Assistant Professor @_indylab @UCIbrenICS @UCIrvine
Joined December 2012
- Tweets 128
- Following 166
- Followers 307
- Likes 267
3 Photos and videos
Roy Fox (@royf@sigmoid.social) retweeted
9 Feb 2024
Excited to share our work, "Skill Set Optimization", a continual learning method for LLM actors that:
- Automatically extracts modular subgoals to use as skills
- Reinforces skills using environment reward
- Facilitates skill retrieval based on state
allenai.github.io/sso
🧵
1
23
74
15,990
29 Jan 2023
I absolutely love how ChatGPT never actually admits any of its mistakes, instead “apologizing for the confusion”. It's like: “look, one of us seems very confused, but let's not get hung up on who. here's the plan: I won't deny partial responsibility, and you still tip me, k?”
2
7
871
29 Jan 2023
it's like how politicians “apologize if anyone misunderstood what I meant”; ChatGPT is a little weasel
1
286
Roy Fox (@royf@sigmoid.social) retweeted
16 Jan 2023
Are you interested in causality, machine learning and healthcare?
Come work with Mihaela van der Schaar (@MihaelaVDS) and me in a joint PhD or postdoc at Cambridge University, UK and the Technion, Israel
Contact via email: shalit-lab AT technion ac il
2
36
142
34,827
Roy Fox (@royf@sigmoid.social) retweeted
16 Sep 2022
The deadline for our #NeurIPS2022 InfoCog workshop is approaching soon [updated 🗓️: Sep 22]. We expect to have some funding to support a few selected presenters of accepted papers, and a special issue of Open Mind associated with the workshop! More info 👇
sites.google.com/view/infoco…
6 Aug 2022
📣 Very excited to announce our in-person #NeurIPS2022 workshop on Information-Theoretic Principles in Cognitive Systems!
Check out our lineup of invited speakers and CFP, submit short papers by September 19
sites.google.com/view/infoco…
#InfoCog2022 @NeurIPSConf
1
3
6
Roy Fox (@royf@sigmoid.social) retweeted
5 Aug 2022
Very excited for the 2022 edition of the #neurips Deep RL workshop! A few fun changes, see below. Also, submission deadline: Sep 22
5 Aug 2022
Super excited to announce this year’s Deep RL workshop @NeurIPSConf 🎉🎉🎓🎓
website: sites.google.com/corp/view/d…
submission deadline: September 22nd, 11:59 PM PST
Some exciting changes that we made this year in 🧵👇
3
32
Roy Fox (@royf@sigmoid.social) retweeted
3 Aug 2022
We (@BeEngelhardt, @NailaMurray and I) are proud to announce the creation of a Journal-to-Conference track, in collaboration with JMLR and conferences NeurIPS 2022, ICLR 2023 and ICML 2023!
neurips.cc/public/JournalToC…
iclr.cc/public/JournalToConf…
icml.cc/public/JournalToConf…
18
193
1,039
Roy Fox (@royf@sigmoid.social) retweeted
6 Aug 2022
📣 Very excited to announce our in-person #NeurIPS2022 workshop on Information-Theoretic Principles in Cognitive Systems!
Check out our lineup of invited speakers and CFP, submit short papers by September 19
sites.google.com/view/infoco…
#InfoCog2022 @NeurIPSConf
1
27
99
Roy Fox (@royf@sigmoid.social) retweeted
22 Jul 2022
המעבדה שלי בטכניון מחפשת עוזרי.ות מחקר! לפרטים נוספים: drive.google.com/file/d/16je…
כמו כן, מגייסים סטודנטים.ות לתארים מתקדמים. אל תהססו ליצור קשר! lacclab.github.io
2
6
Roy Fox (@royf@sigmoid.social) retweeted
28 Jun 2022
Policy Space Response Oracles (PSRO) mixes over a population of deep RL policies to approximate a Nash equilibrium, but exploitability can increase from one iteration to the next. We introduce Anytime PSRO which does not increase exploitability.
Arxiv: arxiv.org/abs/2201.07700
1
7
32
Roy Fox (@royf@sigmoid.social) retweeted
12 Dec 2021
Come join us tomorrow (Mon) for the #NeurIPS2021 Meaning in Context workshop!
We aim to advance human-machine communication by understanding how pragmatic reasoning works in humans and how it can inform AI
website: mic-workshop.github.io/
NeurIPS link: neurips.cc/virtual/2021/work…
1
8
34
9 Dec 2020
This. Our top conferences are "captive regulators" of noteworthy research, and Big ML has subtly shifted their focus to experiments that have low scientific value, high environmental footprint, and — significantly — only they can run. #demeritNeurIPS
7 Dec 2020
However, the chairs didn’t address the issue of corporate influence on the conference.
1
3
Roy Fox (@royf@sigmoid.social) retweeted
28 Aug 2020
Interested in hearing about the theoretical foundations of RL from a multidisciplinary perspective (CS, control, stats, OR)? If so, join us at the (all virtual) RL Theory Bootcamp at the Simons Institute next week. Lectures in the morning and the afternoon ==>
4
73
368
Roy Fox (@royf@sigmoid.social) retweeted
18 Aug 2020
There is no magical benchmark that experiments must be run against in order to be acceptable.
2
6
46
Roy Fox (@royf@sigmoid.social) retweeted
23 Jul 2020
Would people be ok with renaming it
"I Can't Believe It's Not Intelligence! ®"
23 Jul 2020
1
2
13
UCI researchers launch first-of-its-kind #coronavirus statistics portal: Site provides comparisons between OC & neighboring counties.
More: bit.ly/3adtl3V
19
33
25 Jul 2020
I have an imitation learning joke, but not sure it is the reason why you laugh.
24 Jul 2020
I have a causality joke, but not sure it is the reason why you laugh.
3
25 Jul 2020
I have a reinforcement learning joke, but I'm sure it will be lost on the critics.
25 Jul 2020
I have a computer vision joke hidden somewhere in this tweet, but you're not seeing it.
2
Roy Fox (@royf@sigmoid.social) retweeted
13 Jul 2020
amii.ca/postdoc-opportunity-…
One last time; official ad is out.
13
42