KS
Kai Sheng
cs.AIcs.CLcs.ROcs.CVcs.GRcs.LG
On Valency
published · living versionsW_p9hchf5a·v1 · currentpublished
Ask to Evolve: A Unified Harness for Lifelong Embodied Navigation with Hybrid Action Space and Persistent Memory
with Liuyi Wang, Jinlong Li, Haojie Dai, Chengju Liu +1
1 version
Preprints & journals
8 papers in the corpus · 2026NavJev: Efficient Vision-Language Navigation via Action-Centric Visual Compression and Discriminative Action-Semantic Memory2609.34969v1 · Kai Sheng, Liuyi Wang, Jinlong Li et al.2026 · 0 citationsarXiv
DPed-VLN: A Benchmark for Socially Compliant Vision-and-Language Navigation in Dynamic Pedestrian Environments2609.21504v1 · Haojie Dai, Xiangyi Wang, Liuyi Wang et al.2026 · 0 citationsarXiv
KuaiRP Series Role-playing Models Technical Report2609.11127v1 · Yipeng Wang, Ziwei Zhang, Jiahui Zhang et al.2026 · 0 citationsarXiv
TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation2608.11236v1 · Jiahui Zhang, Ziwei Zhang, Yipeng Wang et al.2026 · 0 citationsarXiv
A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigation2607.09792v1 · Liuyi Wang, Kai Sheng, Zongtao He et al.2026 · 0 citationsarXiv
FAST: A Holistic Framework for Optimizing Memory-I/O, Computation, and Sampling in Temporal GNN Training2607.05095v1 · Yushu Cai, Qingrui Zhu, Lei Liu et al.2026 · 0 citationsarXiv
P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation2605.19634v1 · Kai Sheng, Liuyi Wang, Haojie Dai et al.2026 · 0 citationsarXiv
Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation2604.25318v1 · Lanshan He, Haozhou Pang, Qi Gan et al.2026 · 0 citationsarXiv
Career total: 8 works. 8 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.