Daoyuan Wu
where else to find them
what they talk about
where they keep going back
no series more than once — all 2 in the filters
on a stage with
- Shuai Wang2×
- Dongwei Xiaoonce
- Juergen Rahmelonce
all 13 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| SelfDefend: LLMs Can Defend Themselves against Jailbreaking in... | USENIX Security '25 | 2025-08-13 |
SelfDefend implements a shadow LLM that runs in parallel to a target model to detect harmful intent, using two detection templates (direct and intent prompts)… | ||
| Divergence-Aware Testing of Graphics Shader Compiler Back-Ends | PLDI 2025 | 2025-06-16 |
ShaDiv generates shader tests that deliberately perturb control and data flow divergence to exercise backend optimizations, uses a divergence-aware generator… | ||
| nothing matches | ||