Postdoc-ing @ UIUC. Working on systems reliability and efficiency. Opinions, my own. Retweets are not endorsements.
Joined August 2022
- Tweets 298
- Following 726
- Followers 301
- Likes 1,274
4 Photos and videos
Passionate about making computer architecture, compiler, and parallel-systems research more reproducible?ππ¬π₯οΈ
PACT'26 is looking for Artifact Evaluation Committee members. Self-nominate by July 24: forms.gle/M6ftRqHbzPexkZzk9
1
81
What an awesome first @CAISconf! I'm so grateful to @heathercmiller and @matei_zaharia for letting me be part of it. It was a joy to work with such dedicated folks. Huge shout-out to @aviaviavi__, @lateinteraction, @ChenLingjiao, @deeptir18, @jaredq_ and @JoshQuicksall!
May 27
We welcome you to the first @CAISconf . We have a great lineup of keynotes, talks and demos starting today for the main conference. Come join us!
1
16
580
Vish (@vishctx) is one of the smartest, most talented, hardworking, and incredibly kind person I know! You'd be super lucky to work with him!
3
258
π₯π₯π₯
π The full CAIS '26 schedule is live.
61 peer-reviewed papers. 45 live system demos. Three keynotes. No pitch decks. No vibes-based benchmarks. No "AI-powered" anything without the receipts.
This is what it looks like when the field stops performing and starts publishing.
caisconf.org/schedule/2026/
We're nearly at our registration cap. Single-digit spots left.
caisconf.org/registration/
San Jose Β· May 26β29
1
152
Congratulations! This is an awesome read! Can't wait for the @CAISconf talk :-)
My paper with @ReshabhSharma01 and @shraddha_96, βWillful Disobedience: Automatically Detecting Failures in Agentic Tracesβ, will appear this month in the First ACM Conference on AI and Agentic Systems (CAIS 2026). arxiv.org/abs/2603.23806
1
4
631
Heather (@heathercmiller) is absolutely right! Book mark this tweet ππ
May 12
"It is categorically *not* a victory for pure LLMs; itβs a victory for borrowing from classical AI and CS to move *beyond* pure LLMs."
βοΈ Compound AI Systems alllll the way downnn
1
120
Mind-blowing statistics!! Congrats to everyone!! π
We're working hard to highlight the tremendous effort that went into Artifact Evaluation, as well. Stay tuned! πͺ
Sort of mind-blowing to see how much community effort went into making ACM CAIS happen, and this is only on the side of the committees:
caisconf.org/program/2026/coβ¦
230 people volunteered time!
& this doesn't count artifact evaluation reviewers
or workshop reviewers
or authors
π€―
2
151
I have a confession to make. This is one of the benchmarks that got me incredibly excited about investigating systems capabilities of AI agents (and I'm not just saying this because @tianyin_xu is incredibly generous for giving me the space to explore a few bad ideas π
). Seriously, y'all should read this paper
May 8
Last fall, we wrote a small benchmark called SysMoBench when developing Specula. SysMoBench asks AI to model current, distributed systems in TLA . @qiancheng9788 and the team wrote about the experience and updated the results on newest LLMs. The abilities of frontier models today are rather impressive and our Specula agent can get 100% on the benchmark now.
@qiancheng9788 put up a nice website: sysmobench.com
1
5
1,748
π’One of several exciting workshops happening at @CAISconf this year. Now, with an extra 24h for submitting your work. πππ
π’ Deadline update for the ACM CAIS workshop AI Discovery in the Wild: submissions are now due May 7 AoE.
π€ Encouraging submissions on LLM/agent systems, infrastructure, optimization, evaluation, and real-world deployment challenges.
Concurrent submissions are welcome.
CFP π
3
2
944
Congratulations to all authors!! π₯³π₯³π₯³
We invite all accepted research papers to consider registering for artifact evaluation: caisconf.org/pages/cfa/
πππ
caisconf.org/program/2026/paβ¦
CAIS's 2026 accepted papers!
61 accepted papers, from 110 organizations globally
Papers come equally from industry and academia
2
9
1,066
Woohoo!! We're beyond excited for the demo sessions! π₯³π₯³ @CAISconf strives to be a home for rigorous & reproducible research, so besides working at putting together an absolute banger of a technical program, we're also building a top-notch Artifact Evaluation committee πͺπͺ
Apr 10
the demo track at @CAISconf is gonna be sickkk
mark my words
1
1
192
For those of you that want to volunteer for Artifact Evaluation (great opportunity for MSc and PhD students): forms.gle/DwsV2ST7wRraVY4w5
59
Passionate about Building the future of agentic AI? π€
ACM CAIS'26 (@CAISconf) is looking for our inaugural Artifact Evaluation Committee. Self-nominate by April 12. Details & sign-up link in the reply below! π
1
1
3
491
Here's some useful info:
β’ AE period:Β Apr 23 - May 8, 2026
β’ Workload:Β ~2 artifacts
β’ Sign up: forms.gle/DwsV2ST7wRraVY4w5
β’ Nominations due: Apr 12, 2026
β’ Website: caisconf.org/pages/cfa/
114
Bogdan "Bo" Stoica π @cachemisses.bsky.social retweeted
Apr 4
We are seeking emergency reviewers for the inaugural ACM CAIS 2026 conference @CAISconf on AI systems.
Emergency reviewers should expect a load of ~2 papers, ideally to be completedΒ within 48-60 hours of assignment.
Please fill the short form below!
docs.google.com/forms/d/e/1Fβ¦
3
16
64
17,550