6 papers
Spherical Latent Motion Prior for Physics-Based Simulated Humanoid Control
Jing Tan, Weisheng Xu, Xiangrui Jiang +11
Learning motion priors for physics-based humanoid control is an active research topic. Existing approaches mainly include variational autoencoders (VAE) and adversarial motion prio…
SynMind: Reducing Semantic Hallucination in fMRI-Based Image Reconstruction
Lan Yang, Minghan Yang, Ke Li +3
Recent advances in fMRI-based image reconstruction have achieved remarkable photo-realistic fidelity. Yet, a persistent limitation remains: while reconstructed images often appear…
PerfGuard: A Performance-Aware Agent for Visual Content Generation
Zhipeng Chen, Zhongrui Zhang, Chao Zhang +5
The advancement of Large Language Model (LLM)-powered agents has enabled automated task processing through reasoning and tool invocation capabilities. However, existing frameworks…
4-Doodle: Text to 3D Sketches that Move!
Hao Chen, Jiaqi Wang, Yonggang Qi +3
We present a novel task: text-to-3D sketch animation, which aims to bring freeform sketches to life in dynamic 3D space. Unlike prior works focused on photorealistic content genera…
Amadeus: Autoregressive Model with Bidirectional Attribute Modelling for Symbolic Music
Hongju Su, Ke Li, Lan Yang +2
Existing state-of-the-art symbolic music generation models predominantly adopt autoregressive or hierarchical autoregressive architectures, modelling symbolic music as a sequence o…
VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis
Zhipeng Chen, Lan Yang, Yonggang Qi +4
Despite the rapid advancements in text-to-image (T2I) synthesis, enabling precise visual control remains a significant challenge. Existing works attempted to incorporate multi-face…