SLAC's LCLS-II is rapidly advancing towards MHz repetition rate attosecond X-ray pulses, opening new opportunities to leverage the abundance of data in combination with advances in machine learning (ML) to better align the x-ray source with specific experimental goals. We approach the challenge from both ends of the facility. Starting at the X-ray output, we showcase our low latency, high throughput ML algorithms implemented at-the-edge for X-ray detection and reconstruction in the Multi-Resolution 'Cookiebox' (MRCO) angle resolved electron spectrometer with its 16 electron time-of-flight detectors. MRCO performs spectro-temporal characterization of X-ray profiles with a resolution that allows single shot identification of well-seeded shots versus SASE background at MHz rate. MRCO enables fast feedback, so we also tackle the problem as a control issue, focusing on programmable photoinjector laser shaping to adjust the initial electron bunch. Towards this end of using advances in ML to explore the parameter space for optimizing X-ray production, we present our progress towards a digital twin linking the photoinjector laser all the way through MRCO in the endstation diagnostics.

High-power attosecond X-ray pulses are ideal probes of ultrafast nonlinear interactions in quantum systems. We demonstrate the production of soft X-ray pulses with terawatt-scale peak powers and few hundred attosecond pulse durations in a two-stage cascaded X-ray free-electron laser. We diagnose the pulse properties in the time domain with angular streaking. Our results exceed the peak power of previous state-of-the-art attosecond XFELs by an order of magnitude. Furthermore, our data provides strong evidence of operation in the soliton-like superradiant regime of the free-electron laser at X-ray wavelengths.

SLAC's LCLS-II is rapidly advancing towards MHz repetition rate attosecond X-ray pulses, opening new opportunities to leverage the abundance of data in combination with advances in machine learning (ML) to better align the x-ray source with specific experimental goals. We approach the challenge from both ends of the facility. Starting at the X-ray output, we showcase our low latency, high throughput ML algorithms implemented at-the-edge for X-ray detection and reconstruction in the Multi-Resolution 'Cookiebox' (MRCO) angle resolved electron spectrometer with its 16 electron time-of-flight detectors. MRCO performs spectro-temporal characterization of X-ray profiles with a resolution that allows single shot identification of well-seeded shots versus SASE background at MHz rate. MRCO enables fast feedback, so we also tackle the problem as a control issue, focusing on programmable photoinjector laser shaping to adjust the initial electron bunch. Towards this end of using advances in ML to explore the parameter space for optimizing X-ray production, we present our progress towards a digital twin linking the photoinjector laser all the way through MRCO in the endstation diagnostics.