Xin Jiang

Existing AI-generated image detectors falter dramatically, with accuracy plummeting from 91-96% to as low as 54-66% when faced with realistic manipulations.

Scaling AEB systems with massive unlabeled data can lead to a 35% increase in accident-free driving mileage while maintaining a positive-to-false activation ratio over 100:1.

An automated annotation system for rare AEB events boosts recall by 80% while slashing manual workload in half, paving the way for smarter vehicle safety systems.

Sinkhorn-CPD achieves state-of-the-art point cloud registration accuracy while automatically handling outliers and partial overlaps without manual tuning.

TriMatch achieves superior correspondence discrimination by integrating geometric and semantic features, effectively tackling the issue of pseudo-consistent outliers in complex scenes.

YouZhi-LLM achieves unprecedented concurrency and accuracy in financial LLMs by dramatically reducing KV-cache overhead, setting a new standard for deployment efficiency.

LLMs can achieve state-of-the-art results on complex reasoning tasks with far fewer parameters by iteratively excavating and reasoning over external knowledge.