3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work proposes Visual Contrastive Self-Distillation, namely VCSD, which converts image-content removal into an on-policy self-distillation signal, and consistently outperforms matched OPSD across Qwen3-VL and Qwen3.5 models.
LongPIBench is introduced, a long-context benchmark for prompt injection covering 4 realistic application scenarios: paper peer review, resume screening, code review, and email summary, and the evaluation results reveal significant vulnerabilities of prompt injection defenses under long-context settings.
ContextLeak is developed, a malicious tool attack that induces the agent to both select the tool and disclose its context as input arguments, and significantly outperforms existing malicious tool attacks when adapted to this setting.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
