6 papers
PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement
Tianyidan Xie, Peiyu Wang, Yuyi Qian +7
Physics-aware symbolic simulation of 3D scenes is critical for robotics, embodied AI, and scientific computing, requiring models to understand natural language descriptions of phys…
A training-free framework for high-fidelity appearance transfer via diffusion transformers
Shengrong Gu, Ye Wang, Song Wu +4
Diffusion Transformers (DiTs) excel at generation, but their global self-attention makes controllable, reference-image-based editing a distinct challenge. Unlike U-Nets, naively in…
Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers
Ruidong Chen, Yancheng Bai, Xuanpu Zhang +6
Region-instructed layout control in text-to-image generation is highly practical, yet existing methods suffer from limitations: (i) training-based approaches inherit data bias and…
RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation
Yuwen Du, Anning Hu, Zichen Chao +6
Roadside Collaborative Perception refers to a system where multiple roadside units collaborate to pool their perceptual data, assisting vehicles in enhancing their environmental aw…
Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation
Tianyidan Xie, Rui Ma, Qian Wang +6
Recent advancements in image-conditioned image generation have demonstrated substantial progress. However, foreground-conditioned image generation remains underexplored, encounteri…
DP-Adapter: Dual-Pathway Adapter for Boosting Fidelity and Text Consistency in Customizable Human Image Generation
Ye Wang, Xuping Xie, Lanjun Wang +2
With the growing popularity of personalized human content creation and sharing, there is a rising demand for advanced techniques in customized human image generation. However, curr…