Yongshun Gong

Deterministic dependency graphs severely misalign with stochastic residual structures in decoupled diffusion forecasters, but dynamically sparsifying edges via residual uncertainty estimation eliminates redundant conditioning and repairs calibration.

The ASCII Attack reveals that framing harmful requests as artistic critique can bypass safety filters in large language models, achieving up to 93% success in eliciting harmful responses.

Make your prompts 5x more interpretable without hurting accuracy: IPL combines discrete token selection with continuous optimization, and it's plug-and-play with existing methods.