arXiv subjects

Yao Yao

Publications and source records attributed to Yao Yao.

At least 73 records · Page 4Linked to original sources

arXiv2025

The Internal Kinematics, Stellar Population, and Gas-phase Properties of The Pseudobulge in An Ultra-diffuse Galaxy: AGC721966

Leveraging spectroscopic data from the Sloan Digital Sky Survey, we conduct a comprehensive analysis of the central stellar velocity dispersion, stellar population properties, star formation history, and gas-phase chemical abundances in AGC721966, a unique ultra-diffuse galaxy (UDG) harboring a pseudobulge. Our findings reveal that the pseudobulge formed in the early universe but underwent a recent episode of rejuvenated star formation. The system exhibits a mass-weighted (light-weighted) stellar population age of $τ_{\star}\sim 7.4\pm2.5$ ($2.9\pm1.5$)~Gyr, a stellar metallicity of [M/H]$\sim -0.62\pm0.26$ ($-0.55\pm0.20$), an $α$-element enhancement of [$α$/Fe]$\sim 0.36\pm0.09$ ($0.37\pm0.07$), and a gas-phase oxygen abundance of \Oabund$\sim 8.15\pm0.03$. The central stellar velocity dispersion is measured as $σ_{\rm c}\sim 57.9\pm15.7$~km/s. These results provide robust evidence supporting the early halo-halo merging formation scenario proposed by \cite{Rong25}, while unequivocally ruling out the ``failed'' $L^{\star}$ formation model, at least for AGC721966. Furthermore, through systematic application of the baryonic Tully-Fisher relation, we establish that these pseudobulge-hosting UDGs are neither misidentified nuclear star cluster-bearing dwarf galaxies nor bulge-dominated massive galaxies, thereby affirming their distinct evolutionary pathway.

astro-ph.GA↗

arXiv2025

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges. We introduce Direct3D-S2, a scalable 3D generation framework based on sparse volumes that achieves superior output quality with dramatically reduced training costs. Our key innovation is the Spatial Sparse Attention (SSA) mechanism, which greatly enhances the efficiency of Diffusion Transformer (DiT) computations on sparse volumetric data. SSA allows the model to effectively process large token sets within sparse volumes, substantially reducing computational overhead and achieving a 3.9x speedup in the forward pass and a 9.6x speedup in the backward pass. Our framework also includes a variational autoencoder (VAE) that maintains a consistent sparse volumetric format across input, latent, and output stages. Compared to previous methods with heterogeneous representations in 3D VAE, this unified design significantly improves training efficiency and stability. Our model is trained on public available datasets, and experiments demonstrate that Direct3D-S2 not only surpasses state-of-the-art methods in generation quality and efficiency, but also enables training at 1024 resolution using only 8 GPUs, a task typically requiring at least 32 GPUs for volumetric representations at 256 resolution, thus making gigascale 3D generation both practical and accessible. Project page: https://www.neural4d.com/research/direct3d-s2.

cs.CV↗

arXiv2025

JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models

Music generation has attracted growing interest with the advancement of deep generative models. However, generating music conditioned on textual descriptions, known as text-to-music, remains challenging due to the complexity of musical structures and high sampling rate requirements. Despite the task's significance, prevailing generative models exhibit limitations in music quality, computational efficiency, and generalization. This paper introduces JEN-1, a universal high-fidelity model for text-to-music generation. JEN-1 is a diffusion model incorporating both autoregressive and non-autoregressive training. Through in-context learning, JEN-1 performs various generation tasks including text-guided music generation, music inpainting, and continuation. Evaluations demonstrate JEN-1's superior performance over state-of-the-art methods in text-music alignment and music quality while maintaining computational efficiency. Our demos are available at https://jenmusic.ai/audio-demos

cs.SD↗

arXiv2025

A negative stellar mass$-$gaseous metallicity gradient relation of dwarf galaxies modulated by stellar feedback

Baryonic cycling is reflected in the spatial distribution of metallicity within galaxies, yet gas-phase metallicity distribution and its connection with other properties of dwarf galaxies are largely unexplored. We present the first systematic study of radial gradients of gas-phase metallicities for a sample of 55 normal nearby star-forming dwarf galaxies (stellar mass $M_\star$ ranging from $10^7$ to $10^{9.5}\ M_\odot$), based on MUSE spectroscopic observations. We find that metallicity gradient shows a significant negative correlation (correlation coefficient $r \approx -0.56$) with $\log M_\star$, in contrast to the flat or even positive correlation observed for higher-mass galaxies. This negative correlation is accompanied by a stronger central suppression of metallicity compared to the outskirts in lower-mass galaxies. Among the other explored galaxy properties-including baryonic mass, star formation distribution, galaxy environment, regularity of the gaseous velocity field, and effective yield of metals $y_{\rm eff}$-only the velocity field regularity and $y_{\rm eff}$ show residual correlation with the metallicity gradient after controlling for $M_\star$, in the sense that galaxies with irregular velocity fields or lower $y_{\rm eff}$ tend to have less negative or more positive gradients. Particularly, a linear combination of $\log M_\star$ and $\log y_{\rm eff}$ significantly improves the correlation with metallicity gradient ($r \approx -0.68$) compared to $\log M_\star$ alone. The lack of correlation with environment disfavors gas accretion as a dominant factor. Our findings imply that metal mixing and transport processes, including but not limited to feedback-driven outflows, are more important than in-situ metal production in shaping the metallicity distribution of dwarf galaxies.

astro-ph.GA↗

arXiv2025

Quantum cellular automata for word statistics facilitated by quantum correlations

We propose an iterative algorithm to investigate the cooperative evolution dominated by information encoded within state spaces in a random quantum cellular automaton. Inspired by the 2-gram model in statistical linguistics, the updates of quantum states are determined by a given corpus, which serves as the interactions to induce quantum correlations. These local cooperative interactions lead to block-diagonal evolution quantified by the entanglement asymmetry. We evaluate the influence of two-site gates on the iteration process and reveal the associated search speedup. Crucially, we demonstrate the information scrambling dependent of gate sampling, uncovering an intriguing bond percolation. Our results provide an adaptive paradigm for quantum search algorithms and random many-body dynamics.

quant-ph↗

arXiv2025

A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety

In real-world applications, learning-enabled systems often undergo iterative model development to address challenging or emerging tasks, which involve collecting new data, training a new model and validating the model. This continual model development process raises a significant issue that acquiring new or improving existing capabilities may inadvertently lose good capabilities of the old model, also known as catastrophic forgetting. While existing continual learning aims to mitigate catastrophic forgetting by trading off performance on previous tasks and new tasks to ensure good average performance, it often falls short in cost-sensitive applications, where failing to preserve essential established capabilities introduces unforeseen costs and risks and substantial expenses for re-improving these capabilities. To address this issue, we impose a requirement on learning systems to ensure that a new model strictly retains important capabilities of the old model while improving target-task performance, which we term model developmental safety. To ensure model developmental safety, we propose a retention-centric framework with data-dependent constraints, and study how to continually develop a pretrained CLIP model for acquiring new or improving existing capabilities of image classification. We propose an efficient constrained optimization algorithm with theoretical guarantees and use its insights to finetune the CLIP model with task-dependent heads for promoting the model developmental safety. Experiments on autonomous driving and scene recognition datasets validate the efficacy of our method.

cs.LG↗

arXiv2025

Can Multi-modal (reasoning) LLMs work as deepfake detectors?

Deepfake detection remains a critical challenge in the era of advanced generative models, particularly as synthetic media becomes more sophisticated. In this study, we explore the potential of state of the art multi-modal (reasoning) large language models (LLMs) for deepfake image detection such as (OpenAI O1/4o, Gemini thinking Flash 2, Deepseek Janus, Grok 3, llama 3.2, Qwen 2/2.5 VL, Mistral Pixtral, Claude 3.5/3.7 sonnet) . We benchmark 12 latest multi-modal LLMs against traditional deepfake detection methods across multiple datasets, including recently published real-world deepfake imagery. To enhance performance, we employ prompt tuning and conduct an in-depth analysis of the models' reasoning pathways to identify key contributing factors in their decision-making process. Our findings indicate that best multi-modal LLMs achieve competitive performance with promising generalization ability with zero shot, even surpass traditional deepfake detection pipelines in out-of-distribution datasets while the rest of the LLM families performs extremely disappointing with some worse than random guess. Furthermore, we found newer model version and reasoning capabilities does not contribute to performance in such niche tasks of deepfake detection while model size do help in some cases. This study highlights the potential of integrating multi-modal reasoning in future deepfake detection frameworks and provides insights into model interpretability for robustness in real-world scenarios.

cs.CV↗

arXiv2025

FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks

With the rapid advancements in diffusion models and 3D generation techniques, dynamic 3D content generation has become a crucial research area. However, achieving high-fidelity 4D (dynamic 3D) generation with strong spatial-temporal consistency remains a challenging task. Inspired by recent findings that pretrained diffusion features capture rich correspondences, we propose FB-4D, a novel 4D generation framework that integrates a Feature Bank mechanism to enhance both spatial and temporal consistency in generated frames. In FB-4D, we store features extracted from previous frames and fuse them into the process of generating subsequent frames, ensuring consistent characteristics across both time and multiple views. To ensure a compact representation, the Feature Bank is updated by a proposed dynamic merging mechanism. Leveraging this Feature Bank, we demonstrate for the first time that generating additional reference sequences through multiple autoregressive iterations can continuously improve generation performance. Experimental results show that FB-4D significantly outperforms existing methods in terms of rendering quality, spatial-temporal consistency, and robustness. It surpasses all multi-view generation tuning-free approaches by a large margin and achieves performance on par with training-based methods.

cs.CV↗

arXiv2025

Mani-GS: Gaussian Splatting Manipulation with Triangular Mesh

Neural 3D representations such as Neural Radiance Fields (NeRF), excel at producing photo-realistic rendering results but lack the flexibility for manipulation and editing which is crucial for content creation. Previous works have attempted to address this issue by deforming a NeRF in canonical space or manipulating the radiance field based on an explicit mesh. However, manipulating NeRF is not highly controllable and requires a long training and inference time. With the emergence of 3D Gaussian Splatting (3DGS), extremely high-fidelity novel view synthesis can be achieved using an explicit point-based 3D representation with much faster training and rendering speed. However, there is still a lack of effective means to manipulate 3DGS freely while maintaining rendering quality. In this work, we aim to tackle the challenge of achieving manipulable photo-realistic rendering. We propose to utilize a triangular mesh to manipulate 3DGS directly with self-adaptation. This approach reduces the need to design various algorithms for different types of Gaussian manipulation. By utilizing a triangle shape-aware Gaussian binding and adapting method, we can achieve 3DGS manipulation and preserve high-fidelity rendering after manipulation. Our approach is capable of handling large deformations, local manipulations, and soft body simulations while keeping high-quality rendering. Furthermore, we demonstrate that our method is also effective with inaccurate meshes extracted from 3DGS. Experiments conducted demonstrate the effectiveness of our method and its superiority over baseline approaches.

cs.GR↗

arXiv2025

FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video

Reconstructing high-fidelity, animatable 3D head avatars from effortlessly captured monocular videos is a pivotal yet formidable challenge. Although significant progress has been made in rendering performance and manipulation capabilities, notable challenges remain, including incomplete reconstruction and inefficient Gaussian representation. To address these challenges, we introduce FATE, a novel method for reconstructing an editable full-head avatar from a single monocular video. FATE integrates a sampling-based densification strategy to ensure optimal positional distribution of points, improving rendering efficiency. A neural baking technique is introduced to convert discrete Gaussian representations into continuous attribute maps, facilitating intuitive appearance editing. Furthermore, we propose a universal completion framework to recover non-frontal appearance, culminating in a 360$^\circ$-renderable 3D head avatar. FATE outperforms previous approaches in both qualitative and quantitative evaluations, achieving state-of-the-art performance. To the best of our knowledge, FATE is the first animatable and 360$^\circ$ full-head monocular reconstruction method for a 3D head avatar.

cs.CV↗

arXiv2025

Matrix3D: Large Photogrammetry Model All-in-One

We present Matrix3D, a unified model that performs several photogrammetry subtasks, including pose estimation, depth prediction, and novel view synthesis using just the same model. Matrix3D utilizes a multi-modal diffusion transformer (DiT) to integrate transformations across several modalities, such as images, camera parameters, and depth maps. The key to Matrix3D's large-scale multi-modal training lies in the incorporation of a mask learning strategy. This enables full-modality model training even with partially complete data, such as bi-modality data of image-pose and image-depth pairs, thus significantly increases the pool of available training data. Matrix3D demonstrates state-of-the-art performance in pose estimation and novel view synthesis tasks. Additionally, it offers fine-grained control through multi-round interactions, making it an innovative tool for 3D content creation. Project page: https://nju-3dv.github.io/projects/matrix3d.

cs.CV↗

arXiv2025

Track reconstruction as a service for collider physics

Optimizing charged-particle track reconstruction algorithms is crucial for efficient event reconstruction in Large Hadron Collider (LHC) experiments due to their significant computational demands. Existing track reconstruction algorithms have been adapted to run on massively parallel coprocessors, such as graphics processing units (GPUs), to reduce processing time. Nevertheless, challenges remain in fully harnessing the computational capacity of coprocessors in a scalable and non-disruptive manner. This paper proposes an inference-as-a-service approach for particle tracking in high energy physics experiments. To evaluate the efficacy of this approach, two distinct tracking algorithms are tested: Patatrack, a rule-based algorithm, and Exa$.$TrkX, a machine learning-based algorithm. The as-a-service implementations show enhanced GPU utilization and can process requests from multiple CPU cores concurrently without increasing per-request latency. The impact of data transfer is minimal and insignificant compared to running on local coprocessors. This approach greatly improves the computational efficiency of charged particle tracking, providing a solution to the computing challenges anticipated in the High-Luminosity LHC era.

physics.ins-det↗

arXiv2025

How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival human capabilities in various domains, we are presented with a unique testbed to investigate human cognition through a new lens. Among the many facets of cognition, one particularly crucial aspect is the concept of semantic size, the perceived magnitude of both abstract and concrete words or concepts. This study seeks to investigate whether LLMs exhibit similar tendencies in understanding semantic size, thereby providing insights into the underlying mechanisms of human cognition. We begin by exploring metaphorical reasoning, comparing how LLMs and humans associate abstract words with concrete objects of varying sizes. Next, we examine LLMs' internal representations to evaluate their alignment with human cognitive processes. Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding, suggesting that real-world, multi-modal experiences are similarly vital for human cognitive development. Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario. The results show that multi-modal LLMs are more emotionally engaged in decision-making, but this also introduces potential biases, such as the risk of manipulation through clickbait headlines. Ultimately, this study offers a novel perspective on how LLMs interpret and internalize language, from the smallest concrete objects to the most profound abstract concepts like love. The insights gained not only improve our understanding of LLMs but also provide new avenues for exploring the cognitive abilities that define human intelligence.

cs.CL↗

arXiv2025

LESA: Learnable LLM Layer Scaling-Up

Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. However, existing depth scaling-up methods rely on empirical heuristic rules for layer duplication, which result in poorer initialization and slower convergence during continual pre-training. We propose \textbf{LESA}, a novel learnable method for depth scaling-up. By concatenating parameters from each layer and applying Singular Value Decomposition, we uncover latent patterns between layers, suggesting that inter-layer parameters can be learned. LESA uses a neural network to predict the parameters inserted between adjacent layers, enabling better initialization and faster training. Experiments show that LESA outperforms existing baselines, achieving superior performance with less than half the computational cost during continual pre-training. Extensive analyses demonstrate its effectiveness across different model sizes and tasks.

cs.LG↗

arXiv2025

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors

3D Gaussian Splatting (3DGS) has achieved excellent rendering quality with fast training and rendering speed. However, its optimization process lacks explicit geometric constraints, leading to suboptimal geometric reconstruction in regions with sparse or no observational input views. In this work, we try to mitigate the issue by incorporating a pre-trained matching prior to the 3DGS optimization process. We introduce Flow Distillation Sampling (FDS), a technique that leverages pre-trained geometric knowledge to bolster the accuracy of the Gaussian radiance field. Our method employs a strategic sampling technique to target unobserved views adjacent to the input views, utilizing the optical flow calculated from the matching model (Prior Flow) to guide the flow analytically calculated from the 3DGS geometry (Radiance Flow). Comprehensive experiments in depth rendering, mesh reconstruction, and novel view synthesis showcase the significant advantages of FDS over state-of-the-art methods. Additionally, our interpretive experiments and analysis aim to shed light on the effects of FDS on geometric accuracy and rendering quality, potentially providing readers with insights into its performance. Project page: https://nju-3dv.github.io/projects/fds

cs.CV↗

arXiv2025

JAMMit! Monolithic 3D-Printing of a Bead Jamming Soft Pneumatic Arm

3D-printed bellow soft pneumatic arms are widely adopted for their flexible design, ease of fabrication, and large deformation capabilities. However, their low stiffness limits their real-world applications. Although several methods exist to enhance the stiffness of soft actuators, many involve complex manufacturing processes not in line with modern goals of monolithic and automated additive manufacturing. With its simplicity, bead-jamming represents a simple and effective solution to these challenges. This work introduces a method for monolithic printing of a bellow soft pneumatic arm, integrating a tendon-driven central spine of bowl-shaped beads. We experimentally characterized the arm's range of motion in both unjammed and jammed states, as well as its stiffness under various actuation and jamming conditions. As a result, we provide an optimal jamming policy as a trade-off between preserving the range of motion and maximizing stiffness. The proposed design was further demonstrated in a switch-toggling task, showing its potential for practical applications.

cs.RO↗

arXiv2025

The circumgalactic medium traced by Mg II absorption with DESI: dependence on galaxy stellar mass, star formation rate and azimuthal angle

Understanding the circumgalactic medium (CGM) distribution of galaxies is the key to revealing the dynamical exchange of materials between galaxies and their surroundings. In this work, we use DESI EDR dataset to investigate the cool CGM of galaxies ($0.3 10.0$, the EW(Mg II) at the minor axis is largely suppressed with respect to low mass galaxies. This suggests that the competing processes, such as stellar feedback and gravity, play a key role in shaping the distribution of outflowing gas.

astro-ph.GA↗

arXiv2025

Tunable superconductivity coexisting with the anomalous Hall effect in 1T'-WS2

Transition metal dichalcogenides are a family of quasi-two-dimensional materials that display a high technological potential due to their wide range of electronic ground states, e.g., from superconducting to semiconducting, depending on the chemical composition, crystal structure, or electrostatic doping. Here, we unveil that by tuning a single parameter, the hydrostatic pressure P, a cascade of electronic phase transitions can be induced in the few-layer transition metal dichalcogenide 1T'-WS2, including superconducting, topological, and anomalous Hall effect phases. Specifically, as P increases, we observe a dual phase transition: the suppression of superconductivity with the concomitant emergence of an anomalous Hall effect at P=1.15 GPa. Remarkably, upon further increasing the pressure above 1.6 GPa, we uncover a reentrant superconducting state that emerges out of a state still exhibiting an anomalous Hall effect. This superconducting state shows a marked increase in superconducting anisotropy with respect to the phase observed at ambient pressure, suggesting a different superconducting state with a distinct pairing symmetry. Via first-principles calculations, we demonstrate that the system concomitantly transitions into a strong topological phase with markedly different band orbital characters and Fermi surfaces contributing to the superconductivity. These findings position 1T'-WS2 as a unique, tunable superconductor, wherein superconductivity, anomalous transport, and band features can be tuned through the application of moderate pressures.

cond-mat.supr-con↗