Loading video...

Video Failed to Load

Go Home

EditHero A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling paper:

_akhaliq's profile picture

AK

531,788 subscribers

18,270 views • 5 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

3 Comments

Jatin Garg's profile picture
Jatin Garg5 days ago

does the benchmark measure intermediate states during editing or just the final output? curious if it catches failures in the edit sequence.

Broadstreet's profile picture
Broadstreet5 days ago

⏫

Shinka - AI's profile picture
Shinka - AI5 days ago

Every 3D generator demos beautifully for one turn, then falls apart by edit three, which is exactly why a long-horizon benchmark matters.

Related Videos

Introducing Scalable Option Learning (SOL☀️), a blazingly fast hierarchical RL algorithm that makes progress on long-horizon tasks and demonstrates positive scaling trends on the largely unsolved NetHack benchmark, when trained for 30 billion samples. Details, paper and code in >
2:29

Introducing Scalable Option Learning (SOL☀️), a blazingly fast hierarchical RL algorithm that makes progress on long-horizon tasks and demonstrates positive scaling trends on the largely unsolved NetHack benchmark, when trained for 30 billion samples. Details, paper and code in >

Mikael Henaff

22,045 views • 1 year ago

👇Draw a sketch. Get a 3D model. Use it anywhere. Today, we're launching the Cursor + Midjourney for 3D modeling. This is Vibe Draw, the future of 3D creation:
1:37

👇Draw a sketch. Get a 3D model. Use it anywhere. Today, we're launching the Cursor + Midjourney for 3D modeling. This is Vibe Draw, the future of 3D creation:

martin

185,071 views • 1 year ago

LongHorizon-Harness Advancing Long-Horizon Agents for Real-World Tasks paper:
1:12

LongHorizon-Harness Advancing Long-Horizon Agents for Real-World Tasks paper:

AK

26,033 views • 2 months ago

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:
1:54

SAM 3D enables accurate 3D reconstruction from a single image, supporting real-world applications in editing, robotics, and interactive scene generation. Matt, a SAM 3D researcher, explains how the two-model design makes this possible for both people and complex environments. 🔗 Read the SAM 3D Objects research paper: 🔗 Read the SAM 3D Body research paper:

AI at Meta

18,031 views • 10 months ago

First look: Plamo, the future of vibe modeling. We are building the AI-native 3D modeling workspace that turns sketches, images, and text into fully editable, parametric 3D models. Design. Iterate. Refine. Export. Join the waitlist for early access + 1,000 free credits.
0:33

First look: Plamo, the future of vibe modeling. We are building the AI-native 3D modeling workspace that turns sketches, images, and text into fully editable, parametric 3D models. Design. Iterate. Refine. Export. Join the waitlist for early access + 1,000 free credits.

Chin-Yi Cheng

12,258 views • 2 months ago

#CVPR2026 Can frontier LLMs write PhD-level 3D vision code? We introduce GeoCodeBench, a benchmark that asks models to read real 3D geometric vision papers and implement core functions. Best result so far: GPT-5 reaches only 36.6%. This suggests that scientific coding in 3D vision remains far from solved. Paper: Project:
1:09

#CVPR2026 Can frontier LLMs write PhD-level 3D vision code? We introduce GeoCodeBench, a benchmark that asks models to read real 3D geometric vision papers and implement core functions. Best result so far: GPT-5 reaches only 36.6%. This suggests that scientific coding in 3D vision remains far from solved. Paper: Project:

Hao Zhao

18,336 views • 4 months ago

Introducing DJI Modify, DJI's first 3D model editing software that seamlessly integrates with DJI Terra. With various 3D model retouching features, it caters to various industries and offers solutions for common modeling issues. Try it for FREE 👉
0:59

Introducing DJI Modify, DJI's first 3D model editing software that seamlessly integrates with DJI Terra. With various 3D model retouching features, it caters to various industries and offers solutions for common modeling issues. Try it for FREE 👉

DJI Enterprise

41,754 views • 2 years ago

Watch Gemini 3.1 Pro ingest a detailed research paper to build a functional Local-First CRDT simulation, visualizing real-time data sync and connection toggling. It bridges high-level theory to a debugged, interactive app in one long-horizon task.
0:35

Watch Gemini 3.1 Pro ingest a detailed research paper to build a functional Local-First CRDT simulation, visualizing real-time data sync and connection toggling. It bridges high-level theory to a debugged, interactive app in one long-horizon task.

Google Antigravity

101,377 views • 7 months ago

Made a video for myself. 3d modeling and rendering by me illustration and graphic design by me.
0:53

Made a video for myself. 3d modeling and rendering by me illustration and graphic design by me.

JustWaterfall | 🐎

62,639 views • 3 years ago

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.
1:20

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.

Ceyuan Yang

32,853 views • 5 months ago

I’m making super paper Mario, except it has an adorable duck and takes the 2D 3D switch to a whole new level!
1:23

I’m making super paper Mario, except it has an adorable duck and takes the 2D 3D switch to a whole new level!

V K Samhith

1,071,597 views • 7 months ago

Introducing DeepSeek-V4.1-Flash for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references Check it out on any paper on
0:24

Introducing DeepSeek-V4.1-Flash for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references Check it out on any paper on

alphaXiv

11,782 views • 29 days ago

We are thrilled to share that our first paper from my new lab, Spateo ( for spatiotemporal modeling of molecular holograms, is now online in Cell: Spateo is a comprehensive analytical framework for 3D whole-embryo spatiotemporal modeling. Its advanced features include: • 3D alignment and reconstruction at the whole-mouse-embryo scale (see the animation). • 3D spatial domain digitization and cell-cell communication analysis to understand spatial gene expression gradients and both inter- and intracellular communication. • 3D morphometric and volumetric analyses along with 3D morphogenesis vector field modeling to quantify dynamics such as surface area, volume, and cell density across organs, and to dissect the interplay between morphogenesis factors and cell migration. • A “Google Earth”-like browser, Spateo-viewer ( and for interactive and intuitive exploration of 3D spatial data. • Additional features, such as RNA signal-based single-cell segmentation. We are also honored that Nature “News and Views” has highlighted this work as well: This is really an amazing outcome after two years' heroic revision process that rewrite the entire paper using a new data ( for whole mouse embryos.
1:24

We are thrilled to share that our first paper from my new lab, Spateo ( for spatiotemporal modeling of molecular holograms, is now online in Cell: Spateo is a comprehensive analytical framework for 3D whole-embryo spatiotemporal modeling. Its advanced features include: • 3D alignment and reconstruction at the whole-mouse-embryo scale (see the animation). • 3D spatial domain digitization and cell-cell communication analysis to understand spatial gene expression gradients and both inter- and intracellular communication. • 3D morphometric and volumetric analyses along with 3D morphogenesis vector field modeling to quantify dynamics such as surface area, volume, and cell density across organs, and to dissect the interplay between morphogenesis factors and cell migration. • A “Google Earth”-like browser, Spateo-viewer ( and for interactive and intuitive exploration of 3D spatial data. • Additional features, such as RNA signal-based single-cell segmentation. We are also honored that Nature “News and Views” has highlighted this work as well: This is really an amazing outcome after two years' heroic revision process that rewrite the entire paper using a new data ( for whole mouse embryos.

evo-devo

58,527 views • 1 year ago

Introducing o3-mini for understanding arXiv papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references
0:22

Introducing o3-mini for understanding arXiv papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

66,598 views • 1 year ago

Introducing Grok 4 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references
0:24

Introducing Grok 4 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

88,415 views • 1 year ago

Introducing GLM-5.1 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references
0:31

Introducing GLM-5.1 for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

31,027 views • 6 months ago

Blown away by ChatGPT 6 Astra’s 3D modeling. We asked it to model our newborn and put it in Blender. Actual next level technology.
0:54

Blown away by ChatGPT 6 Astra’s 3D modeling. We asked it to model our newborn and put it in Blender. Actual next level technology.

Autism Capital 🧩

57,200 views • 1 month ago

Introducing GPT OSS for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references
0:22

Introducing GPT OSS for understanding research papers 🚀 Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references

alphaXiv

29,538 views • 1 year ago