Misha Laskin Reflection AI Super hyped about this release!! Asimov has been a great coworker 🥰

Some problems can’t be rushed—they can only be done step by step, no matter how many people or processors you throw at them. We’ve scaled AI by making everything bigger and more parallel: Our models are parallel. Our scaling is parallel. Our GPUs are parallel. But what if the

there needs to be stronger pushback against AI systems that will be only net harmful to humanity, like pika's "AI only social video app". we need to fight against the slop metaverse

There is 1 more week to submit non-archival extended abstracts to present at the Artificial Social Intelligence workshop #ICCV2025! We welcome work recently published in other venues (including the main ICCV conference) as well as works in progress!

every time i type img[:3, ...] to chop off an alpha channel i'm like hmmm.... a familiar friend.... :3

chatgpt sycophancy psychosis ❌ cursor + claude side project vibecoding flow state ✅

If you’re at SIGGRAPH 2025 in Vancouver, join us Thu 2 PM for our talk “Generative Neural Materials”! We introduce a universal neural material model for bidirectional texture functions and a complementary generative pipeline. 1/2

✨ Our paper Magic Fixup is accepted to ACM TOG! We show how dynamic videos can guide photo editing across many tasks — making this a solid baseline for future research. project page: magic-fixup.github.io paper: dl.acm.org/doi/10.1145/37…

one might think that tpot stands for that part of twitter, but it actually stands for that part of tpot

Guardrails with custom polices are hard for models trained on safety and harm-related datasets. But what if you trained a guardian model on arbitrary rules? Introducing DynaGuard, a guardian model for custom policies: arxiv.org/abs/2509.02563

Every lens leaves a blur signature—a hidden fingerprint in every photo. In our new #TPAMI paper, we show how to learn it fast (5 mins of capture!) with Lens Blur Fields ✨ With it, we can tell apart ‘identical’ phones by their optics, deblur images, and render realistic blurs.

Huge thanks to my amazing co-authors: Zhecheng Wang , Rebecca Lin , Daniel Miau, Florian Kainz, Jiawen Chen, Cecilia Zhang, David Lindell & Kyros Kutulakos 📄 Paper ➡️ blur-fields.github.io 💻 Code: coming soon! IEEE Computer Society #ComputationalPhotography #IEEECS

fast fantastic fashion fabrication

Introducing Ctrl-VI, a video sampling method allowing for a flexible set of user controls—ranging from coarse but easy-to-specify text prompts to precise camera/object trajectories. (1/n) arxiv.org/abs/2510.07670

what if you could combine diffusion models instantly? You would get exponentially better control (for free!!👀) This is exactly what we do. In ✨ coupled diffusion sampling ✨, diffusion models guide each other. The result? Diverse editing capabilities!