arXiv subjects

Yifei Tang

Publications and source records attributed to Yifei Tang.

6 recordsLinked to original sources

arXiv2026

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prompts, single-view images, multi-view images, and videos, and produces 3D world representations. With text or single-view image inputs, the model performs world generation, synthesizing high-fidelity, navigable 3D Gaussian Splatting (3DGS) scenes. This is achieved through a four-stage method: a) Panorama Generation with HY-Pano 2.0, b) Trajectory Planning with WorldNav, c) World Expansion with WorldStereo 2.0, and d) World Composition with WorldMirror 2.0. Specifically, we introduce key innovations to enhance panorama fidelity, enable 3D scene understanding and planning, and upgrade WorldStereo, our keyframe-based view generation model with consistent memory. We also upgrade WorldMirror, a feed-forward model for universal 3D prediction, by refining model architecture and learning strategy, enabling world reconstruction from multi-view images or videos. Also, we introduce WorldLens, a high-performance 3DGS rendering platform featuring a flexible engine-agnostic architecture, automatic IBL lighting, efficient collision detection, and training-rendering co-design, enabling interactive exploration of 3D worlds with character support. Extensive experiments demonstrate that HY-World 2.0 achieves state-of-the-art performance on several benchmarks among open-source approaches, delivering results comparable to the closed-source model Marble. We release all model weights, code, and technical details to facilitate reproducibility and support further research on 3D world models.

cs.CV↗

arXiv2026

Neural Dynamics-Informed Pre-trained Framework for Personalized Brain Functional Network Construction

Brain activity is intrinsically a neural dynamic process constrained by anatomical space. This leads to significant variations in spatial distribution patterns and correlation patterns of neural activity across variable and heterogeneous scenarios. However, dominant brain functional network construction methods, which relies on pre-defined brain atlases and linear assumptions, fails to precisely capture varying neural activity patterns in heterogeneous scenarios. This limits the consistency and generalizability of the brain functional networks constructed by dominant methods. Here, a neural dynamics-informed pre-trained framework is proposed for personalized brain functional network construction. The proposed framework extracts personalized representations of neural activity patterns in heterogeneous scenarios. Personalized brain functional networks are obtained by utilizing these representations to guide brain parcellation and neural activity correlation estimation. Systematic evaluations were employed on 18 datasets across tasks, such as virtual neural modulation and abnormal neural circuit identification. Experimental results demonstrate that the proposed framework attains superior performance in heterogeneous scenarios. Overall, the proposed framework challenges the dominant brain functional network construction method.

cs.LG↗

arXiv2025

Brain Network Analysis Based on Fine-tuned Self-supervised Model for Brain Disease Diagnosis

Functional brain network analysis has become an indispensable tool for brain disease analysis. It is profoundly impacted by deep learning methods, which can characterize complex connections between ROIs. However, the research on foundation models of brain network is limited and constrained to a single dimension, which restricts their extensive application in neuroscience. In this study, we propose a fine-tuned brain network model for brain disease diagnosis. It expands brain region representations across multiple dimensions based on the original brain network model, thereby enhancing its generalizability. Our model consists of two key modules: (1)an adapter module that expands brain region features across different dimensions. (2)a fine-tuned foundation brain network model, based on self-supervised learning and pre-trained on fMRI data from thousands of participants. Specifically, its transformer block is able to effectively extract brain region features and compute the inter-region associations. Moreover, we derive a compact latent representation of the brain network for brain disease diagnosis. Our downstream experiments in this study demonstrate that the proposed model achieves superior performance in brain disease diagnosis, which potentially offers a promising approach in brain network analysis research.

eess.IV↗

arXiv2025

Adaptive Estimation and Learning under Temporal Distribution Shift

In this paper, we study the problem of estimation and learning under temporal distribution shift. Consider an observation sequence of length $n$, which is a noisy realization of a time-varying groundtruth sequence. Our focus is to develop methods to estimate the groundtruth at the final time-step while providing sharp point-wise estimation error rates. We show that, without prior knowledge on the level of temporal shift, a wavelet soft-thresholding estimator provides an optimal estimation error bound for the groundtruth. Our proposed estimation method generalizes existing researches Mazzetto and Upfal (2023) by establishing a connection between the sequence's non-stationarity level and the sparsity in the wavelet-transformed domain. Our theoretical findings are validated by numerical experiments. Additionally, we applied the estimator to derive sparsity-aware excess risk bounds for binary classification under distribution shift and to develop computationally efficient training objectives. As a final contribution, we draw parallels between our results and the classical signal processing problem of total-variation denoising (Mammen and van de Geer,1997; Tibshirani, 2014), uncovering novel optimal algorithms for such task.

cs.LG↗

arXiv2024

Unusual spin dynamics in the van der Waals antiferromagnet FeGa2S4

Spin dynamics in the van der Waals antiferromagnet FeGa$_2$S$_4$ with triangular lattices are investigated using magnetometry, neutron scattering, and muon spin relaxation measurements. The characteristic spin relaxation time is thoroughly clarified over thirteen orders of magnitude. Although the temperature dependence of DC and AC susceptibilities recalls a conventional spin-glass transition, nonlinear susceptibilities showing no divergences at the anomalous temperature, $T^{\ast}=16.87(7)$~K, deny that and instead hint at other mechanisms. Elastic neutron scattering together with previously measured muon results depict a slowly fluctuated ($\sim 10^{-5}$~sec) spin state above $T^{\ast}$. In juxtaposing the underlying simplest structure among frustrated magnets with an intricate hierarchy of time scales, FeGa$_2$S$_4$ can be a playground for studying temporal spin correlations in the two-dimensional limit.

cond-mat.str-el↗

arXiv2021

Triplon current generation in solids

A triplon refers to a fictitious particle that carries angular momentum $S = 1$ corresponding to the elementary excitation in a broad class of quantum dimerized spin systems. Such systems without magnetic order have long been studied as a testing ground for quantum properties of spins. Although triplons have been found to play a central role in thermal and magnetic properties in dimerized magnets with singlet correlation, a spin angular momentum flow carried by triplons, a triplon current, has not been detected yet. Here we report spin Seebeck effects induced by a triplon current: triplon spin Seebeck effect, using a spin-Peierls system CuGeO$_3$. The result shows that the heating-driven triplon transport induces spin current whose sign is positive, opposite to the spin-wave cases in magnets. The triplon spin Seebeck effect persists far below the spin-Peierls transition temperature, being consistent with a theoretical calculation for triplon spin Seebeck effects.

cond-mat.mtrl-sci↗