Jun Li

Achieving 96% decision precision in leak localization transforms how utilities can confidently deploy resources, minimizing unnecessary excavations.

Pipelined Gradient Coding cuts training time significantly while ensuring faster convergence, even in the presence of straggling workers.

Adaptive modulation in RIS-assisted federated learning can drastically improve convergence speed and accuracy, even in challenging wireless environments.

Completing incomplete ECGs can restore diagnostic performance to near-complete levels, unlocking the potential of vast clinical archives for AI applications.

GP-DUN not only removes haze but also reconstructs fine details that traditional methods fail to recover, setting a new benchmark for UAV image clarity.

Roken can generate coordinated multi-robot trajectories in real-time, achieving higher success rates than traditional sequential planning methods.

Earth-OneVision unifies six sensor modalities into a single model, achieving superior performance with only 2B parameters compared to larger counterparts.

Apparent SOTA gains in semi-supervised 3D medical image segmentation may be illusory, driven by confirmation bias and test-set overfitting, not genuine progress.

Frozen vision-language models can dramatically improve abnormality grounding in rare disease imaging by iteratively refining decisions through optimized instructions and visual perturbations.

Text-to-image diffusion models leak backdoor secrets under cross-attention scaling, revealing a surprising divergence between benign and poisoned inputs.