5 papers
Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
Paul Hyunbin Cho, Jinhyuk Jang, SeokYoung Lee +7
Diffusion-based lip synchronization models achieve strong visual quality and audio-visual alignment, but full-sequence bidirectional attention and many denoising steps make them im…
KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks
Yongwoo Kim, Sojung An, Yunjin Park +8
Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision. Current MLLM safety evaluat…
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
Dasol Choi, Eugenia Kim, Jaewon Noh +14
Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's a…
Responsible AI Technical Report
KT, :, Yunjin Park +17
KT developed a Responsible AI (RAI) assessment methodology and risk mitigation technologies to ensure the safety and reliability of AI services. By analyzing the Basic Act on AI im…
Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT
Wonhyuk Lee, Youngchol Kim, Yunjin Park +3
We introduce Guard Vector, a safety task vector computed as the parameter difference between a guardrail model (Guard Model) and a same-architecture pretrained language model. Comp…