Yuchen Lin
@kevin_yuchenlin
CS/AI Undergrad @ PKU
🚨 The era of infinite internet data is ending, So we ask: 👉 What’s the right generative modelling objective when data—not compute—is the bottleneck? TL;DR: ▶️Compute-constrained? Train Autoregressive models ▶️Data-constrained? Train Diffusion models Get ready for 🤿 1/n
Beyond thrilled to officially roll out "Generate in Parts" on app.scenario.com - a new standard for Image-to-3D workflows! Say goodbye to monolithic Al meshes, and hello to clean, modular 3D assets you can animate, edit, or 3D print. Let's dive in with #PartCrafter👇!
🔥 π³ is here! 🔥 The new way to do 3D visual geometry. 🧠 Core Idea: A feed-forward net that doesn‘t care about input order. No more reference view! ✅ Permutation-Equivariant 🔄 ✅ Reference-Free 🆓 ✅ Highly Scalable 📈 ✅ SOTA Results 🚀
Thank @emmanuel_2m for showing us the amazing results of scaling PartCrafter up. Looking forward to the release! Original Project Page: wgsxm.github.io/projects/partc…
Say goodbye to monolithic AI meshes! 👋 We're rolling out "Generate in Parts" for 3D models on app.scenario.com, next week. Things will get modular. ⚙ Another wild update! :) 🚀
Say goodbye to monolithic AI meshes! 👋 We're rolling out "Generate in Parts" for 3D models on app.scenario.com, next week. Things will get modular. ⚙ Another wild update! :) 🚀
Finished your project homepage? 🚀 Next step: create an app for everyone to experience! With Anycoder by @_akhaliq , you can instantly generate Python Gradio apps. 💻✨ Start building now: huggingface.co/spaces/akhaliq… #Gradio #AnyCoder #vibecoding
It's awesome that we have the chance to get the homepage built on day 0, all powered by Kimi K2 and Groq! Thanks to @_akhaliq for making it available in Anycoder. try it out: huggingface.co/spaces/akhaliq… #Anycoder #kimik2 #groq
China is brutally training humanoid robots right now not just walking, they’re pushing them, knocking them down, forcing them to fight gravity this is how to make it tougher and.. scarier here are 10 wild clips you’ve never seen before: 👇
🚨 We just released 🎞️MoVieS — a feed-forward model that reconstructs 4D scenes in ⚡️1 second My favorite part: It learns dense (pixel-wise) sharp 3D world movements from novel view rendering + sparse point tracking supervision 🤯🎯 Check it out 👉 chenguolin.github.io/projects/MoVieS
Thanks @_akhaliq for twittering our work. Our CoPart (accepted at ICCV2025 @ICCVConference) proposes a part-based 3D generation framework & the first large-scale manually-annotated part-level 3D dataset named PartVerse. It contains 12k objects and 91k parts, with part priority…
From One to More Contextual Part Latents for 3D Generation
🎉 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! 🚀
PartCrafter Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
💥 We just open-sourced the inference & training code of PartCrafter 🧩 — along with pretrained checkpoints! 🚀 Check it out here 👉 wgsxm.github.io/projects/partc… ❗️❗️ #OpenSource #3D #Diffusion #AI #PartCrafter
🚨 New drop: PartCrafter 🧩 A 3D-native DiT that generates 3D objects in parts 👉 wgsxm.github.io/projects/partc… The most exciting part for me: 🌟 We realised most 3D datasets already come with part-structured meshes — but previous works just ignored that. 🤯 Simple & Effective 🚀
OmniPart Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion
Vision transformers have high-norm outliers that hurt performance and distort attention. While prior work removed them by retraining with “register” tokens, we find the mechanism behind outliers and make registers at ✨test-time✨—giving clean features and better performance! 🧵
Generating 3D models with parts is a key step toward scalable, interactive simulation environments. Check out our work — PartPacker — and the concurrent project, PartCrafter!" PartPacker: github.com/NVlabs/PartPac… PartCrafter: wgsxm.github.io/projects/partc…
Happy to share our work PartPacker: We enable one-shot image-to-3D generation with any number of parts! Project page: research.nvidia.com/labs/dir/partp… Demo: huggingface.co/spaces/nvidia/… Code: github.com/NVlabs/PartPac…
🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference…
📢📢 We’ll be presenting MeshArt tomorrow morning (Friday 13.06) in the poster session at ExHall D Poster #42 from 10:30-12:30. Come and chat about articulated 3D mesh genereation or any 3D generative stuff! Project page: daoyig.github.io/Mesh_Art/