Mark Boss

301 posts

Mark Boss

Mark Boss

@markb_boss

I’m the Co-Head of 3D & Image at Stability AI with research interests in the intersection of machine learning and computer graphics

Germany Katılım Temmuz 2009
238 Takip Edilen1.3K Takipçiler
Mark Boss
Mark Boss@markb_boss·
@ethanjohnweber Yes, I wanted to add markdown specifically for that - go 80-90% with automated AI, do the rest in a friendly format including your amazing drag and drop, scaling and resizing. Super neat.
English
0
0
1
12
Ethan Weber
Ethan Weber@ethanjohnweber·
@markb_boss Very cool! I love how we can mold content into different formats for better consumption. 🙂
English
1
0
0
15
Mark Boss
Mark Boss@markb_boss·
Current hobby: vibecoding tiny tools that eliminate annoying tasks. I open-sourced them in case they’re useful to others.
English
1
1
10
560
Mark Boss
Mark Boss@markb_boss·
@ethanjohnweber This is what I did before - but doing that constantly annoyed me (especially processing folders, running compression, cropping, trimming). It's just amazing that you can do an application like that while drinking a coffee in the morning 😅
English
1
0
1
16
Ethan Weber
Ethan Weber@ethanjohnweber·
@markb_boss Oh nice, I could have used this earlier in the week when I had to use slides at work for a shared presentation. 🙏 I was dropping videos into my Cursor editor and asking the agent to convert everything to gifs, but I like the UI you have.
English
1
0
0
35
Mark Boss
Mark Boss@markb_boss·
@ethanjohnweber 5) Obsidian Paper Summary (Claude Skill) A template for @obsdmd that auto-summarizes papers and extracts the key overview figure (similar to the poster workflow above). Includes: - backlinks - tags - structured notes Just call via /paper URL github.com/vork/ObsidianT…
Mark Boss tweet media
English
0
0
1
98
Mark Boss
Mark Boss@markb_boss·
4) Postergeist (pun again) Highly inspired by @ethanjohnweber and his poster skill x.com/ethanjohnweber… I built a similar Claude skill, but focused on turning PDFs into a markdown poster definition and the interpreter (including themes) github.com/vork/Postergei…
Ethan Weber@ethanjohnweber

I made a Claude Code skill that generates conference posters 🛠️ Instead of a static PDF, it outputs a single HTML file — drag to resize columns, swap sections, adjust fonts, then give your layout back to Claude. 🔁 🔗 Skill 👉 github.com/ethanweber/pos…

English
2
0
1
180
Mark Boss retweetledi
Tenobrus
Tenobrus@tenobrus·
Donald Knuth is vibemathing now. real tough day for the stochastic-parrot crew.
Tenobrus tweet media
English
78
436
3.4K
516.6K
Mark Boss
Mark Boss@markb_boss·
@Mishok2000 Yes it's rare that a paper perfectly nails my graphics and diffusion interests :D
English
1
0
9
379
Mark Boss retweetledi
Sander Dieleman
Sander Dieleman@sedielem·
Two recent papers (arxiv.org/abs/2510.11690, arxiv.org/abs/2511.13720) suggest that predicting x (clean) works much better than predicting eps or v (noisy) in high dimensions. Natural signals like images live on a low-dimensional manifold. Noise takes you off the manifold! (1/3)
English
18
78
578
50.5K
Mark Boss retweetledi
Gautam Kamath
Gautam Kamath@thegautamkamath·
The pressure to write "mathy" papers (whether or not the math is justified, interesting, or even correct) has reached a natural conclusion: if the reviewers can't understand the math, they're impressed and say accept Only one reviewer is willing to say the emperor has no clothes
Micah Goldblum@micahgoldblum

An LLM-generated paper is in the top 17% of ICLR submissions in terms of average reviewer score, having received two 8's. The paper has tons of BS jargon and hallucinated references. Fortunately, one reviewer actually looked at the paper and gave it a zero. 1/3

English
15
37
695
86K
Mark Boss
Mark Boss@markb_boss·
If you have questions or want to chat about the roles, feel free to DM me.
English
0
0
3
154
Mark Boss
Mark Boss@markb_boss·
3️⃣ VLM Generalist VLMs are powerful building blocks for wide variety of components in several applications across all modalities. Help us to unlock them for several workflows: stability.ai/careers?gh_jid…
English
1
0
3
190
Mark Boss
Mark Boss@markb_boss·
We’re hiring 3 researchers for the Stability AI 3D team — and with our new EA partnership, this is an absolutely massive opportunity. If you’re passionate about 3D, graphics, AI models, or VLMs consider applying below:
English
1
4
7
1.3K
Mark Boss
Mark Boss@markb_boss·
If you’ve been affected by the recent Meta layoffs and your work touches 3D, video, or image generation - please feel free to DM me. We’re hiring at @StabilityAI.
English
0
0
6
1.3K

Keşfet

@CG_Tuebingen @AjlEngelhardt @jampani_varun @ethanjohnweber @obsdmd @Mishok2000 @StabilityAI @elonmusk