Chenyu Zhang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1Crypto×1
Research Timeline
2026
What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers
The paper proposes AHV-D&S, a novel training-free inference-time safeguard that detects and suppresses risky content in Diffusion Transformers (DiTs) by quantifying token sensitivity across attention heads.
Highlighted terms show continued research focus across papers