arXiv subjects

Yixuan Han

Publications and source records attributed to Yixuan Han.

7 recordsLinked to original sources

arXiv2026

MoonSplat: Monocular Online Gaussian Splatting with Sim(3) Global Optimization

Online 3D reconstruction from monocular image sequences is a challenging and ongoing research topic. 3D Gaussian Splatting (3DGS), leveraging its high-quality real-time rendering capability, empowers online 3D reconstruction to represent dense scenes with enhanced expressiveness, and thus holds great promise for a wide range of applications such as robotics and AR/VR. However, existing online 3DGS methods still suffer from some key challenges: fragile camera pose estimation due to the lack of global optimization, and low optimization efficiency in large-scale or long-sequence scenarios. To address these issues, we propose a robust and efficient online voxelized 3DGS reconstruction framework integrated with global $\text{Sim}(3)$ optimization, which enables reliable camera tracking and efficient global loop closure for both camera poses and voxelized 3DGS. To accelerate the convergence of the voxelized 3DGS, we further introduce a color residual learning strategy, which not only boosts optimization speed but also enhances rendering quality. Extensive experiments on diverse indoor and outdoor datasets demonstrate that our method achieves state-of-the-art performance in both camera pose estimation accuracy and rendering quality, while retaining real-time efficiency. Additionally, we develop and deploy a real-world UAV-based active reconstruction system grounded on our proposed method, validating its robustness and generalizability for practical online 3D reconstruction tasks. Our code and data are available at https://github.com/TrickyGo/MoonSplat.

cs.CV↗

arXiv2026

ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo

Active scene reconstruction enables robots/UAVs to autonomously plan trajectories and reconstruct environments without costly manual data acquisition. Unlike passive methods, active reconstruction requires real-time construction of high-confidence occupancy maps for collision-free navigation. Existing approaches rely on depth sensors for occupancy map updates, increasing platform cost and weight. To advance spatial intelligence, we aim for a vision-only monocular solution. However, current monocular scene reconstruction methods operate offline and fail to deliver globally consistent dense depth at the frame rates required for robots/UAVs navigation. To bridge this gap, we introduce ActMVS, the first framework for monocular active reconstruction. Our framework integrates a view factor graph construction for informed Multi-View Stereo depth prediction, along with a global depth optimization, to enable the online generation of high-quality, globally consistent dense depth maps. This enables monocular robots/UAVs to maintain reliable occupancy maps for safe trajectory planning during reconstruction. Experiments on Replica datasets demonstrate performance competitive with RGB-D methods. Our code and data are available at https://github.com/TrickyGo/ActMVS.

cs.RO↗

arXiv2026

AnimeAdapter: A Modular Adapter for Appearance-Consistent Anime Character Generation

We present a lightweight appearance adapter for Stable Diffusion that enables controllable and consistent anime character generation under diverse editing conditions. Instead of relying on large-scale vision-language models or per-subject fine-tuning, our method injects fine-grained visual features from a single reference image into the diffusion process. Based on CLIP emergent local spatialization, we develop semantic-selective local attention. To further disentangle character appearance from spatial layout, we incorporate pose-aware conditioning during adapter training. The resulting pretrained adapter remains compact, modular, and fully compatible with Stable Diffusion community workflows, while requiring no additional fine-tuning at deployment time. Furthermore, we present a high-quality anime character dataset based on curated and restructured Danbooru prompts, and evaluate our method across several practical character editing scenarios. Our code, model weights, and dataset will be publicly released upon acceptance.

cs.CV↗

arXiv2025

Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time

Test-Time Scaling (TTS) enhances the reasoning ability of large language models (LLMs) by allocating additional computation during inference. However, existing approaches primarily rely on output-level sampling while overlooking the role of model architecture. In mainstream Mixture-of-Experts (MoE) LLMs, we observe that varying the number of activated experts yields complementary solution sets with stable accuracy, revealing a new and underexplored source of diversity. Motivated by this observation, we propose Dynamic Experts Search (DES), a TTS strategy that elevates expert activation into a controllable dimension of the search space. DES integrates two key components: (1) Dynamic MoE, which enables direct control of expert counts during inference to generate diverse reasoning trajectories without additional cost; and (2) Expert Configuration Inheritance, which preserves consistent expert counts within a reasoning path while varying them across runs, thereby balancing stability and diversity throughout the search. Extensive experiments across MoE architectures, verifiers and reasoning benchmarks (i.e., math, code and knowledge) demonstrate that DES reliably outperforms TTS baselines, enhancing accuracy and stability without additional cost. These results highlight DES as a practical and scalable form of architecture-aware TTS, illustrating how structural flexibility in modern LLMs can advance reasoning.

cs.AI↗

arXiv2024

Coexisting charge density waves in twisted bilayer NbSe2

Twisted bilayers of two-dimensional materials have emerged as a highly tunable platform for studying broken symmetry phases. While most interest has been focused on emergent states in systems whose constituent monolayers do not feature broken symmetry states, assembling monolayers that exhibit ordered states into twisted bilayers can also give rise to interesting phenomena. Here, we use large-scale first-principles density-functional theory calculations to study the atomic structure of twisted bilayer $\mathrm{{N}b{S}e_2}$ whose constituent monolayers feature a charge density wave. We find that different charge density wave states coexist in the ground state of the twisted bilayer: monolayer-like $3\times 3$ triangular and hexagonal charge density waves are observed in low-energy stacking regions, while stripe charge density waves are found in the domain walls surrounding the low-energy stacking regions. These predictions, which can be tested by scanning tunneling microscopy experiments, highlight the potential to create complex charge density wave ground states in twisted bilayer systems and can serve as a starting point for understanding superconductivity occurring at low temperatures.

cond-mat.mtrl-sci↗

arXiv2023

Atomically-precise Vacancy-assembled Quantum Antidots

Patterning antidots ("voids") into well-defined antidot lattices creates an intriguing class of artificial structures for the periodic modulation of 2D electron systems, leading to anomalous transport properties and exotic quantum phenomena as well as enabling the precise bandgap engineering of 2D materials to address technological bottleneck issues. However, realizing such atomic-scale quantum antidots (QADs) is infeasible by current nanolithographic techniques. Here, we report an atomically-precise bottom-up fabrication of a series of atomic-scale QADs with elegantly engineered quantum states through a controllable assembly of a chalcogenide single vacancy (SV) in 2D PtTe2, a type-II Dirac semimetal. Te SVs as atomic-scale "antidots" undergo thermal migration and assembly into highly-ordered SV lattices spaced by a single Te atom, reaching the ultimate downscaling limit of antidot lattices. Increasing the number of SVs in QADs strengthens the cumulative repulsive potential and consequently enhances collective interference of multiple-pocket scattered quasiparticles inside QADs, creating multi-level quantum hole states with tunable gap from telecom to far-infrared regime. Moreover, precisely engineered quantum hole states of QADs are symmetry-protected and thus survive upon atom-by-atom oxygen substitutional doping. Therefore, SV-assembled QADs exhibit unprecedented robustness and property tunability, which not only holds the key to their future applications but also embody a wide variety of material technologies.

cond-mat.mes-hall↗

arXiv2021

Electronic Self-passivation of Single Vacancy in Black Phosphorus via a Controlled Ionization

We report that mono-elemental black phosphorus presents a new electronic self-passivation scheme of single vacancy (SV). By means of low-temperature scanning tunneling microscopy and bond-resolved non-contact atomic force microscopy, we demonstrate that the local reconstruction and ionization of SV into negatively charged $\mathrm{SV}^-$ leads to the passivation of dangling bonds and thus the quenching of in-gap states, which can be achieved by mild thermal annealing or STM tip manipulation. SV exhibits a strong and symmetric Friedel oscillation (FO) pattern, while $\mathrm{SV}^-$ shows an asymmetric FO pattern with local perturbation amplitude reduced by one order of magnitude and a faster decay rate. The enhanced passivation by forming $\mathrm{SV}^-$ can be attributed to its weak dipole-like perturbation, consistent with density-functional theory and numerical calculations. Therefore, self-passivated $\mathrm{SV}^-$ is electronically benign and acts as a much weaker scattering center, which may hold the key to further enhance the charge mobility of BP and its analogs.

cond-mat.mtrl-sci↗