exevrm-video-reward-modeling

【效率与协作】Build robust reward models for computer-use agents by processing execution videos with spatiotemporal token pruning (STP+TTP) to remove redundancy while preserving task-relevant UI details. Achieve 84.7% accuracy with adversarial instruction translation.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准