Learning Robust Models for Multi-Source Gravitational-Wave Analysis
A workshop talk at NUS on learning the aggregate Galactic foreground for noise calibration and multi-source inference.
A workshop talk at NUS on learning the aggregate Galactic foreground for noise calibration and multi-source inference.
A plenary presentation on behalf of the Taiji Scientific Collaboration, covering mission development, data-analysis readiness, and future network science.
A five-minute nomination presentation outlining experience and ideas for early-career participation in LISA data-analysis research.
A GWFREERIDE flash talk on evolutionary search, Evo-MCTS, and reinforcement learning for gravitational-wave data analysis.
Studies a neural-network method that denoises massive-black-hole-binary signals while predicting their merger times.
Applies continuous normalizing flows and flow matching to posterior estimation for merging massive black hole binaries.
Tests deep-learning extraction of massive-black-hole-binary signals in data affected by gaps, glitches, and changing noise correlations.
Explores flow-matching posterior estimation for extreme-mass-ratio inspirals with a high-dimensional source parameter space.
Reviews the scientific data-processing challenges of space-based gravitational-wave missions and the possible roles of artificial intelligence.
International Workshop on Intelligent Computing in Astronomy 'Computing Senses Cosmos' (2023) @Zhejiang Lab, Hangzhou, China…