Haonan Duan (@haonanduan) 's Twitter Profile
Haonan Duan

@haonanduan

M.Math and B.Math in Computer Science @UWaterloo. Student affiliate @VectorInst. Bayesian learning, probabilistic reasoning and NLP.

ID: 1303461934075969536

linkhttps://cs.uwaterloo.ca/~h4duan/ calendar_today08-09-2020 22:35:25

11 Tweet

40 Followers

303 Following

Paul Pearce (@paul_pearce) 's Twitter Profile Photo

UC Berkeley MIT Stanford CMU UIUC U. of Washington Cornell Georgia Tech Princeton UT Austin Michigan Wisconsin UCSD Harvard UMD UPenn Purdue UMass Amherst NYU NEU UChicago And I hear more are coming. I'll add more if people reply.

Devi Parikh (@deviparikh) 's Twitter Profile Photo

NeurIPS 💯🎉! “all come all served” Registration is $25 for students and $100 for non-students. Tutorials, keynotes and oral pre-recorded presentations accessible without a registration. Video recordings of the poster presentations will be released after the conference.

timorous bestie 😷 (@vnfrombucharest) 's Twitter Profile Photo

New blog post: introduction to gradient-based optimization with constraints: reparametrization, projected gradient, cool connections in between. 🔮Geometry insights show that 🪞mirror descent = reparametrization with a "straight-through" sigmoid! vene.ro/blog/mirror-de…

Stefanie Tellex (@stefanietellex) 's Twitter Profile Photo

I wrote a guide to writing research statements for Ph.D. programs and fellowships. Good luck to everyone who is applying this cycle! h2r.cs.brown.edu/writing-a-rese…

Laura 🌲 ⛰️ (@laurademing) 's Twitter Profile Photo

Is there a good reason why many basic laws of physics are linear or quadratic (for example, F=ma), not much more complex? This might be a silly question - I'm just curious why this isn't true, or what kinds of laws we'd be unlikely to see.

Chris J. Maddison (@cjmaddison) 's Twitter Profile Photo

Is there enough public data in AI4bio to repeat the success of LLMs in NLP? Not clear. What is clear is that we aren’t even using all the available tokens. Our new preprint: often-ignored text tokens can improve protein LMs. 🤗tinyurl.com/yx6cccnw 📝tinyurl.com/3a49epbx

Is there enough public data in AI4bio to repeat the success of LLMs in NLP? Not clear. What is clear is that we aren’t even using all the available tokens. Our new preprint: often-ignored text tokens can improve protein LMs.
🤗tinyurl.com/yx6cccnw
📝tinyurl.com/3a49epbx