Xiang Gao

VIC-RAGENT achieves up to 1.7x higher F1-scores in detecting vulnerability-inducing commits, revolutionizing how we approach software security.

AgentX can autonomously iterate on recommendation algorithms, outpacing human-driven processes and fundamentally changing how we approach system development.

Token-oriented inference optimizations can cut production costs and boost efficiency, transforming large model services from merely callable to fully operable.

ReMP slashes reconfiguration downtime from minutes to mere seconds, revolutionizing how LLMs adapt to fluctuating workloads.

Achieving higher-resolution visual anagrams with enhanced aesthetic quality and faster generation speeds could revolutionize digital art creation.

TEASR achieves seamless any-step sampling and outperforms traditional methods, all while eliminating the need for bulky auxiliary models.

MIXGUARD achieves robust privacy protection in split learning without sacrificing model utility, outperforming existing defenses against advanced data reconstruction attacks.

Current AI agents struggle with long-horizon professional tasks, achieving only 30% success in complex GUI workflows, revealing critical gaps in their capabilities.

LLM conformity isn't just about sycophancy; it's also significantly driven by a model's own uncertainty, opening new avenues for targeted interventions.

Overcome the chaos of classroom behavior recognition with ALC-YOLOv8s, achieving state-of-the-art detection of dense, occluded, and imbalanced student actions.

Open-source library vulnerabilities are easier to spot when you connect the dots between bug reports, code changes, and commit messages.