A VLA policy with auxiliary success/progress heads and AWR+RECAP-style RL finished 1st in the LeHome 2026 simulation round and 2nd on the real robot.
Improving the Sensitivity of Online Controlled Experi- ments by Utilizing Pre-Experiment Data
5 Pith papers cite this work, alongside 218 external citations. Polarity classification is still indexing.
5
Pith papers citing it
218
external citations · external index
years
2026 5representative citing papers
The Latency-Elastic Trust Window is a telemetry-driven UX governor that maps network latency conditions to adaptive feedback modes to preserve trust and engagement during real-time payments in WebRTC streaming.
Including LLM predictions as covariates in standard regression adjustment for randomized experiments reduces variance with a do-no-harm property that reverts to the unadjusted estimator when predictions are uninformative.
Post-stratification plus CUPED cuts required traffic by about 45% for reliable A/B tests on heavy-tailed revenue metrics in ranking experiments.
citing papers explorer
-
Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
A VLA policy with auxiliary success/progress heads and AWR+RECAP-style RL finished 1st in the LeHome 2026 simulation round and 2nd on the real robot.
-
Discovering the Latency-Elastic Trust Window: A Patentable UX Governor for Real-Time Payment Confirmation in WebRTC Streaming
The Latency-Elastic Trust Window is a telemetry-driven UX governor that maps network latency conditions to adaptive feedback modes to preserve trust and engagement during real-time payments in WebRTC streaming.
-
AI-Assisted Variance Reduction in Randomized Experiments
Including LLM predictions as covariates in standard regression adjustment for randomized experiments reduces variance with a do-no-harm property that reverts to the unadjusted estimator when predictions are uninformative.
-
Variance Reduction for Heavy-Tailed Monetization Metrics in Ranking Experiments via Post-Stratification
Post-stratification plus CUPED cuts required traffic by about 45% for reliable A/B tests on heavy-tailed revenue metrics in ranking experiments.
- A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods