Pravesh Koirala
@pravesh.bsky.social
PhD Student @ Vanderbilt University
Game Theory | Mathematical Optimization | Multiagent RL | LLM Numeracy
Game Theory | Mathematical Optimization | Multiagent RL | LLM Numeracy
Reposted by Pravesh Koirala
If you review for a #ML conference like @iclr-conf.bsky.social or @neuripsconf.bsky.social, YOU HAVE A RESPONSIBILITY TO REPLY TO THE AUTHORS.
If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.
I say this as an AC.
#MLSky
If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.
I say this as an AC.
#MLSky
December 4, 2024 at 10:58 PM
If you review for a #ML conference like @iclr-conf.bsky.social or @neuripsconf.bsky.social, YOU HAVE A RESPONSIBILITY TO REPLY TO THE AUTHORS.
If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.
I say this as an AC.
#MLSky
If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude.
I say this as an AC.
#MLSky
Can anyone just write a rebuttal etiquette or share if there is any. Per Cunningham's law, severely tempted to write a makeshift one myself.
December 3, 2024 at 7:07 PM
Can anyone just write a rebuttal etiquette or share if there is any. Per Cunningham's law, severely tempted to write a makeshift one myself.
Language Games seem like an interesting research area!
Are there limits to what you can learn in a closed system? Do we need human feedback in training? Is scale all we need? Should we play language games? What even is "recursive self-improvement"?
Thoughts about this and more here:
arxiv.org/abs/2411.16905
Thoughts about this and more here:
arxiv.org/abs/2411.16905
Boundless Socratic Learning with Language Games
An agent trained within a closed system can master any desired capability, as long as the following three conditions hold: (a) it receives sufficiently informative and aligned feedback, (b) its covera...
arxiv.org
November 30, 2024 at 5:04 AM
Language Games seem like an interesting research area!
Decisions and Dragons is such a nice overview of little RL subtleties that aren't really well explicated elsewhere: www.decisionsanddragons.com
Props @jmac-ai.bsky.social
Props @jmac-ai.bsky.social
November 15, 2024 at 1:34 PM
Whatever happened to NaNoWriMo?
November 14, 2024 at 1:59 AM
Whatever happened to NaNoWriMo?