arXiv subjects

Nian Liu

Publications and source records attributed to Nian Liu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Video Echoed in Music: Semantic, Temporal, and Rhythmic Alignment for Video-to-Music Generation

Video-to-Music generation seeks to generate musically appropriate background music that enhances audiovisual immersion for videos. However, current approaches suffer from two critical limitations: 1) incomplete representation of video details, leading to weak alignment, and 2) inadequate temporal and rhythmic correspondence, particularly in achieving precise beat synchronization. To address the challenges, we propose Video Echoed in Music (VeM), a latent music diffusion that generates high-quality soundtracks with semantic, temporal, and rhythmic alignment for input videos. To capture video details comprehensively, VeM employs a hierarchical video parsing that acts as a music conductor, orchestrating multi-level information across modalities. Modality-specific encoders, coupled with a storyboard-guided cross-attention mechanism (SG-CAtt), integrate semantic cues while maintaining temporal coherence through position and duration encoding. For rhythmic precision, the frame-level transition-beat aligner and adapter (TB-As) dynamically synchronize visual scene transitions with music beats. We further contribute a novel video-music paired dataset sourced from e-commerce advertisements and video-sharing platforms, which imposes stricter transition-beat synchronization requirements. Meanwhile, we introduce novel metrics tailored to the task. Experimental results demonstrate superiority, particularly in semantic relevance and rhythmic precision.

cs.SD↗

arXiv2025

TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models

Audio-Visual Segmentation (AVS) faces a fundamental challenge of effectively aligning audio and visual modalities. While recent approaches leverage foundation models to address data scarcity, they often rely on single-modality knowledge or combine foundation models in an off-the-shelf manner, failing to address the cross-modal alignment challenge. In this paper, we present TAViS, a novel framework that \textbf{couples} the knowledge of multimodal foundation models (ImageBind) for cross-modal alignment and a segmentation foundation model (SAM2) for precise segmentation. However, effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision. To address these challenges, we introduce a text-bridged design with two key components: (1) a text-bridged hybrid prompting mechanism where pseudo text provides class prototype information while retaining modality-specific details from both audio and visual inputs, and (2) an alignment supervision strategy that leverages text as a bridge to align shared semantic concepts within audio-visual modalities. Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.

cs.CV↗

arXiv2025

AURORA:Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation

Reference Audio-Visual Segmentation (Ref-AVS) tasks challenge models to precisely locate sounding objects by integrating visual, auditory, and textual cues. Existing methods often lack genuine semantic understanding, tending to memorize fixed reasoning patterns. Furthermore, jointly training for reasoning and segmentation can compromise pixel-level precision. To address these issues, we introduce AURORA, a novel framework designed to enhance genuine reasoning and language comprehension in reference audio-visual segmentation. We employ a structured Chain-of-Thought (CoT) prompting mechanism to guide the model through a step-by-step reasoning process and introduce a novel segmentation feature distillation loss to effectively integrate these reasoning abilities without sacrificing segmentation performance. To further cultivate the model's genuine reasoning capabilities, we devise a further two-stage training strategy: first, a ``corrective reflective-style training" stage utilizes self-correction to enhance the quality of reasoning paths, followed by reinforcement learning via Group Reward Policy Optimization (GRPO) to bolster robustness in challenging scenarios. Experiments demonstrate that AURORA achieves state-of-the-art performance on Ref-AVS benchmarks and generalizes effectively to unreferenced segmentation.

cs.CV↗

arXiv2025

Saliency-R1: Incentivizing Unified Saliency Reasoning Capability in MLLM with Confidence-Guided Reinforcement Learning

Although multimodal large language models (MLLMs) excel in high-level vision-language reasoning, they lack inherent awareness of visual saliency, making it difficult to identify key visual elements. To bridge this gap, we propose Saliency-R1, the first unified MLLM framework that jointly tackles three representative and heterogeneous saliency tasks: Salient Object Detection (SOD), Salient Instance Segmentation (SIS), and Co-salient Object Detection (CoSOD), enhancing the model's capacity for saliency reasoning. We introduce a textual interface with structured tags ( , ) to encode region- and instance-level referring expressions, enabling a single referring segmenter to produce task-appropriate masks. To train the MLLM efficiently, we propose Confidence-Guided Policy Optimization (CGPO), a novel single-sample reinforcement learning algorithm. CGPO improves on GRPO by replacing group-normalized advantages with a per-sample signal based on reward-confidence discrepancy, thereby reducing computational waste, mitigating signal dilution, and lowering training overhead. Our model exceeds or matches the performance of robust open/closed-source MLLMs and specialized state-of-the-art methods across all three tasks, demonstrating the efficacy of our framework in saliency reasoning.

cs.CV↗

arXiv2025

Diversity Has Always Been There in Your Visual Autoregressive Models

Visual Autoregressive (VAR) models have recently garnered significant attention for their innovative next-scale prediction paradigm, offering notable advantages in both inference efficiency and image quality compared to traditional multi-step autoregressive (AR) and diffusion models. However, despite their efficiency, VAR models often suffer from the diversity collapse i.e., a reduction in output variability, analogous to that observed in few-step distilled diffusion models. In this paper, we introduce DiverseVAR, a simple yet effective approach that restores the generative diversity of VAR models without requiring any additional training. Our analysis reveals the pivotal component of the feature map as a key factor governing diversity formation at early scales. By suppressing the pivotal component in the model input and amplifying it in the model output, DiverseVAR effectively unlocks the inherent generative potential of VAR models while preserving high-fidelity synthesis. Empirical results demonstrate that our approach substantially enhances generative diversity with only neglectable performance influences. Our code will be publicly released at https://github.com/wangtong627/DiverseVAR.

cs.CV↗

arXiv2025

Irregular sets for a class of skew product transformations

In this paper, we study the irregular set of any continuous observable for a class of skew product transformations, which is driven by a uniquely ergodic homeomorphism system $(Ω,\mathbb{P},θ)$ and satisfies Anosov and toplogical mixing on fibers property. We prove that if the irregular set of any continuous observable is nonempty on a fiber, then the irregular set must be nonempty, residual, and carry full fiber topological entropy on $\mathbb{P}$-a.e. fibers. The orbit-gluing technique provided by the fiber specification property are utilized.

math.DS↗

arXiv2025

A Data-constrained Magnetohydrodynamic Simulation of Successive X-class Flares in Solar Active Region 13842. II. Dynamics of the Solar Eruption Associated with the X9.0 Solar Flare

Active region NOAA 13842 produced two successive solar flares: an X7.1-class flare on October 1, 2024, and an X9.0-class flare on October 3, 2024. This study continues our previous simulation work that successfully reproduced the X7.1-class solar flare (Matsumoto et al. 2025). In this study, we performed a data-constrained magnetohydrodynamic (MHD) simulation using the nonlinear force-free field (NLFFF) as the initial condition to investigate the X9.0-class solar flare. The NLFFF showed the sheared field lines, resulting in the tether-cutting reconnection, the magnetic flux ropes (MFRs), and eventually led to eruption. The magnetic reconnection during the pre-eruption phase plays a critical role in accelerating the subsequent eruption, which is driven by torus instability and magnetic reconnection. Furthermore, our simulation results are consistent with several observational features associated with the X9.0 flare. This simulation could reproduce diverse phenomena associated with the X9.0 flare, including the tether-cutting reconnection, the flare ribbons and the flare loops, the transverse field enhancement, and the remote brightening away from the flare ribbons. However, the initial trigger, magnetic flux emergence, was inferred from observations rather than explicitly modeled, and future comprehensive simulations should incorporate this mechanism directly.

astro-ph.SR↗

arXiv2025

RAGNet: Large-scale Reasoning-based Affordance Segmentation Benchmark towards General Grasping

General robotic grasping systems require accurate object affordance perception in diverse open-world scenarios following human instructions. However, current studies suffer from the problem of lacking reasoning-based large-scale affordance prediction data, leading to considerable concern about open-world effectiveness. To address this limitation, we build a large-scale grasping-oriented affordance segmentation benchmark with human-like instructions, named RAGNet. It contains 273k images, 180 categories, and 26k reasoning instructions. The images cover diverse embodied data domains, such as wild, robot, ego-centric, and even simulation data. They are carefully annotated with an affordance map, while the difficulty of language instructions is largely increased by removing their category name and only providing functional descriptions. Furthermore, we propose a comprehensive affordance-based grasping framework, named AffordanceNet, which consists of a VLM pre-trained on our massive affordance data and a grasping network that conditions an affordance map to grasp the target. Extensive experiments on affordance segmentation benchmarks and real-robot manipulation tasks show that our model has a powerful open-world generalization ability. Our data and code is available at https://github.com/wudongming97/AffordanceNet.

cs.CV↗

arXiv2025

Precise Asteroseismology of the High-amplitude Delta Scuti Star EH Librae, an AE UMa Analogue in the Hertzsprung Gap

A subclass of intermediate mass variables Delta Scuti stars, known as High-amplitude Delta Scuti (HADS) stars, exhibits pronounced radial pulsations with high amplitudes. The ground-based and space-based observations of the HADS star EH Lib are used to help making asteroseismological analysis of this pulsating star. Following the reduction of the light curves, the frequency analysis reveals the fundamental frequency as $f_0=11.3105$ c day$^{-1}$ and two more significant frequencies $f_1$ and $f_2$, in addition to the harmonics of $f_0$ and a linear combination. The period change rate is determined as $(1/P_0)(dP_0/dt)=(5.4\pm0.5)\times10^{-9}$ yr$^{-1}$ derived from an O-C diagram, which is constructed from 342 times of maximum light spanning over 70 years. Using these observational constraints, along with the metallicity reported in the literature, we construct theoretical models using the stellar evolution code MESA and calculate the theoretical frequencies of the eigen modes using the oscillation code GYRE. The appropriate models are selected by matching both $f_0$ and $(1/P_0)(dP_0/dt)$ within their respective uncertainties. The results indicate that the observed period change of EH Lib can be attributed to stellar evolutionary effects. The stellar parameters of EH Lib are derived as: the mass of $1.715\pm0.065$ M$_{\odot}$, the luminosity of log $(L/L_{\odot})=1.38\pm0.06$, and the age of $(1.14\pm0.13)\times10^{9}$ years. EH Lib is classified as a single-mode HADS star, locating currently in the Hertzsprung gap, with a helium core and a hydrogen-burning shell. This work expands the asteroseismological sample of HADS stars and establishes a foundation for future investigations into their commonalities and specific properties, thereby advancing our understanding of these variables.

astro-ph.SR↗

arXiv2025

An eco-friendly universal strategy via ribavirin to achieve highly efficient and stable perovskite solar cells

The grain boundaries of perovskite films prepared by the solution method are highly disordered, with a large number of defects existing at the grain boundaries. These defect sites promote the decomposition of perovskite. Here, we use ribavirin obtained through bacillus subtilis fermentation to regulate the crystal growth of perovskite, inducing changes in the work function and energy level structure of perovskite, which significantly reduces the defect density. Based on density functional theory calculations, the defect formation energies of VI, VMA, VPb, and PbI in perovskite are improved. This increases the open-circuit voltage of perovskite solar cells (PSCs) (ITO/PEDOT:PSS/perovskite/PCBM/BCP/Ag) from 1.077 to 1.151 V, and the PCE increases significantly from 17.05% to 19.86%. Unencapsulated PSCs were stored in the environment (humidity approximately 35+-5%) for long-term stability testing. After approximately 900 hours of storage, the PCE of the ribavirin-based device retains 84.33% of its initial PCE, while the control-based device retains only 13.44% of its initial PCE. The PCE of PSCs (ITO/SnO2/perovskite/Spiro-OMETAD/Ag) is increased from 20.16% to 22.14%, demonstrating the universality of this doping method. This universal doping strategy provides a new approach for improving the efficiency and stability of PSCs using green molecular doping strategies.

cond-mat.mtrl-sci↗

arXiv2025

FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering

Large Language Models (LLMs) are often challenged by generating erroneous or hallucinated responses, especially in complex reasoning tasks. Leveraging Knowledge Graphs (KGs) as external knowledge sources has emerged as a viable solution. However, existing KG-enhanced methods, either retrieval-based or agent-based, encounter difficulties in accurately retrieving knowledge and efficiently traversing KGs at scale. In this paper, we propose a unified framework, FiDeLiS, designed to improve the factuality of LLM responses by anchoring answers to verifiable reasoning steps retrieved from KGs. To achieve this, we leverage step-wise beam search with a deductive scoring function, allowing the LLM to validate reasoning process step by step, and halt the search once the question is deducible. In addition, we propose a Path-RAG module to pre-select a smaller candidate set for each beam search step, reducing computational costs by narrowing the search space. Extensive experiments show that our method, as a training-free framework, not only improve the performance but also enhance the factuality and interpretability across different benchmarks. Code is released at https://github.com/Y-Sui/FiDeLiS.

cs.AI↗

arXiv2025

Angle-dependent resonant tunneling and thermoelectric energy management in a hybrid 1D-2D-1D semiconductor nanostructure

Low-dimensional semiconductors have been widely exploited in thermoelectric energy conversion for high efficiencies due to their suppressed lattice thermal conduction, sharply defined electronic density of states, and tunable energy-selective electron transmission. However, the widespread challenge of Fermi-level pinning or doping constraints limit precise control over thermoelectric energy management via chemical potential modulation. Here, we proposed an alternative strategy: leveraging angle-dependent electron incidence to dynamically manipulate electron transmission and heat transport, which was implemented theoretically in a two-dimensional InP/InAs/InP double-barrier heterostructure integrated with laterally one-dimensional electrodes. By combining the transfer matrix method and Landauer formalism, we demonstrated the angle-dependent resonant tunneling dynamics, tunable negative differential resistance effect, and near-Carnot limits in thermoelectric energy conversions. Angular modulation enables precise control over transmission resonances, facilitating dynamic transitions among thermoelectric regimes (power generation, cooling, and hybrid heating) without requiring extreme chemical potential shifts. This work establishes angularly resolved electron transmission as a versatile mechanism for on-chip thermal management and cryogenic applications, offering a pathway to circumvent material limitations in next-generation nanoelectronics and quantum devices.

cond-mat.mes-hall↗

arXiv2025

A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition

Spectral graph convolution, an important tool of data filtering on graphs, relies on two essential decisions: selecting spectral bases for signal transformation and parameterizing the kernel for frequency analysis. While recent techniques mainly focus on standard Fourier transform and vector-valued spectral functions, they fall short in flexibility to model signal distributions over large spatial ranges, and capacity of spectral function. In this paper, we present a novel wavelet-based graph convolution network, namely WaveGC, which integrates multi-resolution spectral bases and a matrix-valued filter kernel. Theoretically, we establish that WaveGC can effectively capture and decouple short-range and long-range information, providing superior filtering flexibility, surpassing existing graph wavelet neural networks. To instantiate WaveGC, we introduce a novel technique for learning general graph wavelets by separately combining odd and even terms of Chebyshev polynomials. This approach strictly satisfies wavelet admissibility criteria. Our numerical experiments showcase the consistent improvements in both short-range and long-range tasks. This underscores the effectiveness of the proposed model in handling different scenarios. Our code is available at https://github.com/liun-online/WaveGC.

cs.LG↗

arXiv2025

Unsupervised Learning for Class Distribution Mismatch

Class distribution mismatch (CDM) refers to the discrepancy between class distributions in training data and target tasks. Previous methods address this by designing classifiers to categorize classes known during training, while grouping unknown or new classes into an "other" category. However, they focus on semi-supervised scenarios and heavily rely on labeled data, limiting their applicability and performance. To address this, we propose Unsupervised Learning for Class Distribution Mismatch (UCDM), which constructs positive-negative pairs from unlabeled data for classifier training. Our approach randomly samples images and uses a diffusion model to add or erase semantic classes, synthesizing diverse training pairs. Additionally, we introduce a confidence-based labeling mechanism that iteratively assigns pseudo-labels to valuable real-world data and incorporates them into the training process. Extensive experiments on three datasets demonstrate UCDM's superiority over previous semi-supervised methods. Specifically, with a 60% mismatch proportion on Tiny-ImageNet dataset, our approach, without relying on labeled data, surpasses OpenMatch (with 40 labels per class) by 35.1%, 63.7%, and 72.5% in classifying known, unknown, and new classes.

cs.CV↗

arXiv2025

A Data-constrained Magnetohydrodynamic Simulation of Successive X-class Flares in Solar Active Region 13842 I. Dynamics of the Solar Eruption Associated with the X7.1 Solar Flare

We investigated the initiation and the evolution of an X7.1-class solar flare observed in solar active region NOAA 13842 on October 1, 2024, based on a data-constrained magnetohydrodynamic (MHD) simulation. The nonlinear force-free field (NLFFF) extrapolated from the photospheric magnetic field about 1 hour before the flare was used as the initial condition for the MHD simulations. The NLFFF reproduces highly sheared field lines that undergo tether-cutting reconnection in the MHD simulation, leading to the formation of a highly twisted magnetic flux rope (MFR), which then erupts rapidly driven by both torus instability and magnetic reconnection. This paper focuses on the dynamics of the MFR and its role in eruptions. We find that magnetic reconnection in the pre-eruption phase is crucial in the subsequent eruption driven by the torus instability. Furthermore, our simulation indicates that magnetic reconnection also directly enhances the torus instability. These results suggest that magnetic reconnection is not just a byproduct of the eruption due to reconnecting of post-flare arcade, but also plays a significant role in accelerating the MFR during the eruption.

astro-ph.SR↗

arXiv2024

Learning Uniformly Distributed Embedding Clusters of Stylistic Skills for Physically Simulated Characters

Learning natural and diverse behaviors from human motion datasets remains challenging in physics-based character control. Existing conditional adversarial models often suffer from tight and biased embedding distributions where embeddings from the same motion are closely grouped in a small area and shorter motions occupy even less space. Our empirical observations indicate this limits the representational capacity and diversity under each skill. An ideal latent space should be maximally packed by all motion's embedding clusters. In this paper, we propose a skill-conditioned controller that learns diverse skills with expressive variations. Our approach leverages the Neural Collapse phenomenon, a natural outcome of the classification-based encoder, to uniformly distributed cluster centers. We additionally propose a novel Embedding Expansion technique to form stylistic embedding clusters for diverse skills that are uniformly distributed on a hypersphere, maximizing the representational area occupied by each skill and minimizing unmapped regions. This maximally packed and uniformly distributed embedding space ensures that embeddings within the same cluster generate behaviors conforming to the characteristics of the corresponding motion clips, yet exhibiting noticeable variations within each cluster. Compared to existing methods, our controller not only generates high-quality, diverse motions covering the entire dataset but also achieves superior controllability, motion coverage, and diversity under each skill. Both qualitative and quantitative results confirm these traits, enabling our controller to be applied to a wide range of downstream tasks and serving as a cornerstone for diverse applications.

cs.GR↗

arXiv2024

Chemical abundances of 20 barium stars from the OHP spectra

Based on the high resolution and high signal-to-noise spectra, we derived the chemical abundances of 20 elements for 20 barium (Ba-) stars. For the first time, the detailed abundances of four sample stars, namely HD 92482, HD 150430, HD 151101 and HD 177304 have been analyzed. Additionally, Ba element abundance has been measured using high resolution spectra for the first time in six of the other 16 sample stars. Based on the [s/Fe] ratios, the Ba-unknown star HD 115927 can be classified as a strong Ba-star, while the Ba-likely star HD 160538 can be categorized into a mild Ba-star. Consequently, our sample comprises three strong and 17 mild Ba-stars. The light odd-Z metal elements and Fe-peak elements exhibit near-solar abundances. The [α/Fe] ratios demonstrate decreasing trends with increasing metallicity. Moreover, the abundances of n-capture elements show significant enhancements in different degrees. Using a threshold of the signed distances to the solar r-process abundance pattern ds = 0.6, we find that all of our sample stars are normal Ba-stars, indicating that the enhancements of s-process elements should be attributed to material transfer from their companions. We compare the observed n-capture patterns of sample stars with the FRUITY models, and estimate the mass of the Thermally-Pulsing Asymptotic Giant Branch stars that previously contaminated the Ba-stars. The models with low masses can successfully explain the observations. From a kinematic point of view, we note that most of our sample stars are linked with the thin disk, while HD 130255 may be associated with the thick disk.

astro-ph.SR↗

arXiv2024

CONDA: Condensed Deep Association Learning for Co-Salient Object Detection

Inter-image association modeling is crucial for co-salient object detection. Despite satisfactory performance, previous methods still have limitations on sufficient inter-image association modeling. Because most of them focus on image feature optimization under the guidance of heuristically calculated raw inter-image associations. They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling. To alleviate these limitations, this paper proposes a deep association learning strategy that deploys deep networks on raw associations to explicitly transform them into deep association features. Specifically, we first create hyperassociations to collect dense pixel-pair-wise raw associations and then deploys deep aggregation networks on them. We design a progressive association generation module for this purpose with additional enhancement of the hyperassociation calculation. More importantly, we propose a correspondence-induced association condensation module that introduces a pretext task, i.e. semantic correspondence estimation, to condense the hyperassociations for computational burden reduction and noise elimination. We also design an object-aware cycle consistency loss for high-quality correspondence estimations. Experimental results in three benchmark datasets demonstrate the remarkable effectiveness of our proposed method with various training settings.

cs.CV↗