Pan Li

Breaking the privacy-utility bottleneck, DP-NGD achieves state-of-the-art accuracy and a 10x speedup in convergence for differentially private training.

Achieving up to 17.5% faster processing of long sequences, HCMS redefines efficiency in multi-head attention by enabling true parallelism.

A two-stage framework for mispronunciation detection in low-resource Arabic achieves a groundbreaking F1-score of 0.7201, outperforming previous methods by over 63%.

Achieving 98.6% tracking efficiency with a 0.8% fake rate, HEPTv2 revolutionizes particle tracking by eliminating the need for graph construction and auxiliary processing.

KVEraser achieves a 3-4x speedup over full recomputation while maintaining high performance in long-context tasks, revolutionizing how we handle context updates in LLMs.

Training on a handful of real-world defect examples plus synthetic data lets you spot entirely new kinds of 3D manufacturing flaws.

RL-trained LLM agents can get stuck in an "information self-locking" trap, failing to ask the right questions and internalize information, but a simple learning signal reallocation can break them out.