Search papers, labs, and topics across Lattice.
2
0
3
Proxy Policy Steering (PPS), an inference-time adaptation method that resolves the challenge of eliciting task-specific behavior from limited demonstrations without degrading their broad capabilities by training two lightweight proxy policies whose calibrated velocity-space difference steers the frozen base sampler.
SPEAR achieves a staggering 99.5% increase in click recall by aligning query rewrites with user intent, transforming e-commerce search effectiveness.
