evanthebouncy (@evanthebouncy) 's Twitter Profile
evanthebouncy

@evanthebouncy

asst prof @ NTU, ex principal scientist @ autodesk, phd mit 2019.

I make programming more communicative 🧠↔️🤖

ID: 1089854503

linkhttp://www.mit.edu/~yewenpu calendar_today14-01-2013 18:54:11

552 Tweet

803 Followers

209 Following

evanthebouncy (@evanthebouncy) 's Twitter Profile Photo

I have yet to see RL succeeds with negative rewards in high dimensions of observation and action space. Do we know of a method that works well while using ONLY negative rewards? OTOH, humans learn very well from negative rewards, we just call them 'lessons'. what gives?

evanthebouncy (@evanthebouncy) 's Twitter Profile Photo

Industry only engages with academia in areas that are: 1) poorly understood 2) tantalizingly profitable 3) threaten extinction Engage industry through mystique, lust, and fears

evanthebouncy (@evanthebouncy) 's Twitter Profile Photo

for fun I went through all my papers and tallied how many times I submitted each. note how it follows a geometric distribution, modeling the policy of "yolo submit until accepted". "but each submission's outcome are not independent coin tosses!!" or is it? plot yours.

for fun I went through all my papers and tallied how many times I submitted each. 

note how it follows a geometric distribution, modeling the policy of "yolo submit until accepted".

"but each submission's outcome are not independent coin tosses!!" 

or is it?

plot yours.
evanthebouncy (@evanthebouncy) 's Twitter Profile Photo

cleaning the whiteboard in my office, I noticed in the upper left corner, in faded ink, "I'd rather be feared than be loved". some previous prof really wrote that down, and it refused to fade. I don't know what to make of it

Gabriel Poesia (@gabrielpoesia) 's Twitter Profile Photo

Thrilled to join the UMich faculty in 2026! I'll also be recruiting PhD students this upcoming cycle. If you're interested in AI and formal reasoning, consider applying!