Author

Hong Zhang

h-index 5 View on Semantic Scholar

We have 3 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Graph3R: Unifying View Graph Initialization with Feed-Forward Reconstruction

Feed-forward reconstruction recovers camera poses and dense geometry from image sets whose views are assumed to come from a single scene. In practice, uncurated image collections often contain views from disjoint scenes, and reconstructing these views jointly can corrupt camera poses and geometry. Existing pipelines ty...

Jing-Wen Yu, Heng-Li Wang, Jian-Hao Jiao et al. · 0 citations

Jul 2026

Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generation

This work proposes an alternative approach: fine-tuning VLMs to learn navigation interactions directly in 2D pixel space through autoregressive trajectory generation, and demonstrates that this flagship model achieves state-of-the-art level performance with relatively limited computational resources and training data.

Changfei Fu, Guangcheng Chen, Aoxiang Gu et al. · arXiv.org · 0 citations

Jul 2026

HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation

HAM-VLN is presented, a decision-coupled, agent-authored memory that equips the robot with a persistent, depth-grounded world graph and reduces the context length by more than 65% compared to previous methods.

An Liu, Bingxi Liu, Hongyu Ding et al. · arXiv.org · 1 citation