Perfect!

@daphnezohar.bsky.social does that mean streaming live, or do we wait for the episode to be released?

This is an interesting case because by all rights, Sasha Rudensky could have easily been named and won as well; I would be curious as to what Brunkow would say if offered (theoretically) to trade the award for access to a career like Rudensky's, and vice-versa!

All scientists! But yes, women scientists, too. Ramsdell, who was outside of academia like Brunkow, got to serve as the CSO of Sonoma; Brunkow was a science writer for a while and then a program manager.

Could it be that it’s so close to translation? There’s an overwhelming feeling of responsibility to stay in, working on what’s important (curing disease, etc.)

I’ll delete this slightly snide comment!

I’d find it more heartening if they hadn’t *wanted* to stay in academia: Kariko famously so, but Bruknow too. Lee managed it, but as a senior scientist in her husband and coauthor’s lab.

I know that these sorts of stories, where recognition comes in the end, are supposed to provide a certain kind of told-you-so satisfaction and inspiration; but I'm sure I (and most) would trade it for 20-40 years of productive work life of controlling and shaping a research program.

I was thinking this too! If anyone on here has a warm intro for me... I reached out today to a few people there, but just on LinkedIn.

You can read more in our post at www.jurabio.com/blog/leavs; preprint forthcoming.

@jura.bsky.social @eliweinstein.bsky.social @mgollub.bsky.social @highvariance.bsky.social

Today we introduce LeaVS (Learning from Variational Synthesis), a system for accelerating AI training on this functional data. LeaVS goes beyond conventional model training procedures by exploiting knowledge of the underlying synthetic library.

The result? A dramatic speedup in learning.

Instead, it requires changes to how we design algorithms, allocate resources, and engineer systems. It requires carefully identifying and removing bottlenecks on learning, across the entire training stack.

This is what's so transformative about variational-synthesis driven discovery; we don't have to learn from positive results only as we have the underlying generative model sequences in addition to the positive hits.