zoryzhang.notion.site Open in urlscan Pro
172.64.155.247  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Zory Zhang's Webpage

Blogs



Erstellt mit



ZORY ZHANG'S WEBPAGE


Hi! I'm Zory Zhang,

Chinese name 张瑜隽 (Pinyin: zhang1 yu2 jun4)

A Junior Undergrad

An Artificial Intelligence researcher

Major in MATH&CS at the University of Illinois Urbana-Champaign (UIUC) during
Fa23-Sp25

Studied at the Hong Kong University of Science and Technology (HKUST) during
Fa21-Su23


Hope you like here >_<

You’re very welcome to reach out and talk about anything!



ALT

Me @Hong Kong West Kowloon Cultural District, 2022 Jan
ALT
Here is my resumé:

Resumé_ZoryZhang_07_2024



RESEARCH INTEREST


I attempt to computationally characterize and model human learning and reasoning
by asking what it takes to build/reverse engineer an (artificial) cognitive
system that learns like a human: A system that can learn sample-efficiently,
incrementally, and continually (never-ending learning, without catastrophic
forgetting), as well as flexibly generalize during performance.

I believe that reasoning is not only a performance task but also helps learning,
i.e. Reason2Learn. Given prior beliefs, humans can learn so much from so little
exposure to a novel domain (e.g. ARC). I also believe perception and reasoning
are bidirectional. This mission bridges artificial intelligence and
computational cognitive science, producing a flexible, explainable and
persuasive AI as a byproduct. My toolkit includes hierarchical concept formation
(COBWEB), schema induction (LISA) and explanation-based learning (EBL) for
human-like learning, analogical reasoning and “neuro-symbolic” architecture for
human-like inference, using knowledge graph as less expressive but cheap factual
(as opposite to rule-like, procedural) knowledge representation, as well as
employing formal mathematics theorem proving as a playground to study cognition.

Side notes



PUBLICATIONS


Under review:

Zory Zhang, Ziyu Zhou, Haoran Liu, Jiaxuan You. (2024). Integrate Analogical
Abduction, Connectionism and Explanation-based Learning in a Theorem Prover.

Accepted with revision, in press:

Dylan Zhang, Curt Tigges, Zory Zhang, Stella Biderman, Maxim Raginsky, and Talia
Ringer (2024). Transformer-Based Models Are Not Yet Perfect At Learning to
Emulate Structural Recursion. Transactions on Machine Learning Research. Arxiv.



NEWS


June 2024: New blog post on cobweb: Computational Aspects of Cobweb: a
Human-like Category Learning Algorithm

May 2024: Glad to share that I’m conducting summer research with Christopher
MacLellan and Pat Langley.

Jan 2024: My first paper Transformer-Based Models Are Not Yet Perfect At
Learning to Emulate Structural Recursion is out.

Dec 2023: Four new posts What We Talk About When We Talk About AI2Reason (2/n),
Humans are Unconsciously Illogical, Collaboration and My 2023 in Academia.



POSTS


> Writing is the process through which ideas are produced and refined.

In this space, I will post blogs that contain mostly my original articulation,
therefore prioritized over other pages on my website, which are mainly notes.

Public view


Bild zum Verschieben ziehen

Computational Aspects of Cobweb: a Human-like Category Learning Algorithm
8. Juli 2024 20:44
Survey
Bild zum Verschieben ziehen

SubgraphGNNs All at Once
30. April 2024 20:41
Survey
Bild zum Verschieben ziehen

Collaboration
28. Februar 2024 23:42
Sharing
Bild zum Verschieben ziehen

My 2023 in Academia
19. Januar 2024 20:00
Sharing
Bild zum Verschieben ziehen

What We Talk About When We Talk About AI2Reason (2/n)
14. Januar 2024 19:38
Pitch
Bild zum Verschieben ziehen

Humans are Unconsciously Illogical
1. Januar 2024 4:21
Essay
Bild zum Verschieben ziehen

What We Talk About When We Talk About AI2Reason (1/n)
1. Januar 2024 2:16
Pitch


HIGHLIGHTED PAGES OF HIGH QUALITY


All blog posts, of course

AI/Cogsci PhD Application Advice Compilation

Attention & Transformer

English for Non-native Speakers

Berkeley CS162 along with most UIUC & HKUST course notes



MY WAY TO ACADEMIA


Blogs

AI/Cogsci PhD Application Advice Compilation

English for Non-native Speakers



KNOWLEDGE MAP


Cognitive Science

Artificial Intelligence

Theoretical CS & Math

System

Programming Languages



Papers Reading

> Hint: you may just search keywords.


MY COURSE NOTES


UIUC-notes

HKUST-notes

Other-notes



MY LIFE


漫漫前路有幾多風光



CONTACTS


Welcome to contact me via zoryz2@illinois.edu

If you see my icon above, that's extremely likely me  (It’s from 麦兜, a Hong Kong
anime character)

Twitter: https://twitter.com/zory_zhang

Google Scholar: https://scholar.google.com/citations?hl=en&user=W96WMoAAAAAJ

Github: https://github.com/zoryzhang

Linkedin: https://www.linkedin.com/in/zoryzhang/

Openreview: https://openreview.net/profile?id=~Zory_Zhang2

ORCID: https://orcid.org/0009-0009-7858-2876

Codeforces: https://codeforces.com/profile/Zory

(Ancient) Olympiad in Informatics website:
https://zoryzhang.github.io/Zory233.github.io/

Wechat: ZoryZHANG (give me your name and background plz)



SOME OF MY FRIENDS ONLINE


PhD@HKUST: Zihao Wang (supervized by Yangqiu Song, working on AI4Science and
Graph learning)

UG@HKUST: Matheart (an enthusiast about DL theory)

UG@HKUST: Yicheng Wang (an enthusiast about AI & reasoning)

UG@PKU: Xinwei Zhang (an enthusiast about ML theory and Math)

UG@Drexel U: Haoran Zhao (an enthusiast about AI, reasoning & cognitive science)

MS@Czech Technical U: Subfish Zhou (an enthusiast about AI, reasoning &
automated theorem proving)




Notion verwendet Cookies. Weitere Informationen findest du unter  Hinweis zu
Cookies .
Alle akzeptieren
Alle ablehnen

Public view