3 papers
cs.AI2026
When and How Order-Flow Interventions Work After Dealers Adapt
Guanghao Wu, Zhuo Cai, Zhidong Li +1
Learning dealer agents can settle on persistently wide quotes, raising what customers pay to trade. A venue can route more orders to tighter quotes, but a wide quote may reflect re…
cs.IR2026
Generate What You Can Trust: Content Credibility in Generative Recommenders
Zhuo Cai, Guanghao Wu, Shoujin Wang +2
Generative recommendation (GR) represents items with semantic IDs (i.e., discrete token sequences) and generates target item tokens as recommendations. Despite its promising result…
cs.CV2026
PSMP-CLIP: Patch-Prompt SAM and Multi-Semantic Prompting for CLIP-Based Zero-Shot Anomaly Detection
Xuezhi Xiang, Guanghao Wu, Heqi Xiang +4
Zero-shot anomaly detection aims to localize anomalies without target-domain samples. Existing CLIP-based methods suffer from coarse anomaly maps and limited semantic prompts. We p…