4 papers
SKIMIX: Multi-Agent Harness-Time Scaling with Skill Mixture for Dynamic Harness Engineering
Jia Luo
AI agents increasingly rely on large skill libraries, but selecting, combining, and maintaining skills remains difficult. We propose SKIMIX, a multi-agent framework in which agents…
From Passive Video to Editable Experience: Physically Grounded Experience Synthesis for Embodied Intelligence
Jia Luo
The key bottleneck in embodied AI is not model architecture but data. Although billions of human manipulation videos exist online, robots cannot directly learn from them due to the…
From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience
Jia Luo
Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) planners, when confronting such…
Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
Zhichao Wu, Junyin Ye, Zhilong Zhang +6
While current embodied policies exhibit remarkable manipulation skills, their execution remains unsatisfactorily slow as they inherit the tardy pacing of human demonstrations. Exis…