Favikon Index
it
← Top 100 IA
SDSander Dieleman, Research scientist, Google DeepMind

Top 100 IA · Paesi Bassi

Sander Dieleman

Google DeepMind Paesi Bassi

Punteggio
73330 oggi
Posizione
70/198 ↓6
in 90 giorni
+309+4,1%

Sander Dieleman è un Ricercatore Scientifico presso Google DeepMind, specializzato in deep learning, modelli generativi e reti neurali. Condivide approfondimenti tecnici, risultati di ricerca e sviluppi nel campo del machine learning, spesso facendo riferimento ai suoi lavori su WaveNet, Imagen e Veo. I suoi contenuti includono analisi di modelli di diffusione, autoencoder e altre tecniche avanzate di ML, insieme a occasionali riferimenti alla music information retrieval e ai sistemi di raccomandazione.

CondividiXWhatsAppLinkedInFacebook

Dati al 25 ott 2026.

I numeri grezzi · ultimi 90 giorni

Visualizzazioni mediane
45,2K
per post
Interazioni mediane
568
per post
Post
31
in 90 giorni
Follower
78,6K
tutti i social nel punteggio

Cosa determina il punteggio

Percentili 0 – 100 rispetto a tutti i creator monitorati.

  • Portata · 30%86

    Visualizzazioni medie per post su 90 giorni

  • Engagement · 30%74

    Reazioni medie per post

  • Audience · 30%66

    Follower totali, rapportati alla popolazione

  • Costanza · 10%100

    Ritmo di pubblicazione (25 post / 90 g = 100)

Social

78,6K follower in totale

SocialFollowerPunteggio
X@sedielem72K7821t2
LinkedIn@sanderdieleman6,5K7512t2

Ultimi 30 giorni

I migliori post di Dieleman

  1. This is a beautiful analysis of the order in which diffusion models resolve uncertainty about information at different abstraction levels in different representation spaces, with significant implications for latent di…
    X · 14 gg fa#1
    SDSander Dieleman, Research scientist, Google DeepMindSander Dieleman

    This is a beautiful analysis of the order in which diffusion models resolve uncertainty about information at different abstraction levels in different representation spaces, with significant implications for latent di…

    25,2K visualizzazioni553 interazioni

  2. X · 14 gg fa#2
    Turns out you can use distribution matching distillation (DMD) to turn diffusion/flow models into looped models that iteratively refine samples directly in data space🤯 Nice bit of out-of-the-box thinking here! Strong…
    SDSander Dieleman, Research scientist, Google DeepMindSander Dieleman

    19,9K visualizzazioni367 interazioni

  3. X · 8 gg fa#3
    More diffusion with nested looping! Looping at a given noise level fixes errors which would otherwise accumulate. Also reduces reliance on CFG. Related in spirit to data-space iteration (https://t.co/zhZPyHj87K) and s…
    SDSander Dieleman, Research scientist, Google DeepMindSander Dieleman

    15,5K visualizzazioni273 interazioni

  4. X · 21 gg fa#4
    As if we needed any more evidence that 2026 is the year of continuous diffusion for language🤭 (I recently wrote a blog post about my thoughts on this topic, in case you missed it: https://t.co/IxtdWvfa6B)
    SDSander Dieleman, Research scientist, Google DeepMindSander Dieleman

    15,4K visualizzazioni239 interazioni

  5. X · 17 gg fa#5
    I've been doing some thinking about multimodality lately, specifically the semantic gap between common representations of language and perceptual signals. In that context, this is an exciting result! (These thoughts a…
    SDSander Dieleman, Research scientist, Google DeepMindSander Dieleman

    12,9K visualizzazioni223 interazioni

  6. X · l’altro ieri#6
    The magic of flow map language models is that they capture dependencies between tokens in just 1-2 model passes. Using this as a drafter for speculative decoding makes a ton of sense, and it's exciting to see this wor…
    SDSander Dieleman, Research scientist, Google DeepMindSander Dieleman

    10,2K visualizzazioni215 interazioni

Faccia a faccia

Confronta Dieleman con…