Skip to main content
Search

Feiran You

2 related articles

Subscribe to updates
  1. arXiv

    FARM replaces policy transfer with reward-space transfer, reaching a 29.8% late-stage gain on unseen Rate-Latency tasks

    The paper proposes FARM, a reward-space transfer framework that shifts cross-task knowledge reuse from policy space to trajectory-level decision evaluation: its Agentic Reward Model first learns a task-conditioned reward prior from heterogeneous source-task trajectories, then freezes it to guide adaptation of a target-specific controller for previously unseen tasks; on heterogeneous MEC tasks, FARM achieves a mean late-stage gain of 29.8% over Single-task SAC on unseen Rate-Latency targets, versus 16.1% for CRA Transfer, reaches a 46.2% gain on the moderate-OOD FAR-M case, and both Mamba and Transformer trajectory encoders support the transfer, with Mamba more robust as longer history dependencies are introduced.

  2. arXiv

    TwinJEPA adds offline-mined action-preference supervision to JEPA control, yielding positive benchmark-level mean differences across all matched state-based evaluations

    The work introduces TwinJEPA, which augments JEPA-based offline zero-shot control by identifying approximately matched states across offline trajectories and constructing preference pairs via goal-conditioned reward relabeling, then learning two training-only objectives, reward-gap regression and preference classification, to obtain action-preferred predictive representations; on long-horizon navigation and continuous-control benchmarks with state- and pixel-based observations, it yields positive benchmark-level mean differences across all matched state-based evaluations, with analyses indicating larger gains tend to arise when local action alternatives provide more informative outcome contrasts.

You’re all caught up