Philippe Hansen-Estruch

Third-year PhD student at UT Austin. Working on generative modeling, visual understanding, and visual compression.

[Philippe Hansen-Estruch @tokenpilled65B]

Releasing ViTok-v2: open-source ViT auto-encoder codebase + pretrained weights

Train your own ViT auto-encoder on any streamed (hf://) or local webdataset. NaFlex pipeline handles any resolution and aspect ratio

Includes reproduced 350M and 4.5B models weights competitive at 256p, SOTA at high-res (512p+)

[Philippe Hansen-Estruch @tokenpilled65B]

@volisdead full tits semis?

[Philippe Hansen-Estruch @tokenpilled65B]

@TexasOncologist @Dcpcooks everyone in this country will be posting pronouns if that day happens

[Philippe Hansen-Estruch @tokenpilled65B]

@Larryjamieson_ do you?

[Iain Dunning @iaindunning]

@fl0ct0 Honestly if you can autoresearch well then that's a win for everyone. Only a problem when people think autoresearch is sufficient, or it gives them illusion of productivity because they're using a lot tokens but not achieving much

[difficultyang @difficultyang]

It's also a miss to describe Agent-1 as a uniform 50% research multiplier? It really speeds you up a lot on the sort of side tasks but the hard core loop really hasn't sped up that much. ChatGPT 5.5 is nice but ... not 50% probably?

[Philippe Hansen-Estruch @tokenpilled65B]

@TexasOncologist @BlacklionCTA we gonna send them pallets of our new 250 dollar bill

[Irrational Analysis @insane_analyst]

Very depressed today because of other reasons.

Money does not buy happiness. I assure you it does not.

Every year I have vacation with old college friends. Always richest. Always most unhappy.

Amusingly this year my wealth > all them combined.

Its just money. It's made up.

[Philippe Hansen-Estruch @tokenpilled65B]

@TexasOncologist @CamaradeRea @Rebecca98869736 imo avgo just showed the move in semis was too fast. Def more buyable and im plenty bullish, but Jesus the movement was crazy from March 30th

[Philippe Hansen-Estruch @tokenpilled65B]

@boymanrobshit I bought up a bunch

[Michael Tschannen @mtschannen]

For the past years my research focus was on unifying models and training paradigms across modalities. Today I'm excited that we're releasing our latest model aligned with this theme:

Gemma 4 12B, a dense encoder-free model which processes raw text, image, and audio inputs!

1/

[Philippe Hansen-Estruch @tokenpilled65B]

@jnconkle @valuedrift what if you just buy them all close your app and sleep

[Zihan "Zenus" Wang @wzenus]

Time for this meme again :)

[vik @vikhyatk]

Wrote a post about how Photon (Moondream's inference engine) hides GPU bubbles using pipelined decoding. Speeding up inference by up to 35%.

[Philippe Hansen-Estruch @tokenpilled65B]

@jennajrussell @jon_barron +++ dont ever waste your time with latex again

[Philippe Hansen-Estruch @tokenpilled65B]

@jnconkle @calvinfroedge @insane_analyst ur making me enable Taiwan but im allergic to not crossing a fat spread to
buy derivatives

[Philippe Hansen-Estruch @tokenpilled65B]

@jnconkle @calvinfroedge I’m buying SMTC @insane_analyst

[Yash Bhalgat @ysbhalgat]

Most (or some?) senior advisors haven't written code in their last 5-10 years. Their only experience with agents is prompting their PhD students 😂

[Philippe Hansen-Estruch @tokenpilled65B]

@jon_barron idk what advisors you have worked with but good luck getting any major ones to even touch your code let alone paper

[Philippe Hansen-Estruch @tokenpilled65B]

@FangYi11101 @taobanker the meta ai exploits are new maus, seems like it’s getting return already

[Philippe Hansen-Estruch @tokenpilled65B]

@steve2bacon what was the big killer lol