2 papers
cs.LG2026
From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
Shuchang Ye, Jinqiang Yu, Zhujun Xiao +6
Industry-scale video and live-streaming moderation imposes requirements that are difficult to satisfy with generic pretrained public models or external APIs, including adaptation t…
cs.AI2026
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing
Jiacheng Zhang, Haoyu He, Sen Zhang +5
In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on prede…