Conference Deadline

NEW POST

  • [CoRL 2025] Planning from Point Clouds over Continuous Actions for Multi-object Rearrangement
  • [ACCV2024]Vision language models are blind: Failing to translate detailed visual features into words
  • Improving Language Understanding by Generative Pre-Training
  • [CoRL 2025] O3Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation
  • [CoRL 2025]One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation

New Comment

  1. 김 영규 on [CoRL 2025(Oral)] X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real09/16/2025

    안녕하세요 인하님 리뷰 읽어주셔서 감사합니다. 첫번째 질문에 대한 답으로는 해당 기법은 물체의 trajectory를 dense reward로 정의해서 강화학습을 통해서 manipulator가 trajectory를…

  2. 김 영규 on [CoRL 2025(Oral)] X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real09/16/2025

    안녕하세요 재찬님 댓글 감사합니다. reward를 다른 방식으로 변화를 주어 RL을 진행한 ablation이라는 표현이 객체 중심의 reward와 모션 중심의 reward를 말씀하시는건가요?…

  3. 허 재연 on [CVPR 2023] Feature Aggregated Queries for Transformer-based Video Object Detectors09/16/2025

    basic query는 기본적으로 random init되므로 해당 frame의 시각적 정보를 담고 있지 않습니다. 이를 함께 사용하면 학습 과정에서 도움을 줄 수는…

  4. 신 인택 on [CVPR 2024] Open-Vocabulary Calibration for Fine-tuned CLIP09/15/2025

    안녕하세요 예은님 답글 감사합니다. 1번 질문에 대해서는 올바르게 이해하셨씁니다. 파인튜닝을 진행하지 않았을때는 뭐 당연하게도 base novel 클래스에 대해 비슷한 분포를…

  5. 신 인택 on [CVPR 2024] Open-Vocabulary Calibration for Fine-tuned CLIP09/15/2025

    안녕하세요 재윤님 답글 감사합니다. temperature는 softmax 함수에서 확률값이 되기 전 로짓에 T 라는 상수를 나눠줘 너무 극단적으로 확률값이 치우쳐지지 않게…

  • 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