activity
20242026
most citedToward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling

1 citations · 1 across the 1 of their papers we have counts for

collaborators

6 papers

cs.HC20261 cited

Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling

Feier Qin, Xiao Li, Yi Zheng +5

Recent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet most still remain unable to suppo…

cs.CV2025

IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting

Yuxin Zhang, Minyan Luo, Weiming Dong +6

The stories and characters that captivate us as we grow up shape unique fantasy worlds, with images serving as the primary medium for visually experiencing these realms. Personaliz…

cs.CL2024

DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning

Xun Guo, Shan Zhang, Yongxin He +4

Current techniques for detecting AI-generated text are largely confined to manual feature crafting and supervised binary classification paradigms. These methodologies typically lea…

cs.CV2024

Towards Unified 3D Hair Reconstruction from Single-View Portraits

Yujian Zheng, Yuda Qiu, Leyang Jin +5

Single-view 3D hair reconstruction is challenging, due to the wide range of shape variations among diverse hairstyles. Current state-of-the-art methods are specialized in recoverin…

cs.CV2024

VRMM: A Volumetric Relightable Morphable Head Model

Haotian Yang, Mingwu Zheng, Chongyang Ma +3

In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling. While recent volumetric prior mo…

cs.CV2024

Text-Driven Diverse Facial Texture Generation via Progressive Latent-Space Refinement

Chi Wang, Junming Huang, Rong Zhang +5

Automatic 3D facial texture generation has gained significant interest recently. Existing approaches may not support the traditional physically based rendering pipeline or rely on…