arXiv subjects

Yi Wang

Publications and source records attributed to Yi Wang.

At least 451 records · Page 25Linked to original sources

arXiv2025

Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

We present Vchitect-2.0, a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation. The overall Vchitect-2.0 system has several key designs. (1) By introducing a novel Multimodal Diffusion Block, our approach achieves consistent alignment between text descriptions and generated video frames, while maintaining temporal coherence across sequences. (2) To overcome memory and computational bottlenecks, we propose a Memory-efficient Training framework that incorporates hybrid parallelism and other memory reduction techniques, enabling efficient training of long video sequences on distributed systems. (3) Additionally, our enhanced data processing pipeline ensures the creation of Vchitect T2V DataVerse, a high-quality million-scale training dataset through rigorous annotation and aesthetic evaluation. Extensive benchmarking demonstrates that Vchitect-2.0 outperforms existing methods in video quality, training efficiency, and scalability, serving as a suitable base for high-fidelity video generation.

cs.CV↗

arXiv2025

SELMA3D challenge: Self-supervised learning for 3D light-sheet microscopy image segmentation

Recent innovations in light sheet microscopy, paired with developments in tissue clearing techniques, enable the 3D imaging of large mammalian tissues with cellular resolution. Combined with the progress in large-scale data analysis, driven by deep learning, these innovations empower researchers to rapidly investigate the morphological and functional properties of diverse biological samples. Segmentation, a crucial preliminary step in the analysis process, can be automated using domain-specific deep learning models with expert-level performance. However, these models exhibit high sensitivity to domain shifts, leading to a significant drop in accuracy when applied to data outside their training distribution. To address this limitation, and inspired by the recent success of self-supervised learning in training generalizable models, we organized the SELMA3D Challenge during the MICCAI 2024 conference. SELMA3D provides a vast collection of light-sheet images from cleared mice and human brains, comprising 35 large 3D images-each with over 1000^3 voxels-and 315 annotated small patches for finetuning, preliminary testing and final testing. The dataset encompasses diverse biological structures, including vessel-like and spot-like structures. Five teams participated in all phases of the challenge, and their proposed methods are reviewed in this paper. Quantitative and qualitative results from most participating teams demonstrate that self-supervised learning on large datasets improves segmentation model performance and generalization. We will continue to support and extend SELMA3D as an inaugural MICCAI challenge focused on self-supervised learning for 3D microscopy image segmentation.

eess.IV↗

arXiv2025

Uncovering Non-native Speakers' Experiences in Global Software Development Teams -- A Bourdieusian Perspective

Globally distributed software development has been a mainstream paradigm in developing modern software systems. We have witnessed a fast-growing population of software developers from areas where English is not a native language in the last several decades. Given that English is still the de facto working language in most global software engineering teams, we need to gain more knowledge about the experiences of developers who are non-native English speakers. We conducted an empirical study to fill this research gap. In this study, we interviewed 27 Chinese developers in commercial software development and open source global software development teams and applied Bourdieu's capital-field-habitus framework in an abductive data analysis process. Our study reveals four types of capital (language, social, symbolic, and economic) involved in their experiences and examines the interrelations among them. We found that non-native speakers' insufficient language capital played an essential role in prohibiting them from accessing and accumulating other capital, thus reproducing the sustained and systematic disadvantaged positions of non-native English speakers in GSD teams. We further discussed the theoretical and practical implications of the study.

cs.SE↗

arXiv2025

Time-asymptotic stability of generic Riemann solutions for Boltzmann equation

Time-asymptotic stability of generic Riemann solution, consisting of a rarefaction wave, a contact discontinuity and a shock, for the one-dimensional Boltzmann equation, has been a long-standing open problem in kinetic theory. In this paper, we proved that the composite waves of generic Riemann profile including the inviscid self-similar rarefaction wave, the viscous contact wave (i.e., the viscous version of contact discontinuity) and the viscous shock profile with the time-dependent shift to both macroscopic and microscopic components are nonlinearly stable for the one-dimensional Boltzmann equation, by the first using the $a$-contraction method to the Boltzmann equation. Compared with the compressible Navier-Stokes-Fourier equations, the new difficulties here lie in the microscopic effects of the Boltzmann shock profile and their interactions and/or couplings with the rarefaction wave, viscous contact wave and the macroscopic components from the macro-micro decomposition of the Boltzmann equation.

math.AP↗

arXiv2025

Salient Region Matching for Fully Automated MR-TRUS Registration

Prostate cancer is a leading cause of cancer-related mortality in men. The registration of magnetic resonance (MR) and transrectal ultrasound (TRUS) can provide guidance for the targeted biopsy of prostate cancer. In this study, we propose a salient region matching framework for fully automated MR-TRUS registration. The framework consists of prostate segmentation, rigid alignment and deformable registration. Prostate segmentation is performed using two segmentation networks on MR and TRUS respectively, and the predicted salient regions are used for the rigid alignment. The rigidly-aligned MR and TRUS images serve as initialization for the deformable registration. The deformable registration network has a dual-stream encoder with cross-modal spatial attention modules to facilitate multi-modality feature learning, and a salient region matching loss to consider both structure and intensity similarity within the prostate region. Experiments on a public MR-TRUS dataset demonstrate that our method achieves satisfactory registration results, outperforming several cutting-edge methods. The code is publicly available at https://github.com/mock1ngbrd/salient-region-matching.

eess.IV↗

arXiv2025

Stochastically Constrained Best Arm Identification with Thompson Sampling

We consider the problem of the best arm identification in the presence of stochastic constraints, where there is a finite number of arms associated with multiple performance measures. The goal is to identify the arm that optimizes the objective measure subject to constraints on the remaining measures. We will explore the popular idea of Thompson sampling (TS) as a means to solve it. To the best of our knowledge, it is the first attempt to extend TS to this problem. We will design a TS-based sampling algorithm, establish its asymptotic optimality in the rate of posterior convergence, and demonstrate its superior performance using numerical examples.

cs.LG↗

arXiv2025

Interpretable Load Forecasting via Representation Learning of Geo-distributed Meteorological Factors

Meteorological factors (MF) are crucial in day-ahead load forecasting as they significantly influence the electricity consumption behaviors of consumers. Numerous studies have incorporated MF into the load forecasting model to achieve higher accuracy. Selecting MF from one representative location or the averaged MF as the inputs of the forecasting model is a common practice. However, the difference in MF collected in various locations within a region may be significant, which poses a challenge in selecting the appropriate MF from numerous locations. A representation learning framework is proposed to extract geo-distributed MF while considering their spatial relationships. In addition, this paper employs the Shapley value in the graph-based model to reveal connections between MF collected in different locations and loads. To reduce the computational complexity of calculating the Shapley value, an acceleration method is adopted based on Monte Carlo sampling and weighted linear regression. Experiments on two real-world datasets demonstrate that the proposed method improves the day-ahead forecasting accuracy, especially in extreme scenarios such as the "accumulation temperature effect" in summer and "sudden temperature change" in winter. We also find a significant correlation between the importance of MF in different locations and the corresponding area's GDP and mainstay industry.

cs.LG↗

arXiv2025

Robust altermagnetism and compensated ferrimagnetism in MnPX$_3$-based (X = S or Se) heterostructures

The recent research interests in the non-relativistic spin splitting of electronic band structures have led to the exploration of altermagnets and other compensated magnets. Here, we show that various types of non-relativistic spin splitting can be robustly induced by constructing Van der Waals heterostructures consisting of materials with intra-plane anti-ferromagnetic orders and suitable substrates. Using MnPX$_3$ (X = S or Se) as an example, which has a Néel magnetic order, we demonstrate that altermagnetic spin splitting can arise in the AA-stacking MnPX$_3$/MPX$_3$ (M = Cd, Mg, or Zn) heterostructures. For the AB-stacking heterostructures that are semiconducting, ferrimagnetic-type spin splitting emerges, and the fully compensated magnetization is protected by the Luttinger theorem. By combining with a Van der Waals ferroelectric substrate like CuInP$_2$S$_6$, MnPX$_3$-based heterostructures can show tunable spin splitting and spin-related properties that depend on the electronic band structures and ferroelectric polarization, which can be non-volatilely reversed by applying an out-of-plane electric field. Our study provides a route to induce tunable non-relativistic spin splitting in experimentally synthesizable two-dimensional magnets.

cond-mat.mtrl-sci↗

arXiv2024

Global convergence for time-periodic systems with negative feedback and applications

For the discrete-time dynamical system generated by the Poincare map T of a time-periodic closed-loop negative feedback system, we present an amenable condition which enables us to obtain the global convergence of the orbits. This yields the global convergence to the harmonic periodic solutions of the corresponding time-periodic systems with negative feedback. Our approach is motivated by embedding the negative feedback system into a larger time-periodic monotone dynamical systems. We further utilize the theoretical results to obtain the global convergence to periodic solutions for the time periodically-forced gene regulatory models. Numerical simulations are exhibited to illustrate the feasibility of our theoretical results for this model.

math.DS↗

arXiv2024

Nonlinear asymptotic stability of non-self-similar rarefaction wave for two-dimensional viscous Burgers equation

We investigate the large time behavior of solutions to the two-dimensional viscous Burgers equation $u_t+uu_x+uu_y=Δu$, toward a non-self-similar rarefaction wave of inviscid Burgers equation with two initial constant states, seperated by a curve $y=φ(x)$, and prove that the above 2D non-self-similar rarefaction wave is time-asymptotically stable. Furthermore, we also get the decay rate. Both the rarefaction wave strength and the initial perturbation can be large.

math.AP↗

arXiv2024

LLM Agent for Fire Dynamics Simulations

Significant advances have been achieved in leveraging foundation models, such as large language models (LLMs), to accelerate complex scientific workflows. In this work we introduce FoamPilot, a proof-of-concept LLM agent designed to enhance the usability of FireFOAM, a specialized solver for fire dynamics and fire suppression simulations built using OpenFOAM, a popular open-source toolbox for computational fluid dynamics (CFD). FoamPilot provides three core functionalities: code insight, case configuration and simulation evaluation. Code insight is an alternative to traditional keyword searching leveraging retrieval-augmented generation (RAG) and aims to enable efficient navigation and summarization of the FireFOAM source code for developers and experienced users. For case configuration, the agent interprets user requests in natural language and aims to modify existing simulation setups accordingly to support intermediate users. FoamPilot's job execution functionality seeks to manage the submission and execution of simulations in high-performance computing (HPC) environments and provide preliminary analysis of simulation results to support less experienced users. Promising results were achieved for each functionality, particularly for simple tasks, and opportunities were identified for significant further improvement for more complex tasks. The integration of these functionalities into a single LLM agent is a step aimed at accelerating the simulation workflow for engineers and scientists employing FireFOAM for complex simulations critical for improving fire safety.

cs.AI↗

arXiv2024

Context-aware knowledge graph framework for traffic speed forecasting using graph neural network

Human mobility is intricately influenced by urban contexts spatially and temporally, constituting essential domain knowledge in understanding traffic systems. While existing traffic forecasting models primarily rely on raw traffic data and advanced deep learning techniques, incorporating contextual information remains underexplored due to insufficient integration frameworks and the complexity of urban contexts. This study proposes a novel context-aware knowledge graph (CKG) framework to enhance traffic speed forecasting by effectively modeling spatial and temporal contexts. Employing a relation-dependent integration strategy, the framework generates context-aware representations from the spatial and temporal units of CKG to capture spatio-temporal dependencies of urban contexts. A CKG-GNN model, combining the CKG, dual-view multi-head self-attention (MHSA), and graph neural network (GNN), is then designed to predict traffic speed utilizing these context-aware representations. Our experiments demonstrate that CKG's configuration significantly influences embedding performance, with ComplEx and KG2E emerging as optimal for embedding spatial and temporal units, respectively. The CKG-GNN model establishes a benchmark for 10-120 min predictions, achieving average MAE, MAPE, and RMSE of $3.46\pm0.01$, $14.76\pm0.09\%$, and $5.08\pm0.01$, respectively. Compared to the baseline DCRNN model, integrating the spatial unit improves the MAE by 0.04 and the temporal unit by 0.13, while integrating both units further reduces it by 0.18. The dual-view MHSA analysis reveals the crucial role of relation-dependent features from the context-based view and the model's ability to prioritize recent time slots in prediction from the sequence-based view. Overall, this study underscores the importance of merging context-aware knowledge graphs with graph neural networks to improve traffic forecasting.

cs.LG↗

arXiv2024

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a recurrent neural network (RNN) as the draft model conditioning on LLM's hidden states, (2) applying a dynamic tree attention algorithm over beam search results to eliminate duplicated prefixes in candidate sequences, and (3) training through knowledge distillation from the LLM. ReDrafter accelerates Vicuna inference in MT-Bench by up to 2.8x with a PyTorch implementation on Nvidia H100 GPUs. To demonstrate its practicality in real environments, we also validated its effectiveness for on-device applications by implementing the approach in MLX and benchmarking performance on Metal GPUs in Apple Silicon chips, achieving up to 2.3x speedup.

cs.CL↗

arXiv2024

Multi-Level Speaker Representation for Target Speaker Extraction

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model's generalization capability. Additionally, we propose a contextual embedding feature based on cross-attention mechanisms that integrate frame-level embeddings from a pre-trained speaker encoder. By incorporating speaker features across multiple levels, we significantly enhance the performance of the TSE model. Our approach achieves a 2.74 dB improvement and a 4.94% increase in extraction accuracy on Libri2mix test set over the baseline.

eess.AS↗

arXiv2024

Asymmetric Colorings of Disjoint Unions of Graphs

The asymmetric coloring number of a graph is the minimum number of colors needed to color its vertices, so that no non-trivial automorphism preserves the color classes. We investigate the asymmetric coloring number of graphs that are disjoint unions of graphs. We will derive a general relationship between the asymmetric coloring number of disjoint copies of graphs and the number of ways to color a single copy asymmetrically, and then look at particular cases such as disjoint copies of paths, stars, cycles, and hypercubes.

math.CO↗

arXiv2024

Investigation of ideal shear strength of dilute binary and ternary Ni-based alloys using first-principles calculations, CALPHAD modeling and correlation analysis

In the present work, the ideal shear strength (τ_is) of dilute Ni34XZ ternary alloys (X or Z = Al, Co, Cr, Fe, Mn, Mo, Nb, Si, Ti) are predicted by first-principles calculations based on density functional theory (DFT) in terms of pure alias shear deformations. The τ_is results show that within the concentration up to 8.3% of alloying elements, τ_is increases with composition in binary systems with Mn, Fe, and Co in ascending order, and decreases with composition with Nb, Si, Mo, Ti, Al, and Cr in descending order. The composition dependence of τ_is in binary and ternary systems is modeled using the CALculation of PHAse Diagrams (CALPHAD) approach considering lattice instability, indicating that atomic bonding strength significantly influences τ_is. Correlational analyses further show that lattice constant and elastic constant C11 affect τ_is, the most out of the elemental features.

cond-mat.mtrl-sci↗

arXiv2024

Asymptotically Optimal Sampling-Based Path Planning Using Bidirectional Guidance Heuristic

This paper introduces Bidirectional Guidance Informed Trees (BIGIT*),~a new asymptotically optimal sampling-based motion planning algorithm. Capitalizing on the strengths of \emph{meet-in-the-middle} property in bidirectional heuristic search with a new lazy strategy, and uniform-cost search, BIGIT* constructs an implicitly bidirectional preliminary motion tree on an implicit random geometric graph (RGG). This efficiently tightens the informed search region, serving as an admissible and accurate bidirectional guidance heuristic. This heuristic is subsequently utilized to guide a bidirectional heuristic search in finding a valid path on the given RGG. Experiments show that BIGIT* outperforms the existing informed sampling-based motion planners both in faster finding an initial solution and converging to the optimum on simulated abstract problems in $\mathbb{R}^{16}$. Practical drone flight path planning tasks across a campus also verify our results.

cs.RO↗

arXiv2024

Vertical Emission of Blue Light from a Symmetry Breaking Plasmonic Nanocavity-Emitter System Supporting Bound States in the Continuum

The concept of photonic bound states in the continuum (BICs), introduced in structured metallic surface cavities, provides a crucial mechanism for designing plasmonic open-resonant cavities with high quality (high-Q) factors, making significant advances in plasmonic nanophotonics. However, the two major bottlenecks for plasmonic nanocavities: enhancing emission and big beam divergence for quantum emitters, due to the strong intrinsic Ohmic losses of metals. Here, we propose and realize a σh symmetry-breaking plasmonic honeycomb nanocavities (PHC) that support quasi-BIC resonance modes with high-Q factors. Our anodic oxidation-engineered strategy breaks out-of-plane symmetry while preserving in-plane symmetry, enabling the PHC to exhibit collective plasmonic lattice resonances (PLR) couplings and achieve Q-factors exceeding 106. Experimentally, we couple perovskite quantum dots (PQDs) to the PHC, demonstrating effective tuning of their emission properties and beam quality in the blue spectral region, achieving a 32-fold emission enhancement by suppress Ohmic loss and the life time of quantum emitters, simultaneously realize vertical emission in the 2.556 - 2.638 eV region, with a far-field hexagonal beam shape and a full width at half maximum of 12.6 degree under optimal coupling conditions. Furthermore, we demonstrate topological band inversion characterized by Zak phase transitions by continuously tuning the system parameters, confirming that the PHC supports topologically non-trivial q-BIC due to PLR coupling. The PHC presents itself as a promising next-generation, high-brightness nanoscale light source matrix, which can be directly scaled up to cover a wide wavelength range from UV to IR.

physics.optics↗