Panwang Pan (@paulpanwang) / X

Panwang Pan

102 posts

Panwang Pan

@paulpanwang

Generative Models

paulpanwang.github.io

Joined May 2023

Panwang Pan
@paulpanwang
May 5
Appreciate the mention! It’s exciting to see PartCrafter being explored as a world model. 💻 Check out the repo: github.com/wgsxm/PartCraf…
Jitendra MALIK
@JitendraMalikCV
Apr 28
Replying to @jon_barron
"World models" has a technical meaning - the transition model/dynamics model from Bellman/Kalman in the context of MDPs/ state space approach to control theory ~ 1960. I gave a talk on this history youtube.com/watch?v=9B4kka…
Panwang Pan
@paulpanwang
Dec 13, 2025
Awesome work ！
Hanwen Jiang
@hanwenjiang1
Dec 12, 2025
(1/N) Will this be the BERT/GPT moment for 3D vision？ Finally, unsupervised pre-training for 3D works. Led by @qitao_zhao , we present E-RayZer — a fully self-supervised 3D reconstruction model that: 🔥Matches or surpasses supervised methods like VGGT 👀Learns transferable 3D
00:00
Panwang Pan
@paulpanwang
Dec 4, 2025
🚀 Excited to be attending #NeurIPS2025 in SD! We'll be presenting our work, PartCrafter 🌐, 🗓️ Today from 11:00 AM – 2:00 PM at Poster #4511. Let’s connect and chat about 3D AIGC. See you there! 👋📷✨
Panwang Pan
@paulpanwang
Jul 13, 2025
🎉 Big thanks to @_akhaliq for featuring our work! We’re excited to release the 💻 code & 🤗 Hugging Face checkpoints for PartCrafter: 👉 github.com/wgsxm/PartCraf… --- ⭐️ PartCrafter generates multiple parts from a single RGB image in one unified pass. Stay tuned for updates! 🚀
Panwang Pan
@paulpanwang
Dec 4, 2025
Heading to NeurIPS? 🚀 We released DynamicVerse! 🔗 Project: dynamic-verse.github.io 🤗 Data: huggingface.co/datasets/kairu… If you're passionate about World Models, VLMs, or Generative models, let's connect and chat! #NeurIPS2025 #WorldModels #3DAIGC
00:00
Panwang Pan
@paulpanwang
Oct 28, 2025
Huge congrats to @jianfengzhang95 on their significant contributions to 3D Generation Models.
Jianfeng Zhang
@jianfengzhang95
Oct 25, 2025
🚀 Thrilled to introduce Seed3D 1.0, a foundation model that generates High-Fidelity, Simulation-Ready 3D Assets directly from a Single Image! ✨ Key Capabilities: 1️⃣ High-fidelity Assets: Generates assets with accurate geometry, well-aligned textures, and physically-based
00:00