Liu Liu

Instruction-following in robot manipulation can be rigorously tested with InstructMove, revealing the true capabilities of VLA models beyond visual cues.

PLoRA slashes decode latency for multi-LoRA serving by over 6x while using pooled memory and near-data processing, revolutionizing how we deploy specialized AI models.

DreamWAM achieves up to 75.47% accuracy in unseen scenarios, showcasing that structured future state representations can dramatically enhance action model performance beyond traditional RGB methods.

Achieving a 49% increase in success rate on out-of-distribution tasks, Faster-WAM redefines efficiency in future-aware robot manipulation models.

IGGT4D achieves unprecedented consistency in geometry-instance representation from streaming video, outperforming existing methods in dynamic scene understanding.

Encoding individual consumer preferences in tabular foundation models can outperform traditional Bayesian methods by 8% in predictive accuracy and run 16 times faster.

Explicitly coupling geometry and appearance can dramatically enhance the robustness of 3D reconstruction against pose drift in long sequences.

Achieving a staggering 96.5% human acceptance rate, EmbodiedGen V2 transforms how we create and utilize 3D environments for embodied AI training.