arXiv subjects

Yanze Wu

Publications and source records attributed to Yanze Wu.

At least 19 recordsLinked to original sources

arXiv2026

A Perspective on Phase Space Electronic Structure Theory : From Its Surface Hopping Origins Through To Its Future Promise

We trace the history of phase space electronic structure theory (PSEST), high- lighting how this powerful approach emerged from fundamental questions in semi- classical surface hopping dynamics and evolved into an alternative to standard Born- Oppenheimer based electronic structure theory (with moving instead of frozen nuclei). Our goal herein is not to recapitulate the mathematical details of phase space electronic structure calculations, and few equations are presented so as to maximize readability. Instead, our goal is to provide intuition for those new to the field both (i) regarding the physics present when solving the Schrodinger equation in a non-inertial frame as well as (ii) regarding why PSEST is a necessary step forward towards understanding chemical problems involving spin (with limited practical alternatives). We further high- light some of the many open questions in this fast developing area, which will hopefully inspire new practitioners in this field. This intuitive perspective lacks many equations and is meant to complement (rather than replace) the more technical review given in Bian et al, Chem. Phys. Rev. 7, 011303 (2026)

physics.chem-ph↗

arXiv2026

Real-Time Electron-Electron Scattering Dynamics in Plasmonic Nanostructures

Electron-electron scattering is one of the most important hot carrier relaxation pathways in plasmonic nanoparticles. Understanding the dynamics of this scattering process and the effects of this on excited state dephasing and relaxation is therefore essential for the design of plasmonic nanostructures, including optical properties and the dynamics of electrons in plasmon-driven catalytic reactions. In this work, we have developed a novel approach that incorporates real-time time-dependent density functional tight-binding (DFTB) simulations with the Lindblad quantum Boltzmann equation (LQBE) based on a screened electron-electron interaction that is determined by the random phase approximation (RPA). This approach enables a self-consistent description of electron-electron scattering effects that occur during and after plasmon excitation in clusters/nanoparticles with hundreds of atoms. With our RT-TDDFTB+LQBE method, we investigate the quasiparticle lifetime as well as population and coherence dynamics in silver, gold and aluminum nanoclusters with sizes between 1.5-2.6 nm. Our results show that the quasiparticle lifetimes and relaxation dynamics are highly energy dependent, becoming much faster at higher energies. For clusters less than 2 nm, quantum effects associated with discrete energy levels can lead to the fluctuating lifetimes and deviation of the dynamics from the typical thermalization process, while for larger nanoparticles, the transition to bulk metallic behavior is found. Decoherence of the initially excited plasmon resonance is observed with a timescale of 10 fs, much faster than population relaxation. For gold, we find that the 5d-band can significantly slow down the relaxation of energetic electrons though Auger scattering, and interband transitions can lead to a secondary decoherence process longer than 50 fs.

physics.chem-ph↗

arXiv2026

OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer

Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the rich spatio-temporal information inherent in videos, thereby limiting flexibility and generalization in video generation. To address these limitations, we propose OmniTransfer, a unified framework for spatio-temporal video transfer. It leverages multi-view information across frames to enhance appearance consistency and exploits temporal cues to enable fine-grained temporal control. To unify various video transfer tasks, OmniTransfer incorporates three key designs: Task-aware Positional Bias that adaptively leverages reference video information to improve temporal alignment or appearance consistency; Reference-decoupled Causal Learning separating reference and target branches to enable precise reference transfer while improving efficiency; and Task-adaptive Multimodal Alignment using multimodal semantic guidance to dynamically distinguish and tackle different tasks. Extensive experiments show that OmniTransfer outperforms existing methods in appearance (ID and style) and temporal transfer (camera movement and video effects), while matching pose-guided methods in motion transfer without using pose, establishing a new paradigm for flexible, high-fidelity video generation.

cs.CV↗

arXiv2025

InstructX: Towards Unified Visual Editing with MLLM Guidance

With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most studies lack an in-depth analysis of MLLM design choices. Moreover, the integration of MLLMs and diffusion models remains an open challenge in some difficult tasks, such as video editing. In this paper, we present InstructX, a unified framework for image and video editing. Specifically, we conduct a comprehensive study on integrating MLLMs and diffusion models for instruction-driven editing across diverse tasks. Building on this study, we analyze the cooperation and distinction between images and videos in unified modeling. (1) We show that training on image data can lead to emergent video editing capabilities without explicit supervision, thereby alleviating the constraints imposed by scarce video training data. (2) By incorporating modality-specific MLLM features, our approach effectively unifies image and video editing tasks within a single model. Extensive experiments demonstrate that our method can handle a broad range of image and video editing tasks and achieves state-of-the-art performance.

cs.CV↗

arXiv2025

The Phase-Space Way To Electronic Structure Theory and Subsequently Chemical Dynamics

Phase-space electronic structure theory offers up a new and powerful approach for tackling problems with coupled nuclear-electronic dynamics in a fashion that goes beyond Born-Oppenheimer (BO) theory. Whereas BO theory stipulates that we consider electronic states parameterized by nuclear position $X$ only, i.e. molecular orbitals are functions of nuclear positions but not nuclear velocities, phase-space (PS) theory allows for electronic states to be parameterized by both nuclear position X and nuclear momentum $P$. As a result, within a phase-space approach, one can directly recover many new features, including electronic momentum and vibrational circular dichroism spectra. Moreover, phase-space electronic structure theory is exact for the hydrogen atom and, for a set of model problems, the method can even improve upon vibrational energies relative to BO theory. Perhaps most importantly, the phase-space approach offers up a very new perspective on spin physics, stipulating that molecules and materials with degenerate or nearly degenerate ground states (due to spin degeneracy) display broken-symmetry ground states in their phase-space potential energy surfaces. This last feature opens up very new possibilities for exploring spin chemistry (including the Einstein-de Haas effect and chiral induced spin selectivity) within the context of more established electronic structure theory. At the end of the day, in order to tackle electronic dynamical phenomena, especially subtle problems in magnetic chemistry, it will be essential for the electronic structure community to pivot towards diagonalizing $\hat H_{PS}(X, P)$ rather than $\hat H_{BO}(X)$.

physics.chem-ph↗

arXiv2025

CDST: Color Disentangled Style Transfer for Universal Style Reference Customization

We introduce Color Disentangled Style Transfer (CDST), a novel and efficient two-stream style transfer training paradigm which completely isolates color from style and forces the style stream to be color-blinded. With one same model, CDST unlocks universal style transfer capabilities in a tuning-free manner during inference. Especially, the characteristics-preserved style transfer with style and content references is solved in the tuning-free way for the first time. CDST significantly improves the style similarity by multi-feature image embeddings compression and preserves strong editing capability via our new CDST style definition inspired by Diffusion UNet disentanglement law. By conducting thorough qualitative and quantitative experiments and human evaluations, we demonstrate that CDST achieves state-of-the-art results on various style transfer tasks.

cs.CV↗

arXiv2025

MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routing

Current multi-subject customization approaches encounter two critical challenges: the difficulty in acquiring diverse multi-subject training data, and attribute entanglement across different subjects. To bridge these gaps, we propose MUSAR - a simple yet effective framework to achieve robust multi-subject customization while requiring only single-subject training data. Firstly, to break the data limitation, we introduce debiased diptych learning. It constructs diptych training pairs from single-subject images to facilitate multi-subject learning, while actively correcting the distribution bias introduced by diptych construction via static attention routing and dual-branch LoRA. Secondly, to eliminate cross-subject entanglement, we introduce dynamic attention routing mechanism, which adaptively establishes bijective mappings between generated images and conditional subjects. This design not only achieves decoupling of multi-subject representations but also maintains scalable generalization performance with increasing reference subjects. Comprehensive experiments demonstrate that our MUSAR outperforms existing methods - even those trained on multi-subject dataset - in image quality, subject consistency, and interaction naturalness, despite requiring only single-subject dataset.

cs.CV↗

arXiv2025

DreamO: A Unified Framework for Image Customization

Recently, extensive research on image customization (e.g., identity, subject, style, background, etc.) demonstrates strong customization capabilities in large-scale generative models. However, most approaches are designed for specific tasks, restricting their generalizability to combine different types of condition. Developing a unified framework for image customization remains an open challenge. In this paper, we present DreamO, an image customization framework designed to support a wide range of tasks while facilitating seamless integration of multiple conditions. Specifically, DreamO utilizes a diffusion transformer (DiT) framework to uniformly process input of different types. During training, we construct a large-scale training dataset that includes various customization tasks, and we introduce a feature routing constraint to facilitate the precise querying of relevant information from reference images. Additionally, we design a placeholder strategy that associates specific placeholders with conditions at particular positions, enabling control over the placement of conditions in the generated results. Moreover, we employ a progressive training strategy consisting of three stages: an initial stage focused on simple tasks with limited data to establish baseline consistency, a full-scale training stage to comprehensively enhance the customization capabilities, and a final quality alignment stage to correct quality biases introduced by low-quality data. Extensive experiments demonstrate that the proposed DreamO can effectively perform various image customization tasks with high quality and flexibly integrate different types of control conditions.

cs.CV↗

arXiv2024

Upper Mid-Band Channel Measurements and Characterization at 6.75 GHz FR1(C) and 16.95 GHz FR3 in an Indoor Factory Scenario

This paper presents detailed radio propagation measurements for an indoor factory (InF) environment at 6.75 GHz and 16.95 GHz using a 1 GHz bandwidth channel sounder. Conducted at the NYU MakerSpace in the NYU Tandon School of Engineering campus in Brooklyn, NY, USA, our measurement campaign characterizes the radio propagation in a representative small factory with diverse machinery and open workspaces across 12 locations, comprising 5 line-of-sight (LOS) and 7 non-line-of-sight (NLOS) scenarios. Analysis using the close-in (CI) free space path loss (FSPL) model with a 1 m reference distance reveals path loss exponents (PLE) below 2 in LOS at 6.75 GHz and 16.95 GHz, while in NLOS, PLE is similar to free-space propagation (e.g., PLE = 2). The RMS delay spread (DS) decreases at higher frequencies with a clear frequency dependence. Also, measurements show a wider RMS angular spread (AS) in NLOS compared to LOS at both frequency bands, with a decreasing trend as frequency increases. These observations in a dense-scatterer factory environment demonstrate frequency-dependent behavior that differs from existing industry-standard 3GPP models. Our findings provide crucial insights into complex propagation mechanisms in factory environments, essential for designing robust air interface and industrial wireless networks at the upper mid-band FR3 spectrum.

eess.SP↗

arXiv2024

Urban Outdoor Propagation Measurements and Channel Models at 6.75 GHz FR1(C) and 16.95 GHz FR3 Upper Mid-Band Spectrum for 5G and 6G

Global allocations in the upper mid-band spectrum (4--24 GHz) necessitate a comprehensive exploration of the propagation behavior to meet the promise of coverage and capacity. This paper presents an extensive Urban Microcell (UMi) outdoor propagation measurement campaign at 6.75 GHz and 16.95 GHz conducted in Downtown Brooklyn, USA, using a 1 GHz bandwidth sliding correlation channel sounder over 40--880 m propagation distance, encompassing seven Line of Sight (LOS) and 13 Non-Line of Sight (NLOS) locations. Analysis of the path loss (PL) reveals lower directional and omnidirectional PL exponents compared to mmWave and sub-THz frequencies in the UMi environment, using the close-in (CI) free space PL (FSPL) model with a 1 m reference distance. Additionally, a decreasing trend in root mean square (RMS) delay spread (DS) and angular spread (AS) with increasing frequency was observed. The measured NLOS RMS DS and RMS AS mean values (as computed by 3GPP methods) are found to be consistently lower compared to 3GPP model predictions. Point-data tables with corresponding site-specific environmental information for all measured statistics at each TX-RX location are provided to support the models and results. The spatio-temporal statistics presented here offer valuable insights for the design of next-generation wireless systems and networks.

eess.SP↗

arXiv2024

A semiclassical non-adiabatic phase-space approach to molecular translations and rotations: A new picture of surface hopping and electronic inertial effects

We present a novel semiclassical phase-space surface hopping approach that goes beyond the Born-Oppenheimer approximation and all existing surface hopping formalisms. We demonstrate that working with a correct phase-space electronic Hamiltonian can capture electronic inertial effects during pure nuclear translational and rotational motion and completely eliminate (at least to very high order) non-adiabatic transitions between electronic eigenstates. This work opens many new avenues for quantitatively investigating complex phenomena, including angular momentum transfer between chiral phonons and electrons as well as chiral-induced spin selectivity effects.

physics.chem-ph↗

arXiv2024

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation. By incorporating a Lightning T2I branch with a standard diffusion one, PuLID introduces both contrastive alignment loss and accurate ID loss, minimizing disruption to the original model and ensuring high ID fidelity. Experiments show that PuLID achieves superior performance in both ID fidelity and editability. Another attractive property of PuLID is that the image elements (e.g., background, lighting, composition, and style) before and after the ID insertion are kept as consistent as possible. Codes and models are available at https://github.com/ToTheBeginning/PuLID

cs.CV↗

arXiv2024

Modeling of Collision-Induced Excitation and Quenching of Atomic Nitrogen

Excited atomic nitrogen atoms play an important role in plasma formation in hypersonic shock-waves, as happens during spacecraft reentry and other high velocity vehicle applications. In this study, we have thoroughly studied collision induced excitation (CIE) associated with two colliding nitrogen atoms in the N(4S), N(2D) and N(2P) states at collisions energies up to 6 eV, using time-independent scattering calculations to determine cross sections and temperature-dependent rate coefficients. The calculations are based on potential curves and couplings determined in earlier MRCI calculations with large basis sets, and the results are in good agreement with experiment where comparisons are possible. To properly consider the spin-orbit coupling matrix, we have developed a scaling method for treating transitions between different fine-structure components with calculations that only require calculations with two coupled states, and with this we define accurate degeneracy factors for determining cross sections and rate coefficients that include all states. The results indicate that both spin-orbit and derivative coupling effects can play important roles in collisional excitation and quenching, and that although derivative coupling is always much stronger than spin-orbit, there are many transitions where only spin-orbit can contribute. As part of this, we identify two distinct pathways associated with N(2D) relaxation, including one Auger-like mechanism leading to 2N(2D) that could be important at high temperature.

physics.chem-ph↗

arXiv2024

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations

The diffusion-based text-to-image model harbors immense potential in transferring reference style. However, current encoder-based approaches significantly impair the text controllability of text-to-image models while transferring styles. In this paper, we introduce DEADiff to address this issue using the following two strategies: 1) a mechanism to decouple the style and semantics of reference images. The decoupled feature representations are first extracted by Q-Formers which are instructed by different text descriptions. Then they are injected into mutually exclusive subsets of cross-attention layers for better disentanglement. 2) A non-reconstructive learning method. The Q-Formers are trained using paired images rather than the identical target, in which the reference image and the ground-truth image are with the same style or semantics. We show that DEADiff attains the best visual stylization results and optimal balance between the text controllability inherent in the text-to-image model and style similarity to the reference image, as demonstrated both quantitatively and qualitatively. Our project page is https://tianhao-qi.github.io/DEADiff/.

cs.CV↗

arXiv2023

Linear and Angular Momentum Conservation in Surface Hopping Methods

We demonstrate that, for systems with spin-orbit coupling and an odd number of electrons, the standard fewest switches surface hopping (FSSH) algorithm does not conserve the total linear or angular momentum. This lack of conservation arises not so much from the hopping direction (which is easily adjusted) but more generally from propagating adiabatic dynamics along surfaces that are not time reversible. We show that one solution to this problem is to run along eigenvalues of phase-space electronic Hamiltonians $H(R,P)$ (i.e. electronic Hamiltonians that depend on both nuclear position and momentum) with an electronic nuclear coupling $Γ\cdot P$ and we delineate the conditions that must be satisfied by the operator $Γ$. The present results should be extremely useful as far as developing new semiclassical approaches that can treat systems where the nuclear, electronic orbital, and electronic spin degrees of freedom altogether are all coupled together, hopefully including systems displaying the chiral induced spin selectivity (CISS) effect.

physics.chem-ph↗

arXiv2023

Total Angular Momentum Conservation in Ehrenfest Dynamics with a Truncated Basis of Adiabatic States

We show that standard Ehrenfest dynamics does not conserve linear and angular momentum when using a basis of truncated adiabatic states. However, we also show that previously proposed effective Ehrenfest equations of motion[Amano2005,Krishna2007] involving the non-Abelian Berry force do maintain momentum conservation. As a numerical example, we investigate the Kramers' doublet of the methoxy radical using generalized Hartree-Fock with spin-orbit coupling and confirm angular momentum is conserved with the proper equations of motion. Our work makes clear some of the limitations of the Born-Oppenheimer approximation when using ab initio electronic structure theory to treat systems with unpaired electronic spin degrees of freedom and we demonstrate that Ehrenfest dynamics can offer much improved, qualitatively correct results.

physics.chem-ph↗

arXiv2023

Surface Hopping, Electron Translation Factors, Electron Rotation Factors, Momentum Conservation, and Size Consistency

For a system without spin-orbit coupling, the (i) nuclear plus electronic linear momentum and (ii) nuclear plus orbital electronic angular momentum are good quantum numbers. Thus, when a molecular system undergoes a nonadiabatic transition, there should be no change in the total linear or angular momentum. Now, the standard surface hopping algorithm ignores the electronic momentum and indirectly equates the momentum of the nuclear degrees of freedom to the total momentum. However, even with this simplification, the algorithm still does not conserve either the nuclear linear or the nuclear angular momenta. Here, we show that one way to address these failures is to dress the derivative couplings (i.e. the hopping directions) in two ways: (i) we disallow changes in the nuclear linear momentum by working in a translating basis (which is well known and leads to electron translation factors [ETFs]); and (ii) we disallow changes in the nuclear angular momentum by working in a basis that rotates around the center of mass (which is not well-known and leads to a novel, rotationally removable component of the derivative coupling that we will call electron rotation factors [ERFs] below, cf. Eq. 96). The present findings should be helpful in the short term as far as interpreting surface hopping calculations for singlet systems (without spin) and then developing new surface hopping algorithm in the long term for systems where one cannot ignore the electronic orbital and/or spin angular momentum.

physics.chem-ph↗

arXiv2023

Total Angular Momentum Conservation in Ab Initio Born-Oppenheimer Molecular Dynamics

We prove both analytically and numerically that the total angular momentum of a molecular system undergoing adiabatic Born-Oppenheimer dynamics is conserved only when pseudo-magnetic Berry forces are taken into account. This finding sheds light on the nature of Berry forces for molecular systems with spin-orbit coupling and highlights how ab initio Born-Oppenheimer molecular dynamics simulations can successfully capture the entanglement of spin and nuclear degrees of freedom as modulated by electronic interactions.

physics.chem-ph↗