Li-Ping Liu

Associate Professor @ Tufts

[Li-Ping Liu @lipingliulp]

We still need more moderators. If you are interested, please let Dr. Thomas Dietterich know.

[Li-Ping Liu @lipingliulp]

I have taken on a new role as an arXiv moderator, reviewing submissions to the cs category.LG category. It's a fun job: while serving the community, I can also stay up-to-date with the latest research in this area.

[New Submissions to TMLR @TmlrSub]

Graph-based Confidence Calibration for Large Language Models

https://t.co/vXE887bVi6

#reliability #confidence #labeled

[Li-Ping Liu @lipingliulp]

Here is the paper link:

https://t.co/9RtwXCgPvt

[Li-Ping Liu @lipingliulp]

Our work on a new graph generative model G2PT is just accepted by ICML. The work opens up a new direction in graph generation by using token sequences. Now graph generation begins to align with image and language generation! Is the transformer taking over everything?

[Li-Ping Liu @lipingliulp]

Huge credit to my student Xiaohui, who led the effort. Honestly, with my old-school mindset, I wouldn’t have gone down this path myself. I’m proud of him for pushing the boundary and making it happen.

[Li-Ping Liu @lipingliulp]

@tweetsatpreet Thank you!

[Li-Ping Liu @lipingliulp]

Just got two papers and two proposals submitted in the last two weeks. Now it's time for social interactions with friends. I'd like to share some good news: my tenure case has been approved, and I will be promoted starting from 9/1

[Li-Ping Liu @lipingliulp]

@thejaan Thank you! I am still using Aeropress you introduced to me to make coffee for myself :)

[Li-Ping Liu @lipingliulp]

Great thanks to @TuftsCS! So supportive during the procedure!

[Li-Ping Liu @lipingliulp]

@rao2z Love it! How did you discover this web page?

[Li-Ping Liu @lipingliulp]

Is Total Solar Eclipse on your 2024 schedule? It will happen on April 8th and cover a long path in Mexico, US and Canada.
https://t.co/kV0kxpAGVw

[Li-Ping Liu @lipingliulp]

@berty38 @SnorkelAI Congrats to your new position!

[Li-Ping Liu @lipingliulp]

Happy new year! I wish everyone has another prosperous year. I am sure that AI will continue to gain impressive successes in 2024!

[Li-Ping Liu @lipingliulp]

but it doesn't have the ability to control the power supply of the town. So far, AI risk is not a concern unless we voluntarily give control of everything to a SINGLE learning agent -- this is not happening in the foreseeable future.

[Li-Ping Liu @lipingliulp]

On a survey of AI risk, this is what I have written:

Sometimes a buggy program (e.g. one with recursive calls) exhausts the stack, and the OS will throw an error and kill the program.

[Li-Ping Liu @lipingliulp]

A nuclear power plant explodes in extreme conditions, but the harm can still be contained within some expected range. The risk from the AI is similar. Suppose we have a highly intelligent service robot, it may give the wrong drugs to a patient,

[Li-Ping Liu @lipingliulp]

Does your transformer have a class token to predict? If so you may want to apply normalization separately for that token: https://t.co/fOSuBXjNIk --> see you at #NeurIPS2023 . (PS: the main idea is from students :))

[Li-Ping Liu @lipingliulp]

@keyonV @blei_lab @harvard_data Congrats! Want to give a talk at Tufts?

[Li-Ping Liu @lipingliulp]

We have updated our implementation of "Kriging Convolutional Networks" with PyTorch: https://t.co/eFwOY1mUhh