Weixian Xu

Third-year Undergraduate

ACM Honors Class

Shanghai Jiao Tong University

GAIR Lab

About Me

I am Weixian Xu, a third-year undergraduate at the ACM Honors Class, Shanghai Jiao Tong University. Currently, I am a research intern at GAIR Lab, supervised by Prof. Pengfei Liu.

My research philosophy is grounded in the belief that AI should evolve from static tools into dynamic partners. While I possess a strong background in systems programming (OS & Compilers) and Neural Architecture Search, my current focus is on building systems capable of interactive evolution—learning and adapting continuously through long-term human interaction.

Research Focus

My research pursues the vision of Self-Evolving AI. I identify the critical limitations in current models as the lack of sustained self-improvement and long-horizon reliability.

To address this, my work proceeds on two fronts:

Internal Architecture: Refining the learning objectives and memory mechanisms of individual models to enable continuous growth.
System Strategy: Engineering multi-agent ecosystems where models collaborate and optimize via complex interaction protocols.

Ultimately, I aim to empower human-centric models that utilize affective understanding to deeply align with user preferences over time.

Current Projects

ASI-Arch: Autonomous Neural Architecture Discovery

Research Project (GAIR Lab) | Paper | Code (1.1k Stars)

An autonomous AI system designed to conduct neural architecture discovery and reveal new design patterns without human intervention.

Impact: The repository garnered 1.1k+ stars within a month of publication.
Contribution: Designed the autonomous discovery pipeline, orchestrated 1,773 large-scale experiments, and validated 105 state-of-the-art architectures.

ACore: Operating System Kernel

System Implementation | Code

A comprehensive OS kernel exploring core operating system concepts through independent development in Rust.

Implemented memory management with virtual memory and page allocation.
Developed process scheduling, thread management, and a VFS layer supporting multiple filesystems.
Engineered user/kernel space isolation for security.

Imxc: Advanced Compiler

System Implementation | Code

A full-featured compiler for a C-like language (Mx*), achieving performance comparable to Clang.

Implemented advanced optimizations including Mem2Reg, Function Inlining, SCCP, and ADCE.
Designed a high-performance Register Allocation module using Graph Coloring.
Supported incremental compilation for efficient multi-file builds.

RISC-V CPU (Tomasulo Architecture)

Hardware Implementation | Code

A sophisticated RISC-V processor core implementation in Verilog.

Features Tomasulo architecture for dynamic instruction scheduling and out-of-order execution.
Supports the complete RV32I instruction set with FPGA deployment capabilities.

Technical Background

Research: Python, PyTorch, Transformers, CUDA, Continual Learning, Neural Architecture Search.
Systems: Rust, C++, C, Verilog, OS Development, Compiler Design.
Infrastructure: Linux, Docker, Git, CI/CD.

Personal Interests

Beyond research and coding, music is a big part of my life. I play both acoustic and electric guitar, and I hold a Grade 9 certification in Clarinet. I also enjoy playing badminton to stay active and exploring video games for their storytelling and mechanics. Back in high school, I was a competitive physics student (CPhO Provincial Second Prize), which shaped my analytical thinking.

On a more personal note, I am happily in a relationship and value the time spent exploring life’s journey with my partner.

Contact

I am always open to discussing AI evolution, memory mechanisms, systems engineering, or potential collaborations.

Email: hz.czar@sjtu.edu.cn
GitHub: @HZxCzar

selected publications

arXiv
AlphaGo Moment for Model Architecture Discovery

Yixiu Liu, Yang Nan, Weixian Xu, and 4 more authors

arXiv preprint arXiv:2507.18074, Jul 2025

Abs DOI Bib

While AI systems demonstrate exponentially improving capabilities, the pace of AI research itself remains linearly bounded by human cognitive capacity, creating an increasingly severe development bottleneck. We present ASI-Arch, the first demonstration of Artificial Superintelligence for AI research (ASI4AI) in the critical domain of neural architecture discovery–a fully autonomous system that shatters this fundamental constraint by enabling AI to conduct its own architectural innovation. Moving beyond traditional Neural Architecture Search (NAS), which is fundamentally limited to exploring human-defined spaces, we introduce a paradigm shift from automated optimization to automated innovation. ASI-Arch can conduct end-to-end scientific research in the domain of architecture discovery, autonomously hypothesizing novel architectural concepts, implementing them as executable code, training and empirically validating their performance through rigorous experimentation and past experience. ASI-Arch conducted 1,773 autonomous experiments over 20,000 GPU hours, culminating in the discovery of 106 innovative, state-of-the-art (SOTA) linear attention architectures. Like AlphaGo’s Move 37 that revealed unexpected strategic insights invisible to human players, our AI-discovered architectures demonstrate emergent design principles that systematically surpass human-designed baselines and illuminate previously unknown pathways for architectural innovation. Crucially, we establish the first empirical scaling law for scientific discovery itself–demonstrating that architectural breakthroughs can be scaled computationally, transforming research progress from a human-limited to a computation-scalable process. We provide comprehensive analysis of the emergent design patterns and autonomous research capabilities that enabled these breakthroughs, establishing a blueprint for self-accelerating AI systems.
@article{liu2025alphago, title = {AlphaGo Moment for Model Architecture Discovery}, author = {Liu, Yixiu and Nan, Yang and Xu, Weixian and Hu, Xiangkun and Ye, Lyumanshan and Qin, Zhen and Liu, Pengfei}, journal = {arXiv preprint arXiv:2507.18074}, year = {2025}, month = jul, url = {https://arxiv.org/abs/2507.18074}, doi = {10.48550/arXiv.2507.18074}, }