Song Wang

SAFEDREAM introduces a lightweight, external world-model framework that proactively detects multi-turn jailbreak attacks by modeling cumulative safety erosion and predicting early failure points.

The paper proposes a novel framework combining behavior-invariant task representation learning and a Transformer-based world model to achieve robust generalization in offline meta-reinforcement learning, particularly in sparse-reward settings.

This paper proposes a training-free framework called ReasonAlloc to mitigate inference bottlenecks in large language models by recasting decoding-time key-value compression as a hierarchical budget allocation problem.