Searcharxiv⌕ Search

arXiv subjects

Junrong Huang

Publications and source records attributed to Junrong Huang.

3 recordsLinked to original sources

Controllable Texture Tiling with Transformed RoPE-Enhanced Diffusion Models

Realistic integration of user-specified textures into scene images is a fundamental task in computer graphics and image editing. While existing material transfer and reference-guided inpainting methods can edit surface appearances, they often fail to address the specific requirements of texture tiling. This task necessitates precisely repeating a reference pattern according to user-defined parameters such as frequency, orientation, and scale. Furthermore, current generative approaches often struggle to maintain the structural fidelity of the reference texture, limited by either destructive pixel-level resampling or the lack of fine-grained spatial information in semantic image encoders, and they frequently fail to preserve the coherent lighting and geometry of the original scene. In this paper, we propose a novel framework for controllable and high-fidelity texture tiling based on Diffusion Transformers. Our approach introduces two key technical innovations to decouple spatial manipulation from content generation. First, we propose a Coordinate-Transformed Rotary Embedding mechanism. By applying 2D affine transformations directly to the relative positional embeddings between the target latent and the image condition, we achieve precise control over tiling patterns without explicit pixel warping, thereby utilizing the full information of the reference condition without degradation. Second, a Disjoint Attention Mask is employed to shield reference features from semantic leakage. This preserves structural integrity while seamlessly blending the synthesized texture with the scene's original lighting and geometry. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines in both control accuracy and texture fidelity.

cs.GR↗

Reconfigurable Dysprosium Isotope Mixtures with Selectable Quantum Statistics

Dipolar quantum mixtures offer new opportunities to explore many-body phenomena shaped by long-range anisotropic interactions, intercomponent coupling, and quantum statistics. Here we develop a reconfigurable platform for bosonic and fermionic dysprosium isotope mixtures using a single-isotope-like optical layout. We time-multiplex the 421-nm light to generate isotope-selective slow-atom fluxes, while spectrally engineered 626-nm light provides simultaneous common-path narrow-line cooling and trapping. By reconfiguring optical frequencies, we prepare seven isotope pairs spanning Bose--Bose, Bose--Fermi, and Fermi--Fermi combinations, with continuous population-balance control through the 421-nm dwell-time allocation. Systematic comparisons with sequence-matched single-isotope references, from magneto-optical-trap loading and compression to optical-dipole-trap transfer, reveal nearly single-isotope-like performance for most combinations. The larger deviations occur only for certain isotope pairs and preparation stages, with controlled measurements revealing optical sensitivities during loading and additional losses under high-density conditions. Our results make isotope composition and quantum statistics selectable within a strongly dipolar system while largely preserving single-isotope preparation simplicity and performance, opening new possibilities for exploring multicomponent dipolar quantum matter.

physics.atom-ph↗

Binary Dipolar Condensates of Dysprosium Isotopes with Tunable Spatial Order

Dipolar quantum mixtures provide a route to many-body phases in which long-range anisotropic interactions couple with density, composition and spatial order. Here we realize a new quantum-degenerate dipolar mixture of $^{162}$Dy and $^{164}$Dy in a single-species-like apparatus. The mixture combines nearly matched single-particle Hamiltonians, tunable interactions and composition parameters, and isotope-resolved characterization. Tuning the interaction balance and relative composition reorganizes the coupled condensates from a miscible state into core--shell-like, side-by-side, and exchanged core--shell-like immiscible configurations. These results establish dysprosium isotope mixtures as a compact and versatile platform for multicomponent dipolar quantum matter, ranging from impurity physics to binary supersolidity.

cond-mat.quant-gas↗