3 papers
cs.CV2026
Attention-Scoped Guidance: Training-Free Spatial Control for Image Editing
Zeyan Li, Wei Zhou, Hadi Amirpour +3
Instruction-guided image editing should change what the instruction names and leave the rest of the image untouched. In dual classifier-free guidance (CFG), an editor combines two…
cs.CV2026
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
Panqi Yang, Haodong Jing, Jiahao Chao +5
Unified visual tokenization faces a fundamental trade-off between high-fidelity pixel reconstruction (spatial equivariance) and semantic abstraction (conceptual invariance). We att…
cs.CV2025
UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space
Panqi Yang, Haodong Jing, Nanning Zheng +1
In the field of human-object interaction (HOI), detection and generation are two dual tasks that have traditionally been addressed separately, hindering the development of comprehe…