2 papers
cs.AI2026
Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge
Xiaofeng Shi, Xiaosong Qiu, Wenxin Ma +6
Enterprise question answering requires models to acquire proprietary knowledge without discarding general capabilities. We present Wnuan, a three-stage pipeline that constructs tas…
cs.CV2025
DualCap: Enhancing Lightweight Image Captioning via Dual Retrieval with Similar Scenes Visual Prompts
Binbin Li, Guimiao Yang, Zisen Qi +2
Recent lightweight retrieval-augmented image caption models often utilize retrieved data solely as text prompts, thereby creating a semantic gap by leaving the original visual feat…