The Alignment Problem: Reward, Values, and Policy
Why I think reward always carries assumptions, and why AI systems should remain uncertain and correctable.
Read articlePhysics · Generative Models · 3D/4D Vision · Physical AI
Physics undergraduate at Sun Yat-sen University interested in generative models, 3D/4D vision, and Physical AI, especially reliable, low-latency reconstruction of dynamic physical states from limited visual evidence.
I want to build visual models that recover a usable 3D/4D state from sparse observations, generate only where evidence is missing, expose what remains uncertain, and spend additional computation where it produces a measurable correction.
Why I think reward always carries assumptions, and why AI systems should remain uncertain and correctable.
Read articleA first-principles look at the W2SD hypothesis, an analytic counterexample, and a small SDXL reproduction.
Read articleMajor in Physics
Sun Yat-sen University
Sept. 2024–Present
Expected June 2028 · Shenzhen
First Prize, 2nd “Illuminating the Future” Optics Science Communication Writing Competition
UCAS Education Foundation / Wiley · “Chirped Pulse Amplification: Born from Playing with Fire”
USACO Gold
Spring 2026