5 papers
When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation
Dongbin Na
A vision-language AI assistant returns its answer as a stream of generated tokens. Therefore, a safety guard that watches that answer has to keep up with the stream and stop a harm…
Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation
Dongbin Na
In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follows a common belief that step…
Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models
Dongbin Na, Chanwoo Kim, Soonbin Rho +3
This work addresses spatial question answering for service robots traversing long egocentric routes. Given a query such as "where can I find a dry cleaner on the way back home?", t…
Semantic Flip: Synthetic OOD Generation for Robust Refusal in Embodied Question Answering and Spatial Localization
Dongbin Na, Chanwoo Kim, Giyun Choi +1
Detecting unanswerable user queries remains essential for the reliable deployment of real-world embodied agents. However, modern vision-language models (VLMs) often generate overly…
Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting
Dasol Choi, Dongbin Na
With the explosive growth of deep learning applications and increasing privacy concerns, the right to be forgotten has become a critical requirement in various AI industries. For e…