Kai Sheng

Real-time embodied navigation no longer requires slow autoregressive MLLM rollouts at every timestep: compressing candidate waypoints into discriminative semantic tokens enables sub-second decisions on continuous navigation benchmarks with zero loss in task success.

Experimental results demonstrate that the KuaiRP models not only match the current state-of-the-art proprietary models in role-playing fidelity within the authors' target domains, but also successfully recover general agent capabilities, maintaining extremely low deployment costs.

Achieving up to 4.7x speedup in TGNN training without sacrificing accuracy could redefine performance benchmarks in dynamic graph applications.

Forget tedious manual workflows: LLMs can now autonomously generate editable, engine-native 3D cutscenes by intelligently orchestrating animation, cinematography, and sound design.