Man Yuan

Achieving superior performance with one-third the resources, Qwen3.8-Flash-Next redefines efficiency in large-scale language models.

EDA not only corrects the current memory write but also actively removes outdated information, leading to superior performance in long-context scenarios.

Achieve real-time, high-accuracy LiDAR-visual-inertial odometry by ditching marginalization for a pose-only bundle adjustment, outperforming existing methods on extensive datasets.