Zhifei Li

Zhifei Li

Auto-generated profile, based on publicly available information

Zhifei Li

Renmin University of China, Beijing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 April 2026
Verified
Conference Paper
Open access
TXTian Xia
Tian Xia
ZMZiming Mao
Ziming Mao
JKJamison Kerney
Jamison Kerney
EJEthan J. Jackson
Ethan J. Jackson
ZLZhifei Li
Zhifei Li
ISIon Stoica
Ion Stoica

26 May 2026
Verified
Conference Paper
Open access
SLShu Liu
Shu Liu
MCMert Cemri
Mert Cemri
SAShubham Agarwal
Shubham Agarwal
AKAlexander Krentsel
Alexander Krentsel
ANAshwin Naren
Ashwin Naren
ISIon Stoica
Ion Stoica
LLM-driven evolutionary search is emerging as a powerful approach for discovering algorithms and designs, but existing frameworks are difficult to reuse, extend, and compare. We present SkyDiscover, a flexible, adaptive framework for AI-driven scientific and algorithmic discovery. SkyDiscover decomposes the discovery loop into four reusable components: Context Builder, Solution Generator, Evaluator, and Solution Selector, while exposing the control logic above them as a programmable interface. This modular design enables rapid experimentation and even supports adaptive designs where AI can adapt or even optimize the optimization process itself during search. We demonstrate SkyDiscover across more than 200 optimization tasks spanning mathematical optimization, systems design, algorithmic programming, and constrained image generation. Under fixed budgets and shared models, the adaptive algorithms implemented on top of SkyDiscover achieves the strongest open-source performance compared to OpenEvolve, ShinkaEvolve, and GEPA, and matches or exceeds AlphaEvolve on many tasks. A live demo further showcases end-to-end discovery with real-time monitoring, human-in-the-loop steering, and meta-optimization of the search process.

18 February 2025
Verified
Conference Paper
Open access
CBConnor Robert Bernard
Connor Robert Bernard
MFMelissa Fabros
Melissa Fabros
ZLZhifei Li
Zhifei Li
NNNarges Norouzi
Narges Norouzi
DGDaniel Garcia
Daniel Garcia
AFArmando Fox
Armando Fox
Checkpoint is a responsive, terminal-based assignment system designed to support faculty in teaching and assessing a broad scope of computer science topics with Capture-the-Flag (CTF) style challenges. Unlike existing CTF frameworks, where binary completion of a given task is the only metric for evaluation, Checkpoint enables students to receive partial credit and dynamic feedback as they complete tasks. Not only does this allow students to confirm they are on the right track, but it simultaneously provides detailed analytics to instructors about each student's progress as they complete the assignment. Presented by an in-browser terminal emulator neatly wrapped in a Docker image, Checkpoint is a versatile tool that can be implemented in a variety of Learning Management Systems (LMSs) with minimal effort. Instructors can easily define flags in a user-friendly configuration file with flag names mapped to optional feedback and regex patterns, which automatically mark flags as complete and render feedback to students within their terminal environment.