arXiv subjects

Xiao Cao

Publications and source records attributed to Xiao Cao.

At least 19 recordsLinked to original sources

arXiv2026

CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing

The quality and diversity of instruction-based video editing datasets are steadily improving, yet existing datasets mainly focus on single editing operations and fall short in supporting compositional instruction-guided video editing. In particular, multiple editing intents must be jointly understood and faithfully executed within the same video. To address this issue, we introduce CoinVE-200K, a large-scale, high-quality dataset for Compositional Instruction-Guided Video Editing. CoinVE-200K contains 1080p video-editing pairs of up to 201 frames, covering diverse compositional scenarios where each sample involves 2 to 5 atomic editing operations. The instructions target humans, objects, and backgrounds, and cover edit types such as addition, removal, modification, and stylization. All samples are built through a carefully designed generation and filtering pipeline to ensure instruction faithfulness, visual quality, temporal consistency, and compositional diversity. We also introduce CoinVE-Bench, a benchmark for compositional-instruction video editing across diverse subjects, operation types, and instruction complexities. Furthermore, we present CoinVE-Edit, a 22B compositional video editing model built upon Wan2.1-T2V-14B and Qwen3-VL-8B-Instruct. CoinVE-Edit disentangles region-aware attention for different editing instructions, enabling precise multi-region editing while preserving irrelevant content and temporal coherence. Experiments on CoinVE-Bench show that CoinVE-Edit achieves strong performance in instruction following, compositional editing accuracy, visual quality, and temporal consistency.

cs.CV↗

arXiv2026

Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking

Existing unified 4D reconstruction and point tracking approaches typically rely on heuristic interpolations or just predict at integer timestamps, lacking kinematic coherence and failing to model dynamics at any arbitrary timestamp. In this paper, we propose Uni4R, a framework that unifies these tasks by learning continuous velocity fields through the synergy of Optimal Transport (OT) and Ordinary Differential Equation (ODE). Importantly, this continuous velocity field acts as a kinematic prior that mutually benefits both 4D reconstruction and point tracking. Specifically, we propose the Flow Matching Guided Decoder (FMGD). A global velocity branch first extracts anchor features that capture the global dynamic state of the sequence. Then, FMGD leverages Flow Matching (FM) theory to formulate a probability path defined by OT on the anchor feature manifold, instantiating it as FM-guided velocity features for velocity prediction. This establishes a robust kinematic inductive bias. Meanwhile, a point reconstruction branch provides geometric features. The local velocity prediction module then joint above features and time embeddings, to decode velocities at arbitrary timestamps. To overcome the absence of high-quality ground-truth velocities in fractional frames, we propose an integral-consistency training strategy. This strategy uses an ODE solver to integrate velocities to recover target pointmaps, enabling the model to be supervised end-to-end directly from integer timestamps. Experimental results demonstrate that Uni4R achieves SOTA performance in both 4D reconstruction and point tracking, and achieves SOTA in our new kinematics-aware benchmark at continuous time.

cs.CV↗

arXiv2026

Jet-ISM Interaction and Multi-channel AGN Feedback in the Post-merger Galaxy 4C+29.30

4C+29.30 is a post-merger galaxy hosting a rejuvenated active galactic nucleus (AGN) with a complex multi-scale radio morphology, making it an ideal laboratory to study the interplay between different AGN feedback modes. We present a multi-wavelength analysis combining optical integral field spectroscopy (SDSS/MaNGA and CFHT/SITELLE) with radio continuum imaging (VLASS) to map the ionized gas kinematics and ionization structure across the galaxy. We uncover a galaxy-scale, biconical ionized gas outflow whose axis is misaligned by $\sim$26$^\circ$ from the radio jet. This outflow, characterized by broad line widths and Seyfert-like ionization, is mostly consistent with a radiatively driven wind from the central supermassive black hole, which is accreting at a relatively high Eddington ratio ($L_{\mathrm{bol}}/L_{\mathrm{Edd}} \gtrsim 0.1$). In contrast, the northern radio lobe clearly drives localized gas acceleration and increased velocity dispersion, indicative of jet-driven shocks interacting with the interstellar medium, consistent with previous X-ray findings. The coexistence of a radiatively driven galactic-scale outflow and a distinct, misaligned radio jet demonstrates that multiple AGN feedback channels can operate simultaneously within the same system, providing new evidence for the concurrent action of radiative and mechanical feedback.

astro-ph.GA↗

arXiv2026

GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes

Existing 3DGS methods effectively render high-quality novel views in clear-day scenes. However, they struggle with night scenes, particularly in glow regions, due to the lack of structural features such as textures and edges, which are key cues for splatting-based reconstruction. To address this problem, we leverage a diffusion model and a Vision Foundation Model (VFM) to compensate for missing structural cues. Our method consists of two key novel ideas: semantic feature generation and novel-view semantic learning. First, semantic feature generation produces high-quality semantic features as implicit structural cues for novel views. Specifically, a diffusion model synthesizes novel views with unknown camera poses from training views, while a VFM evaluates their quality. Once high-quality novel views are identified, the VFM extracts robust features to construct the semantic feature bank. Second, novel-view semantic learning enables 3DGS to optimize rendered novel views without requiring ground truth. It achieves this by extracting semantic features from a rendered novel view, searching the feature bank for the most similar features, and minimizing their distance. This process enforces implicit structural constraints, ensuring semantically coherent, artifact-free rendered views. Extensive experiments demonstrate the effectiveness of our GlowGS in generating semantically accurate 3D views, showing significant improvements over existing methods.

cs.CV↗

arXiv2026

Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework

Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, existing methods struggle when references exhibit severe stylistic domain gaps with the source scene. To overcome this, we propose \textit{\textbf{Smart-Insertion-V}}, an end-to-end \textbf{Dual-Stream} framework that concurrently conducts video insertion and image style transfer. Within this framework, the image stream synchronously guides the video generation process, while a \textbf{Closed-loop Feedback} mechanism is further incorporated to ensure robust insertion. Inevitably, integrating these diverse conditioning signals results in feature entanglement and style leakage. To tackle this issue, we design \textbf{Dual-World-View RoPE} to distinguish different signals via spatial-temporal offsets without incurring heavy training overhead. Furthermore, to facilitate spatial grounding and stylistic adaptation, we introduce a \textbf{Decoupled Guidance Module} that leverages a Vision-Language Model for semantic reasoning while preserving original temporal guidance with native text encoder. To bridge data gap for harmonious reference insertion task, we propose a data curation pipeline and will release an \textbf{open-source dataset}. Experiments demonstrate that our method can insert objects into plausible positions while achieving the most harmonious results.

cs.CV↗

arXiv2026

GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction

3D Gaussian Splatting (3DGS) has emerged as a prominent paradigm for 3D reconstruction and novel view synthesis. However, it remains vulnerable to severe artifacts when trained under sparse-view constraints. While recent methods attempt to rectify artifacts in rendered views using image diffusion models, they typically rely on multi-view self-attention to retrieve information from reference images. We observe that this mechanism often fails when the rendered novel views output by 3DGS are heavily corrupted: damaged query features lead to erroneous cross-view retrieval, resulting in inconsistent rendering refinement. To address this, we propose GeoQuery, a geometry-guided diffusion framework that integrates generative priors with explicit geometric cues via a novel Geometry-guided Cross-view Attention (GCA) mechanism. First, by leveraging predicted depth maps and camera poses, we construct a geometry-induced correspondence field to sample reference features, forming a geometry-aligned proxy query that replaces the corrupted rendering features. Furthermore, we design a new cross-view feature aggregation pipeline, in which we restrict the cross-view attention to a local window around each proxy query to effectively retrieve useful features while suppressing spurious matches. GeoQuery can be seamlessly integrated into existing diffusion-based pipelines, enabling robust reconstruction even under extreme view sparsity. Extensive experiments on sparse-view novel view synthesis and rendering artifact removal demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2026

Let Your Image Move with Your Motion! -- Implicit Multi-Object Multi-Motion Transfer

Motion transfer has emerged as a promising direction for controllable video generation, yet existing methods largely focus on single-object scenarios and struggle when multiple objects require distinct motion patterns. In this work, we present FlexiMMT, the first implicit image-to-video (I2V) motion transfer framework that explicitly enables multi-object, multi-motion transfer. Given a static multi-object image and multiple reference videos, FlexiMMT independently extracts motion representations and accurately assigns them to different objects, supporting flexible recombination and arbitrary motion-to-object mappings. To address the core challenge of cross-object motion entanglement, we introduce a Motion Decoupled Mask Attention Mechanism that uses object-specific masks to constrain attention, ensuring that motion and text tokens only influence their designated regions. We further propose a Differentiated Mask Propagation Mechanism that derives object-specific masks directly from diffusion attention and progressively propagates them across frames efficiently. Extensive experiments demonstrate that FlexiMMT achieves precise, compositional, and state-of-the-art performance in I2V-based multi-object multi-motion transfer. Our project page is: https://ethan-li123.github.io/FlexiMMT_page/

cs.CV↗

arXiv2026

Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing

Recent advances in diffusion-based video generation have substantially improved visual fidelity and temporal coherence. However, most existing approaches remain task-specific and rely primarily on textual instructions, limiting their ability to handle multimodal inputs, contextual references, and diverse video generation and editing scenarios within a unified framework. Moreover, many video editing methods depend on carefully engineered pipelines tailored to individual operations, which hinders scalability and composability. In this paper, we propose Tele-Omni, a unified multimodal framework for video generation and editing that follows multimodal instructions, including text, images, and reference videos, within a single model. Tele-Omni leverages pretrained multimodal large language models to parse heterogeneous instructions and infer structured generation or editing intents, while diffusion-based generators perform high-quality video synthesis conditioned on these structured signals. To enable joint training across heterogeneous video tasks, we introduce a task-aware data processing pipeline that unifies multimodal inputs into a structured instruction format while preserving task-specific constraints. Tele-Omni supports a wide range of video-centric tasks, including text-to-video generation, image-to-video generation, first-last-frame video generation, in-context video generation, and in-context video editing. By decoupling instruction parsing from video synthesis and combining it with task-aware data design, Tele-Omni achieves flexible multimodal control while maintaining strong temporal coherence and visual consistency. Experimental results demonstrate that Tele-Omni achieves competitive performance across multiple tasks.

cs.CV↗

arXiv2025

3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image

3D texture swapping allows for the customization of 3D object textures, enabling efficient and versatile visual transformations in 3D editing. While no dedicated method exists, adapted 2D editing and text-driven 3D editing approaches can serve this purpose. However, 2D editing requires frame-by-frame manipulation, causing inconsistencies across views, while text-driven 3D editing struggles to preserve texture characteristics from reference images. To tackle these challenges, we introduce 3DSwapping, a 3D texture swapping method that integrates: 1) progressive generation, 2) view-consistency gradient guidance, and 3) prompt-tuned gradient guidance. To ensure view consistency, our progressive generation process starts by editing a single reference image and gradually propagates the edits to adjacent views. Our view-consistency gradient guidance further reinforces consistency by conditioning the generation model on feature differences between consistent and inconsistent outputs. To preserve texture characteristics, we introduce prompt-tuning-based gradient guidance, which learns a token that precisely captures the difference between the reference image and the 3D object. This token then guides the editing process, ensuring more consistent texture preservation across views. Overall, 3DSwapping integrates these novel strategies to achieve higher-fidelity texture transfer while preserving structural coherence across multiple viewpoints. Extensive qualitative and quantitative evaluations confirm that our three novel components enable convincing and effective 2D texture swapping for 3D objects. Code will be available upon acceptance.

cs.CV↗

arXiv2025

Positivity bounds in scalar-QED EFT at one-loop level

Understanding the implication of positivity bounds on loop-generated dim-8 operator coefficients is a nontrivial task, as these bounds only strictly hold when all the contributions are included in the dispersion relation up to a certain loop order in the UV theory. As a step towards more realistic gauge theories such as the Standard Model, in this paper we study the positivity bounds in the Scalar QED Effective Field Theory (EFT) from the scalar-photon scattering ($γϕ\to γϕ$) and the photon-photon scattering ($γγ\to γγ$), derived from the dispersion relation of the full one-loop EFT amplitudes. Assuming the UV theory is weakly coupled and all heavy particles have spin $\leq1$, the leading dim-8 interaction for both amplitudes are generated at the one-loop level in the UV theory. Gauge invariance imposes strong constraints on the loop structures, while potential IR divergences also require careful treatments. Our findings reveal that, for $γϕ\to γϕ$, while the tree-level bound does not necessarily hold, the one-loop $β$-function of the corresponding coefficient always tends to restore the tree-level bound in the IR, unless its actual loop order in the UV theory is further suppressed. For $γγ\to γγ$, on the other hand, the tree-level positivity bound is still robust at the one-loop level in the UV theory. These findings are verified in two example UV models with a heavy scalar extension. Importantly, the bounds on the $β$-functions that we obtain should be considered as an accidental feature at one loop, rather than a fundamental property of the theory.

hep-ph↗

arXiv2025

A Dual Active Black Hole Candidate with Mass Ratio ~7:1 in a Disk Galaxy

Dual active galactic nuclei (AGNs) with comparable masses are commonly witnessed among the major merged galaxies with interaction remnants. Considering almost every massive galaxy is associated with multiple dwarf satellites around it, minor mergers involving galaxies with disproportional stellar masses should be much more common than major mergers, which would naturally lead to black hole (BH) pairs with significantly different masses. However, dual AGNs generated by minor mergers involving one or two dwarf galaxies are exceptionally rare and understudied. Moreover, good estimates of the masses of both BHs are not yet available to test this idea. Here we report the evidence of a dual AGN candidate with mass ratio $\sim$7:1 located in an undisturbed disk galaxy. We identify the central BH with mass of $9.4 \times 10^6M_\odot$ from its radio emission as well as AGN-driven galactic-scale biconical outflows. The off-centered BH generates obvious broad and narrow emission-line regions, which gives us a robust estimation of a $1.3 \times 10^6M_\odot$ BH mass. We explore alternative scenarios for explaining the observational features of this system, including the complex gas kinematics triggered by central AGN activity and dust attenuation of the broad-line region of the central BH, finding that they failed to fully account for the kinematics of both the redshifted off-centered broad and narrow emission-line components.

astro-ph.GA↗

arXiv2024

SSNeRF: Sparse View Semi-supervised Neural Radiance Fields with Augmentation

Sparse view NeRF is challenging because limited input images lead to an under constrained optimization problem for volume rendering. Existing methods address this issue by relying on supplementary information, such as depth maps. However, generating this supplementary information accurately remains problematic and often leads to NeRF producing images with undesired artifacts. To address these artifacts and enhance robustness, we propose SSNeRF, a sparse view semi supervised NeRF method based on a teacher student framework. Our key idea is to challenge the NeRF module with progressively severe sparse view degradation while providing high confidence pseudo labels. This approach helps the NeRF model become aware of noise and incomplete information associated with sparse views, thus improving its robustness. The novelty of SSNeRF lies in its sparse view specific augmentations and semi supervised learning mechanism. In this approach, the teacher NeRF generates novel views along with confidence scores, while the student NeRF, perturbed by the augmented input, learns from the high confidence pseudo labels. Our sparse view degradation augmentation progressively injects noise into volume rendering weights, perturbs feature maps in vulnerable layers, and simulates sparse view blurriness. These augmentation strategies force the student NeRF to recognize degradation and produce clearer rendered views. By transferring the student's parameters to the teacher, the teacher gains increased robustness in subsequent training iterations. Extensive experiments demonstrate the effectiveness of our SSNeRF in generating novel views with less sparse view degradation. We will release code upon acceptance.

cs.CV↗

arXiv2024

Towards Better Text-to-Image Generation Alignment via Attention Modulation

In text-to-image generation tasks, the advancements of diffusion models have facilitated the fidelity of generated results. However, these models encounter challenges when processing text prompts containing multiple entities and attributes. The uneven distribution of attention results in the issues of entity leakage and attribute misalignment. Training from scratch to address this issue requires numerous labeled data and is resource-consuming. Motivated by this, we propose an attribution-focusing mechanism, a training-free phase-wise mechanism by modulation of attention for diffusion model. One of our core ideas is to guide the model to concentrate on the corresponding syntactic components of the prompt at distinct timesteps. To achieve this, we incorporate a temperature control mechanism within the early phases of the self-attention modules to mitigate entity leakage issues. An object-focused masking scheme and a phase-wise dynamic weight control mechanism are integrated into the cross-attention modules, enabling the model to discern the affiliation of semantic information between entities more effectively. The experimental results in various alignment scenarios demonstrate that our model attain better image-text alignment with minimal additional computational cost.

cs.CL↗

arXiv2024

Properties of a Fading AGN from SDSS-IV MaNGA

We identify a fading AGN SDSS J220141.64+115124.3 from the internal Product Launch-11 (MPL-11) in Mapping Nearby Galaxies at Apache Point Observatory (MaNGA) survey. The central region with a projected radius of $\sim$2.4 kpc is characterized as LINER-like line ratios while the outskirts extended to $\sim$15 kpc show Seyfert-like line ratios. The [OIII]$λ$5007 luminosity of the Seyfert regions is a factor of 37 (2) higher than the LINER regions without (with) dust attenuation correction, suggesting that the AGN activity decreases at least $\sim$8 $\times$ 10$^3$ yrs ($\sim$2.4 kpc/light-speed) ago. We model the emission line spectra in the central region with double Gaussian components (a narrow core and a broad wing) and analyze the properties of each component. The narrow core component mostly co-rotates with the stellar disc, whereas the broad wing component with a median of the velocity dispersion $\sim$300 km s$^{-1}$ is related to a wind outflow. The kinematic position angle (PA) of the ionized gas shows a $\sim$20° twist from the galaxy center to 1.5 effective radius. The median of the PA difference between the gas and stellar components is as large as $\sim$50° within 0.4 effective radius. The tidal feature in DESI image and star-gas misalignment suggest this galaxy is a merger remnant. Combining all these observational results as well as public available X-ray and MIR luminosities, we confirm this is a fading AGN, the merger process kick-started the central engine to quasar phase which ionized gas composed of tidal debris, and now the activity of the central black hole decreases. The discontinuity in [OIII]$λ$5007 flux and EQW maps is due to multiple AGN outbursts triggered by merger remnant gas inflows.

astro-ph.GA↗

arXiv2023

Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning

Representation learning for images has been advanced by recent progress in more complex neural models such as the Vision Transformers and new learning theories such as the structural causal models. However, these models mainly rely on the classification loss to implicitly regularize the class-level data distributions, and they may face difficulties when handling classes with diverse visual patterns. We argue that the incorporation of the structural information between data samples may improve this situation. To achieve this goal, this paper presents a framework termed \textbf{C}lass-level Structural Relation Modeling and Smoothing for Visual Representation Learning (CSRMS), which includes the Class-level Relation Modelling, Class-aware Graph Sampling, and Relational Graph-Guided Representation Learning modules to model a relational graph of the entire dataset and perform class-aware smoothing and regularization operations to alleviate the issue of intra-class visual diversity and inter-class similarity. Specifically, the Class-level Relation Modelling module uses a clustering algorithm to learn the data distributions in the feature space and identify three types of class-level sample relations for the training set; Class-aware Graph Sampling module extends typical training batch construction process with three strategies to sample dataset-level sub-graphs; and Relational Graph-Guided Representation Learning module employs a graph convolution network with knowledge-guided smoothing operations to ease the projection from different visual patterns to the same class. Experiments demonstrate the effectiveness of structured knowledge modelling for enhanced representation learning and show that CSRMS can be incorporated with any state-of-the-art visual representation learning models for performance gains. The source codes and demos have been released at https://github.com/czt117/CSRMS.

cs.CV↗

arXiv2022

Multiple gas acquisition events in galaxies with dual misaligned gas disks

Frequent accretion of external cold gas is thought to play an important role in galaxy assembly. However, almost all known kinematically misaligned galaxies identify only one gas disk that is misaligned with the stellar disk, implying a single gas acquisition event. Here we report a new configuration in two galaxies where both contain two gas disks misaligned with each other and also with the stellar disk. Such systems are not expected to be stable or long-lasting, challenging the traditional picture of gas accretion of galaxies and their angular momentum build-up. The differences in kinematic position angles are larger than 120° between the two gas disks, and 40° between each gas disk and the stellar component. The star formation activity is enhanced at the interface of the two gas disks compared with the other regions within the same galaxy. Such systems illustrate that low-redshift galaxies can still experience multiple gas acquisition events, and provide a new view into the origins of galactic gas.

astro-ph.GA↗

arXiv2022

Multi-modal Video Chapter Generation

Chapter generation becomes practical technique for online videos nowadays. The chapter breakpoints enable users to quickly find the parts they want and get the summative annotations. However, there is no public method and dataset for this task. To facilitate the research along this direction, we introduce a new dataset called Chapter-Gen, which consists of approximately 10k user-generated videos with annotated chapter information. Our data collection procedure is fast, scalable and does not require any additional manual annotation. On top of this dataset, we design an effective baseline specificlly for video chapters generation task. which captures two aspects of a video,including visual dynamics and narration text. It disentangles local and global video features for localization and title generation respectively. To parse the long video efficiently, a skip sliding window mechanism is designed to localize potential chapters. And a cross attention multi-modal fusion module is developed to aggregate local features for title generation. Our experiments demonstrate that the proposed framework achieves superior results over existing methods which illustrate that the method design for similar task cannot be transfered directly even after fine-tuning. Code and dataset are available at https://github.com/czt117/MVCG.

cs.CV↗

arXiv2022

SDSS-IV MaNGA : spatial resolved properties of kinematically misaligned galaxies

We select 456 galaxies with kinematically misaligned gas and stellar components from 9546 parent galaxies in MaNGA, and classify them into 72 star-forming galaxies, 142 green-valley galaxies and 242 quiescent galaxies. Comparing the spatial resolved properties of the misaligned galaxies with control samples closely match in the D$_n$4000 and stellar velocity dispersion, we find that: (1) the misaligned galaxies have lower values in $V_{\rm gas}/σ_{\rm gas}$ and $V_{\rm star}/σ_{\rm star}$ (the ratio between ordered to random motion of gas and stellar components) across the entire galaxies than their control samples; (2) the star-forming and green-valley misaligned galaxies have enhanced central concentrated star formation than their control galaxies. The difference in stellar population between quiescent misaligned galaxies and control samples is small; (3) gas-phase metallicity of the green valley and quiescent misaligned galaxies are lower than the control samples. For the star forming misaligned galaxies, the difference in metallicity between the misaligned galaxies and their control samples strongly depends on how we select the control samples. All these observational results suggest external gas accretion influences the evolution of star forming and green valley galaxies, not only in kinematics/morphologies, but also in stellar populations. However, the quiescent misaligned galaxies have survived from different formation mechanisms.

astro-ph.GA↗