Jisoo Kim

PhD Student in Visual Computing Lab in Seoul National University | 3D Computer Vision, Human-Object Interaction

[Jisoo Kim @jisooslog]

Introducing ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning

VLMs know what to do. ZeroDex grounds that reasoning in multi-view 3D, enabling robots to perform dexterous actions.

No task-specific demos. No policy fine-tuning.

[Jisoo Kim @jisooslog]

#robotics #DexterousManipulation #VLM #3DGrounding #ZeroshotManipulation

[Jisoo Kim @jisooslog]

Introducing ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning

VLMs know what to do. ZeroDex grounds that reasoning in multi-view 3D, enabling robots to perform dexterous actions.

No task-specific demos. No policy fine-tuning.

[Jisoo Kim @jisooslog]

For long-horizon tasks, ZeroDex closes the loop with task verification and retry.

We demonstrate zero-shot dexterous manipulation across unseen objects, tool-use tasks, and long-horizon real-robot scenarios.

🌐 Project: https://t.co/UXIkp5QHuA
📄 Paper: https://t.co/C36rTEcAxf

[Byungjun Kim @byungjun__kim]

We introduce 🖐️🌏 𝐃𝐞𝐱𝐭𝐞𝐫𝐨𝐮𝐬 𝐖𝐨𝐫𝐥𝐝 𝐌𝐨𝐝𝐞𝐥𝐬 (𝐃𝐖𝐌) — a scene-action-conditioned video diffusion model that simulates human manipulation in static 3D scenes from egocentric hand motions.

📄 Paper: https://t.co/u2IldpfYTD
🌐 Project Page: https://t.co/YSE3rOmV1s

[Jisoo Kim @jisooslog]

The full version of the ParaHome dataset is now available! 🎉
Check out our webpage: https://t.co/qI2HWGQd2q

- 486 min, 207 sequences, 38 subjects
- 3D parameterized 22 objects
- Text annot. for every action
- Full 3D mocap for body and hand movements
- Sequential HOI scenarios