Yilin Wu

“WEAVER achieves a Pearson correlation of ρ=0.870 between simulated and real-world success rates... finetuning on synthetic data closely matches that on real data, with only a 4% average performance gap”

“WEAVER is about 20× faster than Ctrl-World inference pipeline on an RTX A6000 Ada GPU, and batched sampling scales sublinearly with the number of candidates, showing that our inference optimizations make world-model-based test-time planning practical for real-time manipulation”

“Also first author on a 2025 RSS paper on VLM-in-the-loop policy steering via latent alignment — directly adjacent work on using learned representations for robot planning.”