13 papers
LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments
Pei Liu, Nan Zheng, Lang Zhang +8
World Action Models (WAMs) have emerged as a powerful paradigm for embodied intelligence, yet the prevailing reliance on pixel-level video generation creates a fundamental bottlene…
LUNA-AD: Lightweight Uncertainty-Aware Language Model with Lifelong Learning for Autonomous Driving
Ruoyu Yao, Pei Liu, Ruiguo Zhong +3
While large language models (LLMs) offer promising reasoning capabilities, their integration into safety-critical driving systems is hindered by limited reasoning diversity, high c…
Bridging Predictive Uncertainty and Safe Action: Sample-Conditioned Differentiable Planning for Autonomous Driving
Chengzhen Meng, Pei Liu, Zhiyu Huang +2
Complex, dynamic, and interactive driving environments pose significant challenges for autonomous driving, primarily due to the pervasive uncertainty of surrounding traffic. A fund…
Decision-Making with Lightweight Confidence-Aware Language Model for Autonomous Driving
Ruoyu Yao, Ruiguo Zhong, Pei Liu +3
Large Language Models (LLMs) and Multimodal LLMs (MLLMs) have demonstrated immense potential in autonomous driving (AD) by offering human-like reasoning and open-world generalizati…
Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
Hongzhi Ruan, Pei Liu, Weiliang Ma +5
Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to an…
Bridging the Modality Bottleneck in Pathology MIL through Virtual Molecular Staining
Yucheng Xing, Pei Liu, Jingying Ma +6
Multiple instance learning (MIL) is the dominant framework for whole-slide image analysis in computational pathology, typically combining a frozen patch encoder, a projection layer…