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

정 의철

About Posts
[arXiv 2026] VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
  • Posted on: 04/12/2026 –
  • Comments: 4 Comments
[CVPR 2024] MAFA: Managing False Negatives for Vision-Language Pre-training
  • Posted on: 03/30/2026 –
  • Comments: 7 Comments
[arXiv 2026] Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
  • Posted on: 03/22/2026 –
  • Comments: 2 Comments
[arXiv 2024] Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?
  • Posted on: 03/07/2026 –
  • Comments: 3 Comments
[AAAI 2026] UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
  • Posted on: 03/03/2026 –
  • Comments: No Comments
[ICLR 2025] GENERATIVE REPRESENTATIONAL INSTRUCTION TUNING
  • Posted on: 02/22/2026 –
  • Comments: 2 Comments
[ICCV 2025] STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
  • Posted on: 02/09/2026 –
  • Comments: 6 Comments
[ICCV 2025] LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents
  • Posted on: 02/03/2026 –
  • Comments: 2 Comments
[2025 NIPS] KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
  • Posted on: 01/26/2026 –
  • Comments: No Comments
[2025 ICLR] Retrieval Head Mechanistically ExplainsLong Context Factuality
  • Posted on: 01/19/2026 –
  • Comments: 6 Comments
1 2 … 7 8 Older Posts

Conference Deadline

NEW POST

  • [AAAI 2025] Does VLM Classification Benefit from LLM Description Semantics?
  • [ICLR 2026] VisionTrim: Unified Vision Token Compression forTraining-Free MLLM Acceleration
  • [RSS 2025] DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation
  • [ICLR 2024] Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
  • [CVPR 2026] Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs

New Comment

  1. 이 재윤 on [CVPR 2026] SARMAE : Masked Autoencoder for SAR Representation Learning05/11/2026

    안녕하세요 우진님, 좋은 질문 감사합니다. 이쪽 분야를 접한 이유는 저희 팀 기업 과제가 task가 SAR object detection이고, 과제 팔로우업을 겸해서…

  2. 이 재윤 on [CVPR 2026] SARMAE : Masked Autoencoder for SAR Representation Learning05/11/2026

    안녕하세요 정우님, 좋은 질문 감사합니다. DINOv3는 frozen 상태로 optical branch에서 이미지 패치 feature를 추출하는 용도로만 사용되며, SAR branch에서는 일반적인 ViT…

  3. 이 재윤 on [CVPR 2026] SARMAE : Masked Autoencoder for SAR Representation Learning05/11/2026

    안녕하세요 인택님, 좋은 질문 감사합니다. 말씀주신 대로 SAR-1M 데이터셋은 SAR 이미지 중 매칭된 광학 이미지 쌍이 존재하는 경우도 있고, 아닌…

  4. 이 재윤 on [AAAI 2025] Does VLM Classification Benefit from LLM Description Semantics?05/11/2026

    안녕하세요 예은님, 좋은 리뷰 감사합니다. description selection 과정에서, 단순히 타겟 클래스의 이미지와 가장 유사도가 높은 텍스트를 고르는 것에 그치지 않고…

  5. 최 인하 on [RSS 2025] DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation05/11/2026

    안녕하세요 승현님 좋은 질문 감사합니다 프로젝트 페이지에 따로 fingertip nail을 사용해서 task를 수행한 정성적인 영상 결과가 있습니다. 예를 들어서 바닥에…

  • 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