Zhiying Leng

Zhiying Leng

Auto-generated profile, based on publicly available information

Zhiying Leng

Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 November 2024
Verified
Book Chapter
Closed access
PDF file
BFBowen Fu
Bowen Fu
GWGu Wang
Gu Wang
CZChenyangguang Zhang
Chenyangguang Zhang
YDYan Di
Yan Di
ZHZiqin Huang
Ziqin Huang
FTFederico Tombari
Federico Tombari

11 July 2025 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YWYin Wang
Yin Wang
MLMu Li
Mu Li
ZLZhiying Leng
Zhiying Leng
Frederick W. B. LiFrederick W. B. Li
Frederick W. B. Li
XLXiaohui Liang
Xiaohui Liang
We introduce MOST, a novel MOtion diffuSion model via Temporal clip Banzhaf interaction, aimed at addressing the persistent challenge of generating human motion from rare language prompts. While previous approaches struggle with coarse-grained matching and overlook important semantic cues due to motion redundancy, our key insight lies in leveraging fine-grained clip relationships to mitigate these issues. MOST’s retrieval stage presents the first formulation of its kind - temporal clip Banzhaf interaction - which precisely quantifies textual-motion coherence at the clip level. This facilitates direct, fine-grained text-to-motion clip matching and eliminates prevalent redundancy. In the generation stage, a motion prompt module effectively utilizes retrieved motion clips to produce semantically consistent movements. Extensive evaluations confirm that MOST achieves state-of-the-art text-to-motion retrieval and generation performance by comprehensively addressing previous challenges, as demonstrated through quantitative and qualitative results highlighting its effectiveness, especially for rare prompts.

30 March 2026 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YWYin Wang
Yin Wang
ZLZhiying Leng
Zhiying Leng
HLHaitian Liu
Haitian Liu
FLFrederick W. B. Li
Frederick W. B. Li
MLMu Li
Mu Li
XLXiaohui Liang
Xiaohui Liang
Scenes are continuously undergoing dynamic changes in the real world. However, existing human–scene interaction generation methods typically treat the scene as static, which deviates from reality. Inspired by world models, we introduce Dyn-HSI, the first cognitive architecture for dynamic human-scene interaction, which endows virtual humans with three humanoid components. (1) Vision (human eyes): we equip the virtual human with a Dynamic Scene-Aware Navigation, which continuously perceives changes in the surrounding environment and adaptively predicts the next waypoint. (2) Memory (human brain): we equip the virtual human with a Hierarchical Experience Memory, which stores and updates experiential data accumulated during training. This allows the model to leverage prior knowledge during inference for context-aware motion priming, thereby enhancing both motion quality and generalization. (3) Control (human body): we equip the virtual human with Human–Scene Interaction Diffusion Model, which generates high-fidelity interaction motions conditioned on multimodal inputs. To evaluate performance in dynamic scenes, we extend the existing static human–scene interaction datasets to construct a dynamic benchmark, Dyn-Scenes. We conduct extensive qualitative and quantitative experiments to validate Dyn-HSI, showing that our method consistently outperforms existing approaches and generates high-quality human–scene interaction motions in both static and dynamic settings.

27 January 2026 in arXiv
Verified
Preprint
Open access
PDF file
YWYin Wang
Yin Wang
ZLZhiying Leng
Zhiying Leng
HLHaitian Liu
Haitian Liu
Frederick W. B. LiFrederick W. B. Li
Frederick W. B. Li
MLMu Li
Mu Li
XLXiaohui Liang
Xiaohui Liang
Scenes are continuously undergoing dynamic changes in the real world. However, existing human-scene interaction generation methods typically treat the scene as static, which deviates from reality. Inspired by world models, we introduce Dyn-HSI, the first cognitive architecture for dynamic human-scene interaction, which endows virtual humans with three humanoid components. (1)Vision (human eyes): we equip the virtual human with a Dynamic Scene-Aware Navigation, which continuously perceives changes in the surrounding environment and adaptively predicts the next waypoint. (2)Memory (human brain): we equip the virtual human with a Hierarchical Experience Memory, which stores and updates experiential data accumulated during training. This allows the model to leverage prior knowledge during inference for context-aware motion priming, thereby enhancing both motion quality and generalization. (3) Control (human body): we equip the virtual human with Human-Scene Interaction Diffusion Model, which generates high-fidelity interaction motions conditioned on multimodal inputs. To evaluate performance in dynamic scenes, we extend the existing static human-scene interaction datasets to construct a dynamic benchmark, Dyn-Scenes. We conduct extensive qualitative and quantitative experiments to validate Dyn-HSI, showing that our method consistently outperforms existing approaches and generates high-quality human-scene interaction motions in both static and dynamic settings.