Haoran Chen

ComPrivDet is an efficient object detection method that detects privacy objects in compressed video streams by reusing inference results from I-frames, significantly reducing latency and computational overhead.

The paper introduces Behavioral Canaries, a novel auditing mechanism that detects unauthorized use of private retrieved context data during Reinforcement Learning Fine-Tuning (RLFT) by inducing detectable stylistic behavioral changes.

This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system damage is avoided.

GLOVES is a flow-based adaptation method that selectively corrects non-expert robot actions by guiding them toward a task-specific expert action distribution, thereby improving performance while maintaining agent autonomy.