Yann LeCun

Founder/Chair, AMI Labs; Professor, NYU; Partner, 224 Ventures; Ex-Chief AI Scientist, Meta.
Researcher in AI, ML, Robotics, etc.
ACM Turing Award Laureate.

[Yann LeCun @ylecun]

I do not write posts on X.
I tweet links to posts on other platforms.
I like and retweet (occasionally)
I comment on friends' tweets (rarely)
Follow me on...⬇️⬇️⬇️

[Yann LeCun @ylecun]

@Neupositivist @pmddomingos So, DSA members are jihadists now?

[Yann LeCun @ylecun]

@SokobanHero @pmddomingos Only among people whose disapproval I welcome.

[Yann LeCun @ylecun]

@PetraStPete @pmddomingos I've been in the US for 38 years.
But thanks for the stereotyping.

[Yann LeCun @ylecun]

@EssentialPOV @pmddomingos Whereas you never went to college, think the earth is 5000 years old, and have no idea what communist means.
You never outgrew humanity's superstitious bronze age sheep herder phase.

[Yann LeCun @ylecun]

@trularkinmagnus @pmddomingos Right-wing media divisive propaganda and mainstream media complacent both-side-ism are directly responsible for Donald Trump.

[Yann LeCun @ylecun]

@GPA2NOMSTRFLH @pmddomingos Obama neo-conservateur?
Première nouvelle 😂

[Yann LeCun @ylecun]

@MrPewpy @pmddomingos Yet you followed me until I blocked you just now.

[Yann LeCun @ylecun]

@xavierlois @pmddomingos Reviving the economy after GW Bush disastrous financial meltdown, passing the Affordable Care Act (AKA Obamacare), getting out of Iraq, getting rid of Bin Laden, and stopping Iran's nuclear program were pretty good achievements.

[Yann LeCun @ylecun]

@Bridgetdonegal1 @pmddomingos Your bias is showing.

[Yann LeCun @ylecun]

@remanuelcron @pmddomingos Grokon.

[Yann LeCun @ylecun]

@AgnesK31 @pmddomingos C'est pour mieux te bloquer mon enfant 🐺

[Yann LeCun @ylecun]

@SabbanRobi39611 @pmddomingos Blocked. Grokon.

[Simplifying AI @simplifyinAI]

Yann LeCun has changed the game for robotics.

Research he co-authored tackles a problem inside AI world models: their internal representations can make planning harder than it needs to be.

A world model predicts what happens after an action. But even useful visual features can form curved paths in its internal “map,” making distance to a goal misleading.

The researchers introduced Temporal Straightening.

During training, it encourages those internal paths to become straighter, so the planner gets a more useful measure of progress.

The results:

More stable gradient-based planning
Higher success rates across tested goal-reaching tasks
Code available for others to explore

The approach changes how the model represents movement, rather than rewriting every RL algorithm to work in curved space.

For robotics, that’s a useful direction: build world models whose internal maps help an agent choose its next move.

[Yann LeCun @ylecun]

@jamesingram9999 @pmddomingos You can thank Trump for that.

[Yann LeCun @ylecun]

@George_0s @pmddomingos One more follower blocked.

[Thomas Weber @Thomas__Weber]

Hello @elonmusk, Hitler historian here, having researched & written about Hitler for 22 yrs & being a fellow of the Hoover Institution - not exactly a hotbed of far left ideas. This doesn’t add up. It is predicated on the false assumption that collectivism only exists on the Left

[Kenneth Roth @KenRoth]

While Trump cut taxes for the rich, he tightened access to food stamps—with more than 5 million Americans losing benefits so far—and to Medicaid, the health-care program for the poor. https://t.co/ezJ4MDtbSA

[Yann LeCun @ylecun]

@fractal_friend @pmddomingos Sure dude, just ask the millions of Americans who gains access to health insurance thanks to Obamacare.

[Yann LeCun @ylecun]

@jamesingram9999 @pmddomingos Obamacare gave access to health insurance to millions of Americans.
Ask them if it was a disaster.

[Yann LeCun @ylecun]

@knnebunk @pmddomingos The ACA was not an empty promise.