Small plug, not really advertised but we similarly showed how to perform temperature based control and composition of separately trained diffusion models via SMC and the Feynman Kac model formalism, with score distillation of the energy at AISTATS last year - Diversity control

I am very happy to share Orbformer, a foundation model for wavefunctions using deep QMC that offers a route to tackle strongly correlated quantum states! arxiv.org/abs/2506.19960

It’s not that people think calculus or math is useless in AI. They’re just tired of theory folks who never touch code, never scale a model, and still argue they’re solving problems in AI:) If theory becomes detached from practice, the world will treat it like noise and that’s on

a stark demonstration that a Caltech PhD and partnership at a top-tier venture capital firm are no remedy for profound ignorance

Attending ICML ✈️Tues-Fri to present "The Diffusion Duality" 🗓️Wed, July 16 @ 4:30pm 📍East Exhibition Hall A-B (E-3003) DM if you want to chat about diffusion LMs, or my current work on Duality or Esoteric LMs! x.com/ssahoo_/status…

Accelerated Diffusion Models via Speculative Sampling, at #icml25 ! at 16:30 Tuesday July 15 poster E-3012 arxiv.org/abs/2501.05370 Valentin De Bortoli Alexandre Galashov Arnaud Doucet

There are many great researchers out there. But the ones that really stand out to me are the ones who are also kind, even when they don't need to be.

I won’t be at ICML but check out accepted papers with folks from my former team at MLR - Projective Composition of Diffusion Models led by Arwen Bradley and Preetum Nakkiran icml.cc/virtual/2025/p…

If still around #ICML2025, plz consider checking out my collaborator Qing Qu 's Oral in the MemFM Workshop, 11am Sat West Meeting Room 223-224, on A Closer Look at Model Collapse (in diffusion model): From a Generalization-to-Memorization Perspective

Terence Tao on the supposed Gold from OpenAI at IMO

Thrilled to finally release this study! 🚀 We view (discrete) diffusion models as implicitly doing data augmentation over autoregressive. Through this lens, we find that diffusion outperforms AR in data-constrained settings, but it requires larger models and way more epochs to

Interested in some foundation aspects? Waiting or unhappy about NeurIPS reviews? Plz consider NeurIPS workshop DynaFront: Dynamics at the Frontiers of Optimization, Sampling, and Games sites.google.com/view/dynafront… Yuejie Chi Andrea Montanari Taiji Suzuki Tatjana Chavdarova ++ Sponsor appreciated!

ReLU MLP with width / depth going to infinity. Note how different parameterization makes pathlogical scaling behavior (yellow / blue on activations / gradients of the weight). muP solves this.

Ive just learned so much from this playground today. For example, here is what happens if you do gradient descent on relu MLP, even with muP setup. This shows how model is optimizing on last layers for most part, once it gets it, early layers gets updated(meaningful signal

Datarater on CIFAR-10 dataset, on single-step meta gradient purely implemented on pytorch fair to say, it looks like Datarater works! High score images are much more "feature crisp", where some low score images often looks confusing

I'm looking for talented and ambitious PhD students to join me at Nanyang Technological University Singapore to work on safe and robust AI systems! Full scholarships covering tuition and a stipend are available, and are open to local and international students alike.

It feels so different when you can explore, interact and play with the world you generated, in real time! Check out #genie3. We are having so much fun. It unlocks minutes-long consistency, simply by generating next frame auto-regressively.

To all my academic friends who gave me crap for joining OpenAI: We just open-sourced some banger models. Have fun with them!

What is with these guys, they are printing out papers! They do this very interesting editing-forward-process that performs corruption more than absorption, to 'mimick' false sampling process of langugage model but they dont describe the sampling process afterwords so Im

Something fun we discovered: you can use #Genie3 to step into and explore your favorite paintings. Here's a short visit to Edward Hopper's "Nighthawks".