Jiaming Liu

The data pyramid framework reveals how the interplay of diverse data sources can unlock new capabilities in embodied agents, highlighting critical gaps in current methodologies.

Naive matching in diffusion distillation can inadvertently amplify errors due to hidden information in teacher models, leading to a surprising failure mode called Negative Branch Asymmetry.

Achieving over 10% improvement in manipulation success rates, Lift3D-VLA redefines the integration of 3D geometry and action generation in robotic systems.

Generators can dramatically improve their performance on long-tailed visual requests by leveraging a teach-then-search co-training approach, overcoming a critical knowledge boundary.

Current quantum machine learning models fall short of classical counterparts in key performance metrics, but they show promise in noise reduction and false positive management.

LaST-HD achieves over 90% accuracy in robot manipulation tasks using just 20 minutes of low-cost human demonstration data, revolutionizing how robots learn from human actions.

Ling-2.6 and Ring-2.6 achieve unprecedented efficiency in agentic intelligence, enabling instant responses and deep reasoning at trillion-parameter scale.

Squeeze up to 50 distinct image editing effects, plus few-shot generation, into a single LoRA without sacrificing quality.

Forget static imitation learning: LaST-R1 unlocks near-perfect robotic manipulation (99.8% success) by adaptively reasoning about physical dynamics *before* acting, then refining with RL.

Forget expensive real-world robot training: Hi-WM lets humans directly edit a robot's simulated reality, turning world models into powerful, reusable playgrounds for failure recovery.