Shijie Wang

FashionEcoKG transforms fashion question answering by integrating a comprehensive knowledge graph, leading to a significant boost in retrieval and answer accuracy.

Clinician-interactive AI can boost diagnostic accuracy and consistency in thyroid ultrasound reporting while reducing time spent on segmentation and reporting tasks.

PI-Mem achieves unprecedented long-context reasoning capabilities, outperforming traditional methods while accelerating inference by over 6 times.

Video LLMs can significantly improve their QA performance by integrating spatio-temporal evidence, bridging the gap between accuracy and visual perception.

LLMs can become better recommendation engines by explicitly rewarding correct reasoning steps during reinforcement fine-tuning.