Experiments show that turn-level boundary supervision improves intervention localization, while reinforcement learning further improves the safety--utility trade-off.
Xin-Jie Shen, Rong-Zhe Wei, Pei-Zhi Niu et al.· 0 citations
This work forms attack and defense as partially observed state control in SEAD, deriving their design requirements from this shared execution process and constructs an environment-verifiable dataset integrating controlled initial states, replayable tool environments, and task-specific executable checks.
Xin-Jie Shen, Jun-Ran Wang, Rong-Zhe Wei et al.· 0 citations
AcFlow is introduced, an inference-time controller that transports intermediate layer image-token activations through a learned concept-conditioned velocity field while keeping the base DiT frozen, and supports the learned velocity field as an adaptive control mechanism.
Jun-Ran Wang, Ze-Hao Jin, Tian-Yu Luan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.