📚 세현's Vault

🌍 도메인

  • 🔮3D-Vision
  • 🎨Rendering
  • 🤖Robotics
  • 🧠LLM
  • 👁️VLM
  • 🎬GenAI
  • 🥽XR
  • 🎮Simulation
  • 🛠️Dev-Tools
  • 💰Crypto
  • 📈Finance
  • 📋Productivity
  • 📦기타

📄 Papers

  • 📚전체 논문172
Home

❯

bookmarks

❯

can vlms really think in 4d 3d space time when a model cant

can-vlms-really-think-in-4d-3d-space-time-when-a-model-cant

2025년 10월 21일1 min read

  • VLM
  • spatiotemporal-reasoning
  • ICCV2025

Shijie Zhou (@ShijieZhoucla)

2025-10-21 | ❤️ 122 | 🔁 16


Can VLMs really think in 4D (3D space + time)? 🤔

When a model can’t tell “left” from “right,” something’s missing.

That’s why we built VLM4D — a benchmark for spatiotemporal reasoning, debuting at ICCV2025

📅 Oct 21 | 🕒 3–5 PM | 📍Exhibit Hall I #798 https://vlm4d.github.io/ https://x.com/ShijieZhoucla/status/1980691677728895464/video/1


🔗 Related

Auto-generated bookmark

Tags

AI-ML VLM


그래프 뷰

  • Shijie Zhou (@ShijieZhoucla)
  • 🔗 Related
  • Tags

백링크

  • domain-VLM
  • enriched-codex

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Sehyeon Park