Skip to content

Author

Fuzhen Zhuang

We have 8 of 187 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.

#artificial intelligence Book Open access Sep 2026

HiTS-CL: A Continual Learning Framework for Long-Horizon Temporal Knowledge Graph Extrapolation

History-enhanced Two-Step Continual Learning (HiTS-CL), a backbone-agnostic continual learning framework for extrapolative TKGR that consistently improves extrapolation accuracy, reduces long-horizon degradation, and outperforms strong continual-learning baselines.

Yan-Song Liu, Rui Liu, Yuan Zuo et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Dual-Channel Robust Group-Relative Policy Optimization via Advantage and Sequence-Weight Estimation

RoVR-GSPO is introduced, a dual-channel robust optimizer that addresses group-relative policy optimization failure modes separately and shows consistent improvements over GSPO, while controlled perturbation studies demonstrate stronger robustness to reward contamination and token-ratio anomalies.

Zhong-Yi Li, Wan Tian, Xiang Xu et al. · 0 citations
Sep 2026

NaviScale: Generating Large-Scale Semantic Map Datasets for Object Navigation

NaviScale is proposed for semantic-map-based object navigation (ObjectNav), whose predictor can be trained on pairs of partial and complete semantic maps without reconstructing a complete 3D environment for every training sample.

Chuan-Lin Lan, Yan-Wei Zheng, Yu-Xin Jing et al. · 0 citations
Preprint Aug 2026

Unpaired Modality-Agnostic Generative Recommendation

UnpairGR is proposed, which learns a unified semantic-ID space from paired, image-only, and text-only observations, which confines modality-specific processing to lightweight input projections while sharing the subsequent Transformer and residual codebooks across all observation conditions.

Wei-Hao Shen, Wei Chen, Fu-Wei Zhang et al. · 0 citations
Preprint Aug 2026

WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training

WDL-OPD is introduced, a mixture-constrained co-training method with two trainable policies that shows that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$^2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express.

Ze-Hao Chen, Gong-Xun Li, Tianxiang Ai et al. · 0 citations
Aug 2026

Temporal knowledge graph reasoning via multi-granularity knowledge refinement

This work proposes a multi-granularity knowledge refinement approach to prune historical TKGs, which selectively removes irrelevant edges and unnecessary nodes at both the edge and node levels.

Fu-Wei Zhang, Fu-Zhen Zhuang, Zhao Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.