titlePReMind: When Personal Memory Meets Visual Hazards
authorsYeongtak Oh, Donghyeok Lee, Joonhee Oh, Jaewon Jeong, Sungroh Yoon
date2026-11-18
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.23808
affiliationSeoul National University
upvotes9 (Hugging Face Daily Papers, 2026-11-21)
linksabs pdf hf
cite
related4D Human-Scene Reconstruction from Low-Overlap Captures
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
Articulated Object Reconstruction from Rest-State Observation
ResearchMath-14K: Scaling Research-Level Mathematics via Agents
In-Distribution Forcing for Long Video Generation at Test Time
abstractPersonalized vision-language assistants use visual observations and personal memories to provide advice tailored to the user. When the observed scene contains a physical hazard, personal context, such as allergies, medical conditions, or mobility constraints, can change what help is appropriate. Responding appropriately therefore requires recognizing the visible hazard and applying the relevant person's information. We introduce PReMind-Bench, a diagnostic benchmark that evaluates this combination across diverse hazards and personal-memory conditions. It separately measures memory access, grounding, abstention, and hazard response, and assesses joint success on interdependency cases. Existing models often satisfy one requirement while failing the other, and training only for safety or personalization leaves a gap in joint success. We therefore propose PReMind, a two-phase reinforcement learning framework that combines on-demand and forced-call interactions (memory always retrieved) to jointly train grounded memory use and hazard response. At 4B, PReMind raises joint success from 12.9% to 28.6% over its base on the interdependency set and improves hazard adequacy and correct abstention on the main test. Joint-success gains persist under forced-call evaluation and under a second LLM judge across three Phase II seeds; averaged over these seeds, joint success also improves on unseen hazard groups. These findings highlight the need to evaluate and train personal assistants to connect visual evidence with the relevant person's context.

bibtex

@misc{oh2026premind,
  title={PReMind: When Personal Memory Meets Visual Hazards},
  author={Yeongtak Oh and Donghyeok Lee and Joonhee Oh and Jaewon Jeong and Sungroh Yoon},
  year={2026},
  eprint={2611.23808},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.23808}
}