Dun Li Chan

                                                                                                                     
                                                                                                                     
`7MM"""Yb. `7MMF'   `7MF'`7MN.   `7MF'    `7MMF'      `7MMF'      .g8"""bgd `7MMF'  `7MMF'      db      `7MN.   `7MF'
  MM    `Yb. MM       M    MMN.    M        MM          MM      .dP'     `M   MM      MM       ;MM:       MMN.    M  
  MM     `Mb MM       M    M YMb   M        MM          MM      dM'       `   MM      MM      ,V^MM.      M YMb   M  
  MM      MM MM       M    M  `MN. M        MM          MM      MM            MMmmmmmmMM     ,M  `MM      M  `MN. M  
  MM     ,MP MM       M    M   `MM.M        MM      ,   MM      MM.           MM      MM     AbmmmqMA     M   `MM.M  
  MM    ,dP' YM.     ,M    M     YMM        MM     ,M   MM      `Mb.     ,'   MM      MM    A'     VML    M     YMM  
.JMMmmmdP'    `bmmmmd"'  .JML.    YM      .JMMmmmmMMM .JMML.      `"bmmmd'  .JMML.  .JMML..AMA.   .AMMA..JML.    YM

                                                    
                                                    
    .#*  :@*         *#    .@.         +#.   WW     
 M###@###@@###M   +@@@@@@@+*#.....      W:   WW     
 M*.:..WW..*.*#            M@@@@@W  .MMMMMM  WW     
 M*:@: +W :@::#    W@###@*.@.  WW    ****W#  WW     
 M* +M +W #* :#    W*   M*M@.  M*       .#*  WW     
 MW**+*MM*+**W#    WMWWW#W@#*  @:       MW   WW     
 MMWWWWWWWWWWM#    ++:::W:*+W :@       W#:.  WW     
 ..............    ++++++: :# +M      W@#+@* WW     
  :@########@*     ++++M@*  @:#*    .M#+# *@*WW     
  :#        M*        W#:   +##     WM.*#  : WW   +W
  :@MMMMMMMM@*    :++W@MM#* :@W     .  *#    WW   +M
  :#::::::::#*    *W++@*:: :##@*       *#    WW   WW
  :#********#*        @.  +@W W@+      *#    W#..:#+
  :@WWWWWWWW#*     :M## .#@+   +@M     *#    .#@@@M.
  .+        *.      **.  *.     :.     :+      ...

About Me

I'm currently building across AI safety evaluation in LLMs and physical AIs, mechanistic interpretability, and AI4Astro. My research interest lies in understanding how models work internally (layer-wise) and how this information can advance our progress in AI, while making sure they're safe to deploy in real-world settings. And most of the time, I'm very obsessive and competitive about learning and solving things that I really enjoy (especially in research).

Timeline

Present

Exploring cool stuff in AI safety & Physical AI

Conducting research in safety evaluation, VLA/RL infrastructure, and related areas while exploring opportunities to build or join a startup

2024 - Present

AI research

Conducted AI research with multiple frontier labs after realizing chemistry was not for me; focused mainly on mechanistic interpretability, NLP, and AI4Science projects, and published several papers in top conference workshops
Founded MYResearchGuide & Malaysia Science Scholar's Programme as a side project — an initiative to help Malaysian students discover science research opportunities, supported by 40+ researchers from top institutions (Ivy League and Oxbridge) to frontier industry labs (Meta AI and YC-backed startups), and sponsored by multiple companies and institutions including MathWorks (MATLAB)

2025

Olympiads

Placed 3rd and 2nd in Malaysia Astronomy Olympiad selection rounds (w/ 3 months of prep) → represented Malaysia in IOAA and IAO → now help as a problem setter
Started a science olympiad tutoring platform (olyprep.io) on Discord as a side business, reaching $10K USD MRR within 2 months and serving 50+ students

Malaysia in IOAA [Post]

2023 - 2024

Biochemistry research

Joined my school's science research program under Universiti Sains Malaysia, where I developed a nanopesticide from biowaste materials to eradicate red flour beetles and competed in the Malaysia ISEF national selection finals (Top 25). Project abstract

2020 - 2022

Esports

Reached the top 200 in Apex Legends while competing in the Asian region, achieved Ascendant in Valorant, a five-digit rank in osu!, and Conqueror in PUBG Mobile
Spent ~500 hours completing the entire Legend of Zelda series before Breath of the Wild

2017 - 2019

Still a kid

Spent around 400 hours playing Roblox, mainly Arsenal; learned Kali Linux using a Raspberry Pi 4 I received as a birthday present, and jailbroke multiple phones at home to overclock them
I was part of my elementary school's robotics team, where I spent most of my time building with LEGO Mindstorms EV3; the team won third place at the National Robotics Competition (NRC)

Working Papers / Projects

Identification of Faint Near-Earth Asteroid Streak Candidates Using a Three-Channel Deep-Learning Pipeline. Drafting for journal submission; Dept. of Astronomy, Shanghai Jiao Tong University (SJTU) & University of Maryland with Yiyang Guo, Quanzhi Ye

ongoing

Feature-Based Comet Classification Pipeline for Zwicky Transient Facility (ZTF) Alert Image Streams. Dept. of Astronomy, University of Maryland with Quanzhi Ye et al.

ongoing

Publications (preprints/peer-reviewed papers)

Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy NeurIPS 2026 Interpretability for Discovery Workshop (submitted) with Kshitij Duraphe et al.

ongoing

How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language Models NeurIPS 2026 Interpscience Workshop Long Paper Track (submitted) with Emily Liu et al. [arxiv]

ongoing

Beyond Query Linearity: The Case for Nonlinear Queries. NeurIPS 2026 NeurReps Workshop Extended Abstracts Track & SLM-Agents Workshop Short Paper Track with Marko Karbevski et al.

08/2026

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families. EMNLP 9th BlackboxNLP Workshop Special Track: Reproducibility and Reliability in Interpretability Analyses (submitted) with Alizishaan Khatri [arxiv]

08/2026

Large-Scale Symbolic Music Genre Classification under Class Imbalance using Graph-Based MIDI Embeddings (part of GigaMIDI projects). Drafting for TISMIR with Keon Ju Maverick Lee, Philippe Pasquier et al., Metacreation Lab, Simon Fraser University (SFU)

07/2026

Anthropogenic Regional Adaptation in Multimodal Vision-Language Models. AACL-IJCNLP 2026 Findings with Samuel Cahyawijaya, Peerat Limkonchotiwat et al., SEACrowd [arxiv]

04/2026

Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings? EACL 2026 - LoResMT Workshop with Aishwarya Ramasethu, Niyathi Allu, Rohin Garg, Harshwardhan Fartale [official] [arxiv]

03/2026

A Traditional Approach to Symbolic Piano Continuation. ISMIR 2025 - MIREX with Christian Zhou-Zheng, John Backsund, Alex Coventry, Avid Eslami, Jyotin Goel, Xingwen Han, Danysh Soomro, Galen Wei [arxiv]

09/2025

Projects

Finding the complex permittivity as a function of energy using angular straggling Experimental proposal · CERN Beamline for Schools 2026 A Geant4 simulation project for studying particle interactions and analysis workflows for the proposed beam experiment. [Proposal] [GitHub]

2026

Magnetic Field of Cylindrical Axially Magnetized Ring Simulates and visualizes the magnetic field of an axially magnetized cylindrical ring using the Biot–Savart law. [GitHub]

2024

Chaotic Behavior of Double Pendulum Numerically simulates double-pendulum dynamics with coupled nonlinear equations and Runge–Kutta integration. [GitHub]

2024

EPECscan A deep-learning screening model that detects EPEC bacteria and classifies their growth stage from microscopic water samples. [GitHub]

2024