Sign in

Taylor W. Killian

@twkillian.bsky.social
3.2K followers 441 following 109 posts

Principal Scientist @LilaSciences. Focused on decision making under uncertainty, guided by practical problems in healthcare, reasoning, and biology.

PostsRepliesMedia
Reposted by Taylor W. Killian
Lila Sciences @lilasciences.bsky.social · 25/09/2026
Iridium limits the production of hydrogen from renewable energy, and it's one of the rarest elements on Earth. We screened 2,942 catalysts in 3 months and found a palladium-based candidate the field wrote off decades ago. Early days, but the AI got there on its own. www.lila.ai/news/how-an-...
lila.ai
How an AI-run lab cracked open green hydrogen's catalyst problem | Lila
In three months, Lila Sciences’ AI-directed lab proposed, synthesized and screened 2,942 catalysts for green hydrogen, identifying 6 high-performing material families.
011
Taylor W. Killian @twkillian.bsky.social · 01/09/2026
New ML+RL professor starter pack. (Yes, I only have one shelf filled with books) It’s fun to have friends who’ve written textbooks. Lots to learn and re-learn as I prep for my first lectures this week!
010
Taylor W. Killian @twkillian.bsky.social · 24/08/2026
I've been the recipient of a lot of genuine compliments recently which have made me feel really great. In a period of change in my life, these little blasts of good vibes have been soul-sustaining at times. I'm resolving to pay it forward as much as I can. #sharegoodness
000
Reposted by Taylor W. Killian
Reinforcement Learning Conference @rl-conference.bsky.social · 17/08/2026
A truly compelling keynote from Sheila McIlraith at RLC 2026 today — exploring how formal language can serve as a nexus between signals and symbols for agents that learn, plan, and remember. A principled and thought-provoking perspective on the future of RL and agentic AI!
0174
Taylor W. Killian @twkillian.bsky.social · 18/08/2026
As I leave #RLC2026 (unfortunately a day early)… My best seeds of future research ideas are planted as a result of every interaction I have at this conference. As Workshop Chair and Keynote panelist, it was a great success!
160
Reposted by Taylor W. Killian
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 16/08/2026
Y'all, RLC is so good. It's the community and conference I wish I had had as a grad student
1232
Reposted by Taylor W. Killian
Pablo Samuel Castro @pcastr.bsky.social · 15/08/2026
At #RLC2026 and want to run? Come for a #runconference tomorrow (Sunday)! Let's meet at 7am at the pin below and run up the mountain for a beautiful morning view. See you there! maps.app.goo.gl/w7e7CqRbARdG...
062
Taylor W. Killian @twkillian.bsky.social · 15/08/2026
Standing room only at several points of our workshops today at RLC 2026. RL is not having a moment, it’s a full on movement (has been and will continue to be).
030
Taylor W. Killian @twkillian.bsky.social · 15/08/2026
Kicking off my RLC 2026 Workshop Day by listening to Doina Precup in the Big World workshop. I love her vision about building alternative conceptual frames of RL to overcome limitations of normative MDP assumptions.
030
Taylor W. Killian @twkillian.bsky.social · 15/08/2026
Today is workshop day at RLC 2026! Workshops at RLC have always been a distinct highlight of the conference. Today’s slate is no different. I’m looking forward to seeing everyone there!
061
Taylor W. Killian @twkillian.bsky.social · 13/08/2026
I'm excited about the Reinforcement Learning Conference starting at the end of the week in Montreal! We have some fantastic workshops planned for Saturday (rl-conference.cc/accepted_workshops…) that I am sure will again be a highlight and set the stage for a great conference.
rl-conference.cc
Accepted Workshops | RLC 2026
Accepted pre-conference workshops at RLC 2026.
1142
Taylor W. Killian @twkillian.bsky.social · 13/08/2026
I'm excited to see how this new interface plays out. Interactivity in my bluesky experiences has been low (likely a function of my own activity, sorry), but I'm looking forward to engaging more here!
142
Taylor W. Killian @twkillian.bsky.social · 03/08/2026
Today is my first day @brighamyoungu.bsky.social! As promised in the 👇 thread (a few weeks late but c'mon ;) ), I've written a post explaining my decision to return to academia _and_ my home town: twkillian.github.io/returning-to... I'm excited for the journey ahead!
twkillian.github.io
Returning to Academia: Motivations and Expectations
Personal research webiste for Taylor W. Killian
020
Taylor W. Killian @twkillian.bsky.social · 14/05/2026
📣 There's never a "best" time to share important updates, especially after sitting on this for so long. I'm joining the faculty @brighamyoungu.bsky.social this Summer as an Assistant Professor in the CS Dept, in preparation for the coming school year. Lots of excitement and a fair bit of nerves. 🧵
7192
Reposted by Taylor W. Killian
Ted Underwood @tedunderwood.com · 14/05/2026
Unfortunately positive feedback from students, like all positive feedback, embarrasses me and reminds me of the infinite disproportion between what I’ve given the world and what I owe it. But go ahead and send that note! most of your teachers are sane.
0371
Taylor W. Killian @twkillian.bsky.social · 03/05/2026
I had some time to reflect on my past 12 months after some long flights following #ICLR. It's been a whirlwind year where I've been lucky to visit so many beautiful places while engaging in scientific discussions. Jotted some reflections down in a blog post: twkillian.github.io/science-is-a...
171
Taylor W. Killian @twkillian.bsky.social · 15/04/2026
This has been the README of the Github repo of my personal+academic website since I first started it. And this is my latest commit 😱...
130
Taylor W. Killian @twkillian.bsky.social · 06/04/2026
It's our kid's spring break this week. It's been nice having yard work agents work in parallel to my coding agents.
010
Reposted by Taylor W. Killian
Reinforcement Learning Conference @rl-conference.bsky.social · 31/03/2026
We have the keynote speakers for RLC2026 now! Thrilled to welcome Rika Antonova, Sheila McIlraith, Marc G. Bellemare, Danijar Hafner, Balaraman Ravindran! Details: rl-conference.cc/index.html The RL community is coming together this August in Montréal, Québec, Canada. Hope you make it!
rl-conference.cc
RLC 2026
02410
Taylor W. Killian @twkillian.bsky.social · 31/03/2026
RLC is the _very_ best conference. It's always been great vibes and will continue this for the 2026 version!
040
Taylor W. Killian @twkillian.bsky.social · 24/03/2026
It’s a real joy being a part of @lilasciences.bsky.social! The momentum inside the company is tangible, it’s nice that it’s being recognized externally as well.
020
Reposted by Taylor W. Killian
Christian Wolf @chriswolfvision.bsky.social · 18/03/2026
Nice work by the ICML chairs ... love it. Signal boosting this to help make it known. I hope that the effect will be that reviewers will less "delegate" (sigh) reviewing to LLMs instead of spending more effort on finding watermarks.
2286
Reposted by Taylor W. Killian
Reinforcement Learning Conference @rl-conference.bsky.social · 26/02/2026
RLC2026 Call for Workshops! We’re already live: openreview.net/group?id=rl-... Here's the opportunity to help shape the conference & spotlight your own RL focus areas. Call: rl-conference.cc/call_for_wor... Deadline: Mar 12 (AoE) And don't forget the awesome banquet :) www.cirquedusoleil.com/ludo
075
Reposted by Taylor W. Killian
Aadirupa Saha @aadirupa.bsky.social · 26/02/2026
RLC 2026 Call for Workshop is live on OpenReview! Submission deadline: Mar 12 (AoE). Full details here: rl-conference.cc/call_for_wor... @glenberseth.bsky.social @eugenevinitsky.bsky.social @twkillian.bsky.social @schaul.bsky.social @sologen.bsky.social @audurand.bsky.social @bradknox.bsky.social
rl-conference.cc
RLJ | RLC Call for Workshops
0103
Reposted by Taylor W. Killian
Reinforcement Learning Conference @rl-conference.bsky.social · 25/02/2026
RLC attendees will also enjoy the banquet featuring a theatrical dinner show by Cirque du Soleil (LUDŌ): www.cirquedusoleil.com/ludo All the more reason not to miss the chance to be part of RLC 2026!
cirquedusoleil.com
LUDÕ | Cirque du Soleil
Discover Nuevo Vallarta's new resident dinner show LUDÕ. Immerse yourself in a multi-sensory water-themed experience.
071
Reposted by Taylor W. Killian
Reinforcement Learning Conference @rl-conference.bsky.social · 25/02/2026
Only ~7 days to go until the full paper deadline (Mar 5, AOE)! Wishing everyone a strong close to the submission cycle.
0113
Reposted by Taylor W. Killian
Audrey Durand @audurand.bsky.social · 19/02/2026
RLC 2026 Call for Workshops is up! This is the opportunity to bring the attention of the community to the topics that you find the most important in RL!
054
Reposted by Taylor W. Killian
Claire Vernade @claireve.bsky.social · 18/02/2026
Check out the Call for Workshops at RLC this year. There is still nearly a month before the deadline, we are looking forward to your proposals!
0113
Reposted by Taylor W. Killian
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 17/02/2026
Exciting news... Percepta is growing into doing critical industry transformations in Europe, and that means we're expanding to the UK! If you're an Applied AI engineer looking to work in the UK check it out: jobs.ashbyhq.com/percepta/55a...
jobs.ashbyhq.com
Applied AI Engineer
WHO WE ARE Percepta’s mission is to transform critical institutions with applied AI. We care that industries that power the world (e.g. healthcare, manufacturing, energy) benefit from frontier techno...
1162
Reposted by Taylor W. Killian
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 13/02/2026
The workshops are maybe the best part of RLC. Bring us your workshops that could never happen anywhere else!
0141
Reposted by Taylor W. Killian
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 13/02/2026
3 weeks to get your RLC papers in shape! And to get the word out to those who have yet to experience an RLC review process.
0102
Reposted by Taylor W. Killian
Igor Gilitschenski @igilitschenski.bsky.social · 13/02/2026
🚀 Excited to share REPPO, a new on-policy RL agent! TL;DR: Replace PPO with REPPO for fewer hyperparameter headaches and more robust training. REPPO, led by @cvoelcker.bsky.social, will be presented at ICLR 2026. How does it work? 🧵👇
12510
Taylor W. Killian @twkillian.bsky.social · 13/02/2026
We're thrilled to share that the Call for Workshops for this year's @rl-conference.bsky.social is now live! As Workshop co-chair (alongside the wonderful Raksha Kumaraswamy and @claireve.bsky.social) we are looking forward to seeing the proposals for workshops that we receive. LINK IN NEXT POST
1115
Taylor W. Killian @twkillian.bsky.social · 01/05/2025
One paper accepted to ICML with one paper rejected as well. It’s called balance (and measured frustration) #icml2025
050
Reposted by Taylor W. Killian
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 01/05/2025
Shipping a copy of Kuhn's "Structure of Scientific Revolutions" to every ICML meta-reviewer
2464
Taylor W. Killian @twkillian.bsky.social · 16/04/2025
We're putting in final planning and preparation steps this week to be ready for #ICLR2025. I'm excited to be attending, in part to help represent @mbzuai.bsky.social and @llm360.bsky.social as well as recruit Research Scientists and Engineers to our new lab in the Bay Area! (see next for more info)
120
Taylor W. Killian @twkillian.bsky.social · 22/03/2025
I used to dream of days like this. Mowed the lawn, trimmed some hedges, pruned a few trees to let more sun into our yard, picked the rest of our orange tree (we yielded 658 🍊this year!) had the kids help clean up the branches, etc. #suburbandadsaturdays
040
Reposted by Taylor W. Killian
Peter Henderson @peterhenderson.bsky.social · 12/03/2025
Real-world RL for the public good! Love to see it!
0142
Reposted by Taylor W. Killian
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 12/03/2025
A year later of a multi-agent RL controlled variable speed limit system: arxiv.org/abs/2503.01017 Fewer crashes, quicker responses, quicker warnings
arxiv.org
Real-World Deployment and Assessment of a Multi-Agent Reinforcement Learning-Based Variable Speed Limit Control System
This article presents the first field deployment of a multi-agent reinforcement learning (MARL) based variable speed limit (VSL) control system on Interstate 24 (I-24) near Nashville, Tennessee. We de...
2384
Taylor W. Killian @twkillian.bsky.social · 12/03/2025
Reviewing a paper right now and I'm having lots of "I wish that I'd written this!" feelings. Great sign for the authors tbh.
190
Reposted by Taylor W. Killian
John D. Martin @jdmartin86.bsky.social · 05/03/2025
Congratulations Andy and Rich! You've given RL yet another place in the history books. I can't imagine how you're feeling right now, but it must be amazing to reflect on how far the ideas have come, especially after all the care and dedication you gave them. awards.acm.org/about/2024-t...
awards.acm.org
0101
Taylor W. Killian @twkillian.bsky.social · 04/03/2025
As I've started down the RL+LLM rabbit hole (for reals this time), this blog post by TensorZero is absolutely compelling. It's nice to see clear thinking conceptual framing that at once open the doors to new research but also leverages existing insights: www.tensorzero.com/blog/think-o...
tensorzero.com
Think of LLM Applications as POMDPs — Not Agents · TensorZero
Think of LLM Applications as POMDPs — Not Agents
2204
Taylor W. Killian @twkillian.bsky.social · 03/03/2025
Struggled to find a paper to recommend to authors that would strengthen their claims while writing a review. Used @GeminiApp and @youdotcom to no success. Reluctantly pulled up @ChatGPTapp, nailed it in the first returned result. #HesitantAboutLLMsButTryingToLearn
media.tenor.com
a man with a beard is saying he can 't keep getting away with it !
ALT: a man with a beard is saying he can 't keep getting away with it !
000
Reposted by Taylor W. Killian
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 28/02/2025
"Scaling laws" tries to piggyback on physics where the scaling laws are resultant from statistical limits. To call them "laws" rather than "empirical scaling curves" is real iffy
2401
Taylor W. Killian @twkillian.bsky.social · 24/02/2025
Day 1 with @mbzuai.bsky.social as we start building out a new non-profit, open research lab in the Bay Area. Lots to learn and my head is spinning but I’m excited to get started pushing the boundaries of what we know about reasoning and decision making under uncertainty.
130
Reposted by Taylor W. Killian
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 06/02/2025
We've built a simulated driving agent that we trained on 1.6 billion km of driving with no human data. It is SOTA on every planning benchmark we tried. In self-play, it goes 20 years between collisions.
2229855
Reposted by Taylor W. Killian
Bernhard Jaeger @bernhard-jaeger.bsky.social · 06/02/2025
arxiv.org/abs/2502.03349 Awesome planning results by Vladlen Koltun's new lab (@twkillian.bsky.social, @eugenevinitsky.bsky.social @senerozan.bsky.social and others) that everyone working on driving should read. Lots of details are in the Appendix.
arxiv.org
Robust Autonomy Emerges from Self-Play
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...
1143
Taylor W. Killian @twkillian.bsky.social · 04/02/2025
📍Provo, Utah
010
Taylor W. Killian @twkillian.bsky.social · 30/01/2025
This afternoon I've been putting finishing touches on a talk that I've been invited to give at my undergrad Alma Mater (BYU Math) next Tues. Since graduating, I've been hoping for an opportunity to return & share how my career has grown from the solid foundation I gained there. I'm really excited!
120