Author

Jiajun Cao

Observed names: Cao, Jiajun, Co, Peterson

Institution: Peking University

Observed institution: Peking University

OpenAlex ID: A5128772041

STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models

2026 · Guo, Yichen, Wang, Tinghao, et al. · arXiv (Cornell University)

Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning

2026 · Chen, Sixiang, Liu, Jiaming, et al. · arXiv (Cornell University)

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference

2026 · Wang, Tinghao, Guo, Yichen, et al. · arXiv (Cornell University)

VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models

2026 · Wang, Hao, Wei, Xiaobao, et al. · arXiv (Cornell University)

EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation

2026 · Cao, Jiajun, Zhang, Xiaoan, et al. · arXiv (Cornell University)

Works count: 5

Citation count:

H-index:

I10-index: