Zhe Zhang
Machine learning for real control rooms · SLAC
- Show everything
- Research only
- Projects only
- Design only
- Hand-picked order
- By start year, newest first
- By end year, ongoing first
- Alphabetical
- Flip the sort direction
- Light theme
- Dark theme
- Follow the system theme
- Open the résumé (PDF)
- Open GitHub
- Open LinkedIn
- Write an email
Badger
ML optimization for accelerator control rooms, adopted at 7+ facilities.
Otter
A Claude Code agent for the control room: it writes the tuning routine, you approve, Badger runs it.
DAMA-BAX & mpBAX
Storage-ring sextupole design learned one tracked particle at a time, with 40 times fewer tracking simulations than NSGA-II.
RAG chatbot for research groups
Plug-and-play research assistant, evaluated on every answer.
Teeport
Break the wall between optimization algorithms and problems.
MG-GPO
A Gaussian process decides which bred candidates the live SPEAR3 ring gets to measure.
RCDS-S
An optimizer for a drifting ring that only takes steps likely to stay under a line set in advance.
CoAD
Label-free anomaly detection from coincident signals across subsystems.
Single-shot policy
Straight from what the sensors see to the knob settings, trained without a single optimal action.
UED beam diagnostics with CNNs
A small CNN that reads each electron shot's pointing and energy jitter straight off its diffraction pattern.
ReconNN
One forward pass instead of 500 gradient steps, for neutrino event reconstruction.
quantecho
Self-hosted full-stack platform with a Python backtest lab.
BigWaves Pattern Inspector
What happens after the market drops? An event-study tool, live 12+ months.
Integrity Deck · 草木本心
54 cards designed with AI, shipped as one 84 KB page.
Mixed-reality surgical navigation
One CT scene in mixed reality, shared by every headset and registered to the body.
Photocathode & injector codes, etc.
A PhD asking how low a photocathode gun can push emittance, and the four codes it took.
Nothing matches “”. Press esc to clear, or type /all.