arXiv subjects

Si Li

Publications and source records attributed to Si Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Two-Dimensional Altermagnetic Iron Oxyhalides: Real Chern Topology and Valley-Spin-Lattice Coupling

Altermagnets, a novel class of collinear magnetic materials, exhibit unique spin-split band structures, yet topological insulating states in intrinsic altermagnetic systems are rare. Here, we identify monolayer Fe$_2X_2$O ($X$ = Cl, Br, I) as a new family of 2D altermagnetic real Chern insulators. These materials display robust $d$-wave altermagnetic ordering, semiconducting band gaps, and nontrivial real Chern numbers per spin channel, yielding spin-polarized topological corner modes. They also feature spin-polarized valleys with strong altermagnetism-valley-spin-lattice coupling, enabling valley-selective excitation via linear dichroism and strain-induced valley polarization. In multiferroic Fe$_2$Cl$_2$O, magnetism coexists with ferroelasticity, and an applied strain can switch the Néel vector. These findings position 2D iron oxyhalides as a promising platform for exploring altermagnetism and magnetic topological states for spintronics and valleytronics.

cond-mat.mtrl-sci↗

arXiv2025

Towards Deeper Emotional Reflection: Crafting Affective Image Filters with Generative Priors

Social media platforms enable users to express emotions by posting text with accompanying images. In this paper, we propose the Affective Image Filter (AIF) task, which aims to reflect visually-abstract emotions from text into visually-concrete images, thereby creating emotionally compelling results. We first introduce the AIF dataset and the formulation of the AIF models. Then, we present AIF-B as an initial attempt based on a multi-modal transformer architecture. After that, we propose AIF-D as an extension of AIF-B towards deeper emotional reflection, effectively leveraging generative priors from pre-trained large-scale diffusion models. Quantitative and qualitative experiments demonstrate that AIF models achieve superior performance for both content consistency and emotional fidelity compared to state-of-the-art methods. Extensive user study experiments demonstrate that AIF models are significantly more effective at evoking specific emotions. Based on the presented results, we comprehensively discuss the value and potential of AIF models.

cs.CV↗

arXiv2025

Real Chern insulators in two-dimensional altermagnetic Fe$_2$S$_2$O and Fe$_2$Se$_2$O

Altermagnets, recently identified as a third class of collinear magnetic materials, have attracted significant attention in condensed matter physics. Despite this growing interest, the realization of real Chern insulators in intrinsic altermagnetic systems has rarely been reported. In this work, based on first-principles calculations and theoretical analysis, we identify monolayer Fe$_2$S$_2$O and Fe$_2$Se$_2$O as a novel class of two-dimensional altermagnetic real Chern insulators. We demonstrate that these materials possess altermagnetic ground states and host a nontrivial mirror real Chern number, leading to the emergence of symmetry-protected zero-dimensional corner states. Notably, these corner modes are spin-polarized, giving rise to a unique spin-corner coupling effect. We further show that the real Chern insulating phases and their associated corner states remain robust against spin-orbit coupling, as well as under both uniaxial and biaxial strain. Additionally, these materials exhibit pronounced linear dichroism and strong optical absorption. Our findings uncover the novel topological character of Fe$_2$S$_2$O and Fe$_2$Se$_2$O, establishing them as promising platforms for exploring real Chern insulators in altermagnetic systems.

cond-mat.mtrl-sci↗

arXiv2025

Valley-dependent electronic properties in two-dimensional altermagnetic iron-based transition metal chalcogenides

Altermagnets represent a newly identified third class of collinear magnets and have recently emerged as a focal point in condensed matter physics. In this work, through first-principles calculations and theoretical analysis, we identify monolayer Fe$_2$MoX$_4$ (X = S, Se, Te) and Fe$_2$WTe$_4$, a class of iron-based transition metal chalcogenides, as promising altermagnetic materials. These systems are found to be semiconductors exhibiting spin splitting in their nonrelativistic band structures, indicative of intrinsic altermagnetic ordering. Remarkably, their valence bands feature a pair of valleys at the time-reversal-invariant momenta X and Y points. Unlike conventional valley systems, these valleys are related by crystal symmetries rather than time-reversal symmetry. We investigate valley-dependent physical phenomena in these materials, including Berry curvature and optical circular dichroism, revealing strong valley-contrasting behavior. Furthermore, we investigate the effect of uniaxial strain and show that it effectively lifts the valley degeneracy, resulting in pronounced valley polarization. Under hole doping, this strain-induced asymmetry gives rise to a piezomagnetic response. We also explore the generation of anisotropic noncollinear spin currents in these systems, expanding the scope of their spin-related functionalities. Our findings unveil rich valley physics in monolayer Fe$_2$MoX$_4$ (X = S, Se, Te) and Fe$_2$WTe$_4$, highlighting their significant potential for applications in valleytronics, spintronics, and multifunctional nanoelectronic devices.

cond-mat.mtrl-sci↗

arXiv2025

GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC software and mobile Apps, are often complex and proprietary, making it difficult to obtain the comprehensive environment information needed for agent training and evaluation. This limitation hinders systematic investigation and benchmarking of agent navigation capabilities. To address this limitation, we introduce GUI Exploration Lab, a simulation environment engine for GUI agent navigation research that enables flexible definition and composition of screens, icons, and navigation graphs, while providing full access to environment information for comprehensive agent training and evaluation. Through extensive experiments, we find that supervised fine-tuning enables effective memorization of fundamental knowledge, serving as a crucial foundation for subsequent training. Building on this, single-turn reinforcement learning further enhances generalization to unseen scenarios. Finally, multi-turn reinforcement learning encourages the development of exploration strategies through interactive trial and error, leading to further improvements in screen navigation performance. We validate our methods on both static and interactive benchmarks, demonstrating that our findings generalize effectively to real-world scenarios. These findings demonstrate the advantages of reinforcement learning approaches in GUI navigation and offer practical guidance for building more capable and generalizable GUI agents.

cs.CV↗

arXiv2025

Quantization and Algebraic Index

This article reviews the program on connecting Batalin-Vilkovisky (BV) quantization with index theories of algebraic type. We explain how the classical algebraic index theorem can be proved in terms of BV quantization of topological quantum mechanics. This is generalized to 2d chiral CFT in which we present an elliptic chiral analog of the algebraic index theory. As an application, we show how the generating function of all genus Gromov-Witten invariants on elliptic curves is mirror equivalent to an elliptic chiral index in the mirror BCOV theory.

math-ph↗

arXiv2025

Personalized Image Filter: Mastering Your Photographic Style

Photographic style, as a composition of certain photographic concepts, is the charm behind renowned photographers. But learning and transferring photographic style need a profound understanding of how the photo is edited from the unknown original appearance. Previous works either fail to learn meaningful photographic concepts from reference images, or cannot preserve the content of the content image. To tackle these issues, we proposed a Personalized Image Filter (PIF). Based on a pretrained text-to-image diffusion model, the generative prior enables PIF to learn the average appearance of photographic concepts, as well as how to adjust them according to text prompts. PIF then learns the photographic style of reference images with the textual inversion technique, by optimizing the prompts for the photographic concepts. PIF shows outstanding performance in extracting and transferring various kinds of photographic style. Project page: https://pif.pages.dev/

cs.CV↗

arXiv2025

PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction

Efficient shape reconstruction for surfaces with complex reflectance properties is crucial for real-time virtual reality. While 3D Gaussian Splatting (3DGS)-based methods offer fast novel view rendering by leveraging their explicit surface representation, their reconstruction quality lags behind that of implicit neural representations, particularly in the case of recovering surfaces with complex reflective reflectance. To address these problems, we propose PolGS, a Polarimetric Gaussian Splatting model allowing fast reflective surface reconstruction in 10 minutes. By integrating polarimetric constraints into the 3DGS framework, PolGS effectively separates specular and diffuse components, enhancing reconstruction quality for challenging reflective materials. Experimental results on the synthetic and real-world dataset validate the effectiveness of our method.

cs.CV↗

arXiv2025

PolarAnything: Diffusion-based Polarimetric Image Synthesis

Polarization images facilitate image enhancement and 3D reconstruction tasks, but the limited accessibility of polarization cameras hinders their broader application. This gap drives the need for synthesizing photorealistic polarization images. The existing polarization simulator Mitsuba relies on a parametric polarization image formation model and requires extensive 3D assets covering shape and PBR materials, preventing it from generating large-scale photorealistic images. To address this problem, we propose PolarAnything, capable of synthesizing polarization images from a single RGB input with both photorealism and physical accuracy, eliminating the dependency on 3D asset collections. Drawing inspiration from the zero-shot performance of pretrained diffusion models, we introduce a diffusion-based generative framework with an effective representation strategy that preserves the fidelity of polarization properties. Experiments show that our model generates high-quality polarization images and supports downstream tasks like shape from polarization.

cs.CV↗

arXiv2025

Considering the multi-time scale rolling optimization scheduling method of micro-energy network connected to electric vehicles

The large-scale access of electric vehicles to the power grid not only provides flexible adjustment resources for the power system, but the temporal uncertainty and distribution complexity of their energy interaction pose significant challenges to the economy and robustness of the micro-energy network. In this paper, we propose a multi-time scale rolling optimization scheduling method for micro-energy networks considering the access of electric vehicles. In order to solve the problem of evaluating the dispatchable potential of electric vehicle clusters, a charging station aggregation model was constructed based on Minkowski summation theory, and the scattered electric vehicle resources were aggregated into virtual energy storage units to participate in system scheduling. Integrate price-based and incentive-based demand response mechanisms to synergistically tap the potential of source-load two-side regulation; On this basis, a two-stage optimal scheduling model of day-ahead and intra-day is constructed. The simulation results show that the proposed method reduces the scale of "preventive curtailment" due to more accurate scheduling, avoids the threat of power shortage to the safety of the power grid, and has more advantages in the efficiency of new energy consumption. At the same time, intra-day scheduling significantly reduces economic penalties and operating costs by avoiding output shortages, and improves the economy of the system in an uncertain forecasting environment.

eess.SY↗

arXiv2025

Contact Term Algebras and Dijkgraaf's Master Equation

This paper is devoted to study integrable deformations of chiral conformal field theories on elliptic curves from the viewpoint of contact algebra. We introduce the relevant integrable condition within the framework of conformal vertex algebra, and derive the contact term relations among certain local operators. We investigate three versions of genus one partition functions and derive the contact equations. This leads to a rigorous formulation of Dijkgraaf's master equation \cite{Dijk1996master} for chiral deformations.

math.QA↗

arXiv2025

Audio-Sync Video Generation with Multi-Stream Temporal Control

Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video is essential for understanding and visualizing rich audio narratives (e.g., Podcasts or historical recordings). However, existing approaches fall short in generating high-quality videos with precise audio-visual synchronization, especially across diverse and complex audio types. In this work, we introduce MTV, a versatile framework for audio-sync video generation. MTV explicitly separates audios into speech, effects, and music tracks, enabling disentangled control over lip motion, event timing, and visual mood, respectively -- resulting in fine-grained and semantically aligned video generation. To support the framework, we additionally present DEMIX, a dataset comprising high-quality cinematic videos and demixed audio tracks. DEMIX is structured into five overlapped subsets, enabling scalable multi-stage training for diverse generation scenarios. Extensive experiments demonstrate that MTV achieves state-of-the-art performance across six standard metrics spanning video quality, text-video consistency, and audio-video alignment. Project page: https://hjzheng.net/projects/MTV/.

cs.CV↗

arXiv2025

Affective Image Editing: Shaping Emotional Factors via Text Descriptions

In daily life, images as common affective stimuli have widespread applications. Despite significant progress in text-driven image editing, there is limited work focusing on understanding users' emotional requests. In this paper, we introduce AIEdiT for Affective Image Editing using Text descriptions, which evokes specific emotions by adaptively shaping multiple emotional factors across the entire images. To represent universal emotional priors, we build the continuous emotional spectrum and extract nuanced emotional requests. To manipulate emotional factors, we design the emotional mapper to translate visually-abstract emotional requests to visually-concrete semantic representations. To ensure that editing results evoke specific emotions, we introduce an MLLM to supervise the model training. During inference, we strategically distort visual elements and subsequently shape corresponding emotional factors to edit images according to users' instructions. Additionally, we introduce a large-scale dataset that includes the emotion-aligned text and image pair set for training and evaluation. Extensive experiments demonstrate that AIEdiT achieves superior performance, effectively reflecting users' emotional requests.

cs.CV↗

arXiv2025

VIRES: Video Instance Repainting via Sketch and Text Guided Generation

We introduce VIRES, a video instance repainting method with sketch and text guidance, enabling video instance repainting, replacement, generation, and removal. Existing approaches struggle with temporal consistency and accurate alignment with the provided sketch sequence. VIRES leverages the generative priors of text-to-video models to maintain temporal consistency and produce visually pleasing results. We propose the Sequential ControlNet with the standardized self-scaling, which effectively extracts structure layouts and adaptively captures high-contrast sketch details. We further augment the diffusion transformer backbone with the sketch attention to interpret and inject fine-grained sketch semantics. A sketch-aware encoder ensures that repainted results are aligned with the provided sketch sequence. Additionally, we contribute the VireSet, a dataset with detailed annotations tailored for training and evaluating video instance editing methods. Experimental results demonstrate the effectiveness of VIRES, which outperforms state-of-the-art methods in visual quality, temporal consistency, condition alignment, and human ratings. Project page: https://hjzheng.net/projects/VIRES/

cs.CV↗

arXiv2025

M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?

We investigate a critical yet under-explored question in Large Vision-Language Models (LVLMs): Do LVLMs genuinely comprehend interleaved image-text in the document? Existing document understanding benchmarks often assess LVLMs using question-answer formats, which are information-sparse and difficult to guarantee the coverage of long-range dependencies. To address this issue, we introduce a novel and challenging Multimodal Document Summarization Benchmark (M-DocSum-Bench), which comprises 500 high-quality arXiv papers, along with interleaved multimodal summaries aligned with human preferences. M-DocSum-Bench is a reference-based generation task and necessitates the generation of interleaved image-text summaries using provided reference images, thereby simultaneously evaluating capabilities in understanding, reasoning, localization, and summarization within complex multimodal document scenarios. To facilitate this benchmark, we develop an automated framework to construct summaries and propose a fine-grained evaluation method called M-DocEval. Moreover, we further develop a robust summarization baseline, i.e., M-DocSum-7B, by progressive two-stage training with diverse instruction and preference data. The extensive results on our M-DocSum-Bench reveal that the leading LVLMs struggle to maintain coherence and accurately integrate information within long and interleaved contexts, often exhibiting confusion between similar images and a lack of robustness. Notably, M-DocSum-7B achieves state-of-the-art performance compared to larger and closed-source models (including GPT-4o, Gemini Pro, Claude-3.5-Sonnet and Qwen2.5-VL-72B, etc.), demonstrating the potential of LVLMs for improved interleaved image-text understanding. The code, data, and models are available at https://github.com/stepfun-ai/M-DocSum-Bench.

cs.CV↗

arXiv2025

Stochastic Calculus and Hochschild Homology

This paper is a case study of probabilistic approach to homological aspects of topological quantum field theory via the example of topological quantum mechanics. We propose topological correlations in terms of large variance limit. An investigation on the relation between probabilistic topological correlations on the circle and Hochschild homology is illustrated.

math.PR↗

arXiv2025

Chiral Topological Phononic Quasiparticles in Enantiomeric Crystals SrSi$_2$ and BaSi$_2$

Chiral crystals have recently garnered significant interest in condensed matter physics due to their unique electronic and optical properties. In this paper, we explore the connection between the chirality of crystal structures and the chirality of topological quasiparticles. We specifically predict and analyze several chiral enantiomeric materials, such as SrSi$_2$ and BaSi$_2$, which crystallize in the chiral space groups $P4{_3}32$ and $P4{_1}32$. Based on first-principles calculations and theoretical analysis, we reveal that the phonon spectra of these materials host various topological phononic quasiparticles, including charge-2 triple points, charge-2 Dirac points, charge-2 Weyl points, and charge-1 Weyl points. Our paper shows that in these enantiomeric materials, the opposite chirality of the crystal structure results in topological quasiparticles with opposite chiral topological charges and distinct topological surface states. Our paper elucidates the intrinsic relationship between the chirality of crystal structures and the chirality of topological quasiparticles, providing promising theoretical guidance and material platform for investigating the physical properties of chiral crystals.

cond-mat.mtrl-sci↗

arXiv2024

Strain-induced valley polarization, topological states, and piezomagnetism in two-dimensional altermagnetic V$_2$Te$_2$O, V$_2$STeO, V$_2$SSeO, and V$_2$S$_2$O

Altermagnets (AM) are a recently discovered third class of collinear magnets, and have been attracting significant interest in the field of condensed matter physics. Here, based on first-principles calculations and theoretical analysis, we propose four two-dimensional (2D) magnetic materials--monolayer V$_2$Te$_2$O, V$_2$STeO, V$_2$SSeO, and V$_2$S$_2$O--as candidates for altermagnetic materials. We show that these materials are semiconductors with spin-splitting in their nonrelativistic band structures. Furthermore, in the band structure, there are a pair of Dirac-type valleys located at the time-reversal invariant momenta (TRIM) X and Y points. These two valleys are connected by crystal symmetry instead of time-reversal symmetry. We investigate the strain effect on the band structure and find that uniaxial strain can induce valley polarization, topological states in these monolayer materials. Moreover, piezomagnetism can be realized upon finite doping. Our result reveals interesting valley physics in monolayer V$_2$Te$_2$O, V$_2$STeO, V$_2$SSeO, and V$_2$S$_2$O, suggesting their great potential for valleytronics, spintronics, and multifunctional nanoelectronics applications.

cond-mat.mtrl-sci↗