Zijian Xu — accepted AI-conference papers

2026

Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning

Sixian Zhang, Yiyao Wang, Xinhang Song, Keming Zhang, Zijian Xu, Shuqiang Jiang

CVPR 2026

Understanding the geometric and semantic structure of environments is essential for embodied agents. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics,and lack a native interface for large models, thus requiring additional training of feature projection

Cited by 0 Source ↗Scholar ↗

2023

A fast heuristic to optimize time-space tradeoff for large models

Akifumi Imanishi, Zijian Xu, Masayuki Takagi, Sixue Wang, Emilio Castillo

NeurIPS 2023poster

Training large-scale neural networks is heavily constrained by GPU memory. In order to circumvent this limitation, gradient checkpointing, or recomputation is a powerful technique. There is active research in this area with methods such as Checkmake or Moccasin. However, both Checkmate and Moccasin…

Cited by 1 Source ↗PDF ↗Scholar ↗