Michael Black ✓

@Michael_J_Black

VP Digital Human Research, Epic Games. Emeritus Director, Max Planck Institute for Intelligent Systems (@MPI_IS). Opinions are my own.

104 024Followers

739Following

3 741Posts total

595.9KViews on collected posts

Latest posts

Michael Black ✓@Michael_J_Black10 Sep

There are multiple things going on here that I didn't fully separate and that the comments bring out. * Academia does not have the resources to even evaluate top models as I suggest. This is a critical problem that should be addressed by a coordinated effort between the 4.6K views · 17 likes · 1 reposts · 1 replies Open on X →

Michael Black ✓@Michael_J_Black9 Sep

@Michael_J_Black This resonates with me. One option is to work less on solving tasks and more on understanding the solutions. A paper that analyzes Astra + open models might have more lasting impact than one that tries to solve a new task that Astra+ will inevitably solve. 5.5K views · 146 likes · 8 reposts · 6 replies Open on X →

Michael Black ✓@Michael_J_Black9 Sep

To be clear - I'm not knocking VIGA. I think VIGA is a great paper, which changed my thinking entirely. And it clearly changed the thinking of others. But all of this happened by putting it on arXiv and social media. The follow-on work on inverse graphics has happened outside of 9.9K views · 41 likes · 0 reposts · 1 replies Open on X →

Michael Black ✓@Michael_J_Black9 Sep

What is the role of academic computer vision research in the age of increasingly powerful large models? Is GPT-6 Astra a step change? How can a researcher have an impact today in academia? These are the questions I ask myself as I head off to ECCV 2026, a conference I’ve 576K views · 2.1K likes · 340 reposts · 85 replies Open on X →

Against accounts of the same size

4 posts from the last 90 days, next to the 100K–1M follower range. shown widely, but few of those viewers react.

Median views7 666this account5 774median for 100K–1M

Reach, %7.37%this account1.55%median for 100K–1M

Engagement, %0.44%this account0.98%median for 100K–1M

Metric	This account	Median for 100K–1M	Ratio
Median views per post	7 666	5 774	1.33×
Reach (views ÷ followers)	7.37%	1.55%	4.75×
Engagement rate	0.44%	0.98%	0.45×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

576K9 Sep

9.9K

5.5K

4.6K10 Sep

Last 4 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.45%9 Sep

0.43%

2.96%

0.44%10 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 0.98%.

What the audience does

Likes60.3%2 288 in total

Reposts9.2%349 in total

Replies2.4%93 in total

Quotes1.6%62 in total

Bookmarks26.4%1 004 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

Against accounts of the same size

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Similar accounts