Jian Chen

Client-specific sufficiency estimation in FedSGA allows for more efficient federated learning, boosting performance while slashing unnecessary computation costs.

FlashDrive slashes VLA inference latency by 4.7x while maintaining accuracy, making real-time autonomous driving feasible with a single GPU.

NTCF achieves higher performance by adapting propagation depth to local connectivity, revealing that traditional methods may overlook critical node-specific dynamics.

Querying the right samples can reduce black-box MIA costs by over 80% without sacrificing accuracy.

Achieving 100x parameter efficiency, LoopWM redefines how we approach long-horizon world modeling by introducing iterative latent depth as a new scaling axis.

Lattice matching can make or break the quality of deuterium crystals, with optimal conditions yielding ultra-smooth, defect-free structures essential for fusion ignition.

Achieving robust patient-level predictions in pathology, AGE-MIL outperforms existing methods by effectively integrating evidence from multiple whole-slide images.

LLMs struggle with complex legal rules, often missing critical exceptions, but a new benchmark and structured representation can dramatically enhance their compliance accuracy.

Echo-DM achieves superior ultrasound marker removal while maintaining anatomical integrity, challenging the effectiveness of existing marker removal techniques.

A new 3D representation and BEV alignment framework drastically enhance the generalization of robotic manipulation policies across varied environments and robot types.