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

이 상인

About Posts
[ICCV 2023] Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation
  • Posted on: 07/30/2025 –
  • Comments: 2 Comments
2025년 상반기 회고
  • Posted on: 07/21/2025 –
  • Comments: 5 Comments
[arXiv 2025] [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster
  • Posted on: 06/30/2025 –
  • Comments: 6 Comments
[COLING 2025] Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
  • Posted on: 06/09/2025 –
  • Comments: 6 Comments
ICRA 2025 참관 후기
  • Posted on: 05/28/2025 –
  • Comments: No Comments
[arXiv 2025.02] Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
  • Posted on: 05/05/2025 –
  • Comments: 6 Comments
LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Model
  • Posted on: 04/28/2025 –
  • Comments: 4 Comments
[COLING 2025] Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
  • Posted on: 04/14/2025 –
  • Comments: No Comments
[arXiv 2024] LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
  • Posted on: 04/06/2025 –
  • Comments: No Comments
[ACL 2023] PuMer: Pruning and Merging Tokens for Efficient Vision Language Models
  • Posted on: 03/17/2025 –
  • Comments: 6 Comments
1 2 … 6 7 Older Posts

Conference Deadline

NEW POST

  • [arXiv 2025] VideoRAG: Retrieval-Augmented Generation over Video Corpus
  • [WACV 2026] UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning
  • DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning
  • [NeurIPS 2020]Object-Centric Learning with Slot Attention
  • [ICRA 2024]NoMaD : Goal Masked Diffusion Policies for Navigation and Exploration

New Comment

  1. 김 영규 on [NeurIPS 2025] PhysX-3D: Physical-Grounded 3D Asset Generation11/26/2025

    안녕하세요 정민님 댓글 감사합니다. 정리를 하자면 Absolute Scale의 경우는 사람이 직접 기입합니다. Kinematics에 관련된 부분도 수학적인 기하 알고리즘을 통해 접촉면…

  2. 김 영규 on [NeurIPS 2025] PhysX-3D: Physical-Grounded 3D Asset Generation11/26/2025

    안녕하세요 우현님, 다른 리뷰에 대한 댓글인것 같긴 한데, 일단 답변 드리겠습니다 우선 Robo-SAM 자체가 segment 해야하는게 쉽게 로봇, task 관련…

  3. 김 영규 on [IROS 2025] RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation11/26/2025

    안녕하세요 정우님 댓글 감사합니다. 답변이 늦어 죄송합니다 음.. 일단 최근 Imitation Learning 모델들은 rollout 단위로 학습하지 않고 video 기준으로 특정…

  4. 김 영규 on [IROS 2025] RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation11/26/2025

    안녕하세요 정민님 댓글 감사합니다. 답변이 늦은점 죄송합니다,, A 1,2 (제가 설명을 깔끔하게 못 한것 같습니다,,) Robo-SAM이 저자들이 제안한 3800장의 데이터셋으로…

  5. 신 인택 on [NeurIPS 2020]Object-Centric Learning with Slot Attention11/25/2025

    안녕하세요 재연님 답글 감사합니다. 각 질문에 대해서 답글을 달아드리자면 1. 논문에서 learnable slot 에 대해서 언급하지는 않았으나 random sampled slot이…

  • 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