arXiv subjects

Rui Liu

Publications and source records attributed to Rui Liu.

At least 199 records · Page 11Linked to original sources

arXiv2025

Hardness-Aware Dynamic Curriculum Learning for Robust Multimodal Emotion Recognition with Missing Modalities

Missing modalities have recently emerged as a critical research direction in multimodal emotion recognition (MER). Conventional approaches typically address this issue through missing modality reconstruction. However, these methods fail to account for variations in reconstruction difficulty across different samples, consequently limiting the model's ability to handle hard samples effectively. To overcome this limitation, we propose a novel Hardness-Aware Dynamic Curriculum Learning framework, termed HARDY-MER. Our framework operates in two key stages: first, it estimates the hardness level of each sample, and second, it strategically emphasizes hard samples during training to enhance model performance on these challenging instances. Specifically, we first introduce a Multi-view Hardness Evaluation mechanism that quantifies reconstruction difficulty by considering both Direct Hardness (modality reconstruction errors) and Indirect Hardness (cross-modal mutual information). Meanwhile, we introduce a Retrieval-based Dynamic Curriculum Learning strategy that dynamically adjusts the training curriculum by retrieving samples with similar semantic information and balancing the learning focus between easy and hard instances. Extensive experiments on benchmark datasets demonstrate that HARDY-MER consistently outperforms existing methods in missing-modality scenarios. Our code will be made publicly available at https://github.com/HARDY-MER/HARDY-MER.

cs.LG↗

arXiv2025

Solar magnetic flux rope eruptions caused by inverse flux feeding processes

Large-scale solar eruptions are generally accepted to have coronal magnetic flux ropes as their core structures. Recent studies found that the solar eruptions could be initiated by a sequence of flux feeding processes, during with chromospheric fibrils rise and merge with the pre-existing coronal flux rope. Further theoretical analyses have demonstrated that the normal flux feeding, i.e. the axial magnetic flux within the fibril is in the same direction as that in the flux rope, results in the accumulation of the total axial flux within the flux rope, so as to initiate the eruption. If the directions of the axial flux in the fibril and the flux rope are opposite, it is termed inverse flux feeding, whose influence on coronal flux ropes, however, is still unclear. In this paper, we use a 2.5-dimensional magnetohydrodynamic model to simulate the evolution of coronal flux ropes associated with inverse flux feeding. It is found that inverse flux feeding is also efficient in causing solar eruptions: although the total signed axial magnetic flux of the rope decreases after inverse flux feeding, the total unsigned axial flux can accumulate; the eruption occurs if the unsigned axial flux of the rope reaches a critical value, which is almost the same as the threshold for normal flux feeding. The total axial currents within the rope are also similar during the onset of the eruptions caused by both normal and inverse flux feeding. Our simulation results suggest that it is the unsigned axial magnetic flux rather than the signed axial flux that regulates the onset of coronal flux rope eruptions.

astro-ph.SR↗

arXiv2025

UniTalker: Conversational Speech-Visual Synthesis

Conversational Speech Synthesis (CSS) is a key task in the user-agent interaction area, aiming to generate more expressive and empathetic speech for users. However, it is well-known that "listening" and "eye contact" play crucial roles in conveying emotions during real-world interpersonal communication. Existing CSS research is limited to perceiving only text and speech within the dialogue context, which restricts its effectiveness. Moreover, speech-only responses further constrain the interactive experience. To address these limitations, we introduce a Conversational Speech-Visual Synthesis (CSVS) task as an extension of traditional CSS. By leveraging multimodal dialogue context, it provides users with coherent audiovisual responses. To this end, we develop a CSVS system named UniTalker, which is a unified model that seamlessly integrates multimodal perception and multimodal rendering capabilities. Specifically, it leverages a large-scale language model to comprehensively understand multimodal cues in the dialogue context, including speaker, text, speech, and the talking-face animations. After that, it employs multi-task sequence prediction to first infer the target utterance's emotion and then generate empathetic speech and natural talking-face animations. To ensure that the generated speech-visual content remains consistent in terms of emotion, content, and duration, we introduce three key optimizations: 1) Designing a specialized neural landmark codec to tokenize and reconstruct facial expression sequences. 2) Proposing a bimodal speech-visual hard alignment decoding strategy. 3) Applying emotion-guided rendering during the generation stage. Comprehensive objective and subjective experiments demonstrate that our model synthesizes more empathetic speech and provides users with more natural and emotionally consistent talking-face animations.

eess.AS↗

arXiv2025

SARD: A YOLOv8-Based System for Solar Active Region Detection with SDO/HMI Magnetograms

Solar active regions are where sunspots are located and photospheric magnetic fluxes are concentrated, therefore being the sources of energetic eruptions in the solar atmosphere. The detection and statistics of solar active regions have been forefront topics in solar physics. In this study, we developed a solar active region detector (SARD) based on the advanced object detection model YOLOv8. First, we applied image processing techniques including thresholding and morphological operations to 6975 line-of-sight magnetograms from 2010 to 2019 at a cadence of 12~h, obtained by the Helioseismic and Magnetic Imager onboard the Solar Dynamic Observatory. With manual refinement, we labeled 26531 active regions in the dataset for further training and test with the detection model. Without any overlap between the training and test sets, the superior performance of SARD is demonstrated by an average precision rate as high as 94\%. We then performed a statistical analysis on the area and magnetic flux of the detected active regions, both of which yield log-normal distributions. This result sheds light on the underlying complexity and multi-scale nature of solar active regions.

astro-ph.SR↗

arXiv2025

Exploiting Scale-Variant Attention for Segmenting Small Medical Objects

Early detection and accurate diagnosis can predict the risk of malignant disease transformation, thereby increasing the probability of effective treatment. Identifying mild syndrome with small pathological regions serves as an ominous warning and is fundamental in the early diagnosis of diseases. While deep learning algorithms, particularly convolutional neural networks (CNNs), have shown promise in segmenting medical objects, analyzing small areas in medical images remains challenging. This difficulty arises due to information losses and compression defects from convolution and pooling operations in CNNs, which become more pronounced as the network deepens, especially for small medical objects. To address these challenges, we propose a novel scale-variant attention-based network (SvANet) for accurately segmenting small-scale objects in medical images. The SvANet consists of scale-variant attention, cross-scale guidance, Monte Carlo attention, and vision transformer, which incorporates cross-scale features and alleviates compression artifacts for enhancing the discrimination of small medical objects. Quantitative experimental results demonstrate the superior performance of SvANet, achieving 96.12%, 96.11%, 89.79%, 84.15%, 80.25%, 73.05%, and 72.58% in mean Dice coefficient for segmenting kidney tumors, skin lesions, hepatic tumors, polyps, surgical excision cells, retinal vasculatures, and sperms, which occupy less than 1% of the image areas in KiTS23, ISIC 2018, ATLAS, PolypGen, TissueNet, FIVES, and SpermHealth datasets, respectively.

eess.IV↗

arXiv2025

Waiting Time Distribution of Supra-Arcade Downflows

Supra-arcade downflows (SADs) are dark, sunward-moving structures above the arcade of flare loops. Naturally they are considered to be associated with outflows resulting from magnetic reconnection at the vertical current sheet beneath the eruptive structure. Despite the extensive investigations on the SAD properties, the timing information, particularly the waiting time between consecutive SADs, has not been systematically examined. Here, using the 131~Å passband of the Atmospheric Imaging Assembly on-board the Solar Dynamics Observatory, we studied the waiting time distribution (WTD) of SADs in 7 eruptive flares. In six of the 7 flares, the SADs are identified and tracked in previous studies, by two different methods; and in the 7th flare, by our optimized manual method. Based on statistical evaluations, we found that most of the WTDs are best fitted by a power-law function with the slope ranging from 1.7 to 2.4, in accordance with the prediction of non-stationary Poisson processes or self-organized criticality; but often they can also be fitted almost equally well by a log-normal function. These results rule out linear random or quasi-periodic processes to be responsible for the generation of SADs, but suggest that several nonlinear mechanisms be coupled together in the reconnection outflow region to shape the heavy-tailed WTD of SADs.

astro-ph.SR↗

arXiv2025

GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However, prevailing on-policy RL methods often contend with significant training instability and inefficiency. This is primarily due to a capacity-difficulty mismatch, where the complexity of training data frequently outpaces the model's current capabilities, leading to critically sparse reward signals and stalled learning progress. This challenge is particularly acute for smaller, more resource-efficient LLMs. To overcome this, we introduce the Guided Hybrid Policy Optimization (GHPO), a novel difficulty-aware reinforcement learning framework. GHPO dynamically calibrates task difficulty by employing adaptive prompt refinement to provide targeted guidance. This unique approach adaptively balances direct imitation learning for problems currently beyond the model's reach with exploration-based reinforcement learning for more manageable tasks, effectively creating a smooth and optimized learning curriculum. Extensive experiments demonstrate that GHPO achieves an average performance gain of approximately 5% across six challenging mathematics benchmarks, consistently outperforming strong on-policy reinforcement learning and curriculum learning baselines. Further analysis confirms that our framework significantly enhances both training stability and final reasoning performance, thus offering a scalable and efficient solution for developing powerful and robust reasoning models.

cs.LG↗

arXiv2025

Deep Hashing with Semantic Hash Centers for Image Retrieval

Deep hashing is an effective approach for large-scale image retrieval. Current methods are typically classified by their supervision types: point-wise, pair-wise, and list-wise. Recent point-wise techniques (e.g., CSQ, MDS) have improved retrieval performance by pre-assigning a hash center to each class, enhancing the discriminability of hash codes across various datasets. However, these methods rely on data-independent algorithms to generate hash centers, which neglect the semantic relationships between classes and may degrade retrieval performance. This paper introduces the concept of semantic hash centers, building on the idea of traditional hash centers. We hypothesize that hash centers of semantically related classes should have closer Hamming distances, while those of unrelated classes should be more distant. To this end, we propose a three-stage framework, SHC, to generate hash codes that preserve semantic structure. First, we develop a classification network to identify semantic similarities between classes using a data-dependent similarity calculation that adapts to varying data distributions. Second, we introduce an optimization algorithm to generate semantic hash centers, preserving semantic relatedness while enforcing a minimum distance between centers to avoid excessively similar hash codes. Finally, a deep hashing network is trained using these semantic centers to convert images into binary hash codes. Experimental results on large-scale retrieval tasks across several public datasets show that SHC significantly improves retrieval performance. Specifically, SHC achieves average improvements of +7.26%, +7.62%, and +11.71% in MAP@100, MAP@1000, and MAP@ALL metrics, respectively, over state-of-the-art methods.

cs.CV↗

arXiv2025

DK-RRT: Deep Koopman RRT for Collision-Aware Motion Planning of Space Manipulators in Dynamic Debris Environments

Trajectory planning for robotic manipulators operating in dynamic orbital debris environments poses significant challenges due to complex obstacle movements and uncertainties. This paper presents Deep Koopman RRT (DK-RRT), an advanced collision-aware motion planning framework integrating deep learning with Koopman operator theory and Rapidly-exploring Random Trees (RRT). DK-RRT leverages deep neural networks to identify efficient nonlinear embeddings of debris dynamics, enhancing Koopman-based predictions and enabling accurate, proactive planning in real-time. By continuously refining predictive models through online sensor feedback, DK-RRT effectively navigates the manipulator through evolving obstacle fields. Simulation studies demonstrate DK-RRT's superior performance in terms of adaptability, robustness, and computational efficiency compared to traditional RRT and conventional Koopman-based planning, highlighting its potential for autonomous space manipulation tasks.

cs.RO↗

arXiv2025

Approximation properties and quantitative estimation for uniform ball-covering property of operator spaces

In this paper, by dilation technique on Schauder frames, we extend Godefroy and Kalton's approximation theorem (1997), and obtain that a separable Banach space has the $λ$-unconditional bounded approximation property ($λ$-UBAP) if and only if, for any $\varepsilon>0$, it can be embeded into a $(λ+\varepsilon)$-complemented subspace of a Banach space with an $1$-unconditional finite-dimensional decomposition ($1$-UFDD). As applications on ball-covering property (BCP) (Cheng, 2006) of operator spaces, also based on the relationship between the $λ$-UBAP and block unconditional Schauder frames, we prove that if $X^\ast$, $Y$ are separable and (1) $X$ or $Y$ has the $λ$-reverse metric approximation property ($λ$-RMAP) for some $λ>1$; or (2) $X$ or $Y$ has an approximating sequence $\{S_n\}_{n=1}^\infty$ such that $\lim_n\|id-2S_n\| < 3/2$, then the space of bounded linear operators $B(X,Y)$ has the uniform ball-covering property (UBCP). Actually, we give uniformly quantitative estimation for the renormed spaces. We show that if $X^\ast$, $Y$ are separable and $X$ or $Y$ has the $(2-\varepsilon)$-UBAP for any $\varepsilon>0$, then for all $1-\varepsilon/2 < α\leq 1$, the renormed space $Z_α=(B(X,Y),\|\cdot\|_α)$ has the $(2α, 2α+\varepsilon-2-σ)$-UBCP for all $0 <σ< 2α+\varepsilon-2$. Furthermore, we point out the connections between the UBCP, u-ideals and the ball intersection property (BIP).

math.FA↗

arXiv2025

Reflective VLM Planning for Dual-Arm Desktop Cleaning: Bridging Open-Vocabulary Perception and Precise Manipulation

Desktop cleaning demands open-vocabulary recognition and precise manipulation for heterogeneous debris. We propose a hierarchical framework integrating reflective Vision-Language Model (VLM) planning with dual-arm execution via structured scene representation. Grounded-SAM2 facilitates open-vocabulary detection, while a memory-augmented VLM generates, critiques, and revises manipulation sequences. These sequences are converted into parametric trajectories for five primitives executed by coordinated Franka arms. Evaluated in simulated scenarios, our system achieving 87.2% task completion, a 28.8% improvement over static VLM and 36.2% over single-arm baselines. Structured memory integration proves crucial for robust, generalizable manipulation while maintaining real-time control performance.

cs.RO↗

arXiv2025

Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction

We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides an open-source implementation of the integrated MetaQueries and M2-omni framework, while introducing the novel multi-scale learnable tokens and multi-scale representation alignment strategy. By leveraging a fixed MLLM and a learnable diffusion model, Ming-Lite-Uni enables native multimodal AR models to perform both text-to-image generation and instruction based image editing tasks, expanding their capabilities beyond pure visual understanding. Our experimental results demonstrate the strong performance of Ming-Lite-Uni and illustrate the impressive fluid nature of its interactive process. All code and model weights are open-sourced to foster further exploration within the community. Notably, this work aligns with concurrent multimodal AI milestones - such as ChatGPT-4o with native image generation updated in March 25, 2025 - underscoring the broader significance of unified models like Ming-Lite-Uni on the path toward AGI. Ming-Lite-Uni is in alpha stage and will soon be further refined.

cs.CV↗

arXiv2025

Ming-Omni: A Unified Multimodal Model for Perception and Generation

We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation. Ming-Omni employs dedicated encoders to extract tokens from different modalities, which are then processed by Ling, an MoE architecture equipped with newly proposed modality-specific routers. This design enables a single model to efficiently process and fuse multimodal inputs within a unified framework, thereby facilitating diverse tasks without requiring separate models, task-specific fine-tuning, or structural redesign. Importantly, Ming-Omni extends beyond conventional multimodal models by supporting audio and image generation. This is achieved through the integration of an advanced audio decoder for natural-sounding speech and Ming-Lite-Uni for high-quality image generation, which also allow the model to engage in context-aware chatting, perform text-to-speech conversion, and conduct versatile image editing. Our experimental results showcase Ming-Omni offers a powerful solution for unified perception and generation across all modalities. Notably, our proposed Ming-Omni is the first open-source model we are aware of to match GPT-4o in modality support, and we release all code and model weights to encourage further research and development in the community.

cs.AI↗

arXiv2025

Superatomic hydrogen: achieving effective aggregation of hydrogen atoms at pressures lower than that of metallic hydrogen

Metal hydrogen exhibiting electron delocalization properties has been recognized as an important prospect for achieving controlled nuclear fusion, but the extreme pressure conditions required exceeding hundreds of GPa remain a daunting challenge. Here, we propose a model of superatomic hydrogen, aiming to reduce the pressure conditions required for the effective aggregation of elemental hydrogen atoms. High-precision ab initio calculations indicate that the pressure required to compress the H13 system with one central atom and 12 surrounding atoms into a superatomic state is approximately two orders of magnitude lower than that of metallic hydrogen. Atomic-level analyses reveal that in the superatomic state of compressed H13, the central H atom donates its electron, and all electrons are delocalized on the superatomic molecular orbitals, which conforms to properties of metallic hydrogen. Our discovery in principle opens up the prospect of superatomic hydrogen in areas such as nuclear fusion.

physics.comp-ph↗

arXiv2025

Falling Threads During Solar Filament Eruptions

Mass drainage is frequently observed in solar filaments. During filament eruptions, falling material most likely flows along magnetic field lines, which may provide important clues for the magnetic structures of filaments. Here we study three filament eruptions exhibiting significant mass draining, often manifested as falling threads at a constant speed ranging between 30--300 km/s. We found that most of the falling material lands onto the hooked segments of flare ribbons, only a small fraction lands inside the hooks, and almost none lands onto the straight segments of ribbons. Based on these observations we surmise that before eruptions most of the filament mass is entrained by field lines threading the quasi-separatrix layers (QSLs), which wrap around the filament field and whose footpoints are mapped by the hooked ribbons, and that the magnetic reconnection involving these field lines is the major cause of the mass drainage during eruptions. Additionally, the light curves of the hooked ribbons suggest that during eruptions the earlier (later) QSL boundary of filaments is threaded by mass-loaded (depleted) field lines. By assuming that the constant-speed motion is due to a drag force balancing the gravity, we proposed a simplified analytical model to estimate the density contrast of the falling material. The estimated density contrast is then fed into a numerical model, in which filament threads fall along vertical magnetic field lines through a gravitationally stratified atmosphere. The resultant falling speeds, however, are short of observed values, which calls for further investigations.

astro-ph.SR↗

arXiv2025

Dynamical Frames and Hyperinvariant Subspaces

The theory of dynamical frames evolved from practical problems in dynamical sampling where the initial state of a vector needs to be recovered from the space-time samples of evolutions of the vector. This leads to the investigation of structured frames obtained from the orbits of evolution operators. One of the basic problems in dynamical frame theory is to determine the semigroup representations, which we will call central frame representations, whose frame generators are unique (up to equivalence). Recently, Christensen, Hasannasab, and Philipp proved that all frame representations of the semigroup $\Bbb{Z}_{+}$ have this property. Their proof of this result relies on the characterization of the structure of shift-invariant subspaces in $H^2(\mathbb{D})$ due to Beurling. In this paper we settle the general uniqueness problem by presenting a characterization of central frame representations for any semigroup in terms of the co-hyperinvariant subspaces of the left regular representation of the semigroup. This result is not only consistent with the known result of Han-Larson in 2000 for group representation frames, but also proves that all the frame generators of a semigroup generated by any $k$-tuple $(A_1, ... A_k)$ of commuting bounded linear operators on a separable Hilbert space $H$ are equivalent, a case where the structure of shift-invariant subspaces, or submodules, of the Hardy Space on polydisks $H^{2}(\Bbb{D}^k)$ is still not completely characterized.

math.FA↗

arXiv2025

Towards Emotionally Consistent Text-Based Speech Editing: Introducing EmoCorrector and The ECD-TSE Dataset

Text-based speech editing (TSE) modifies speech using only text, eliminating re-recording. However, existing TSE methods, mainly focus on the content accuracy and acoustic consistency of synthetic speech segments, and often overlook the emotional shifts or inconsistency issues introduced by text changes. To address this issue, we propose EmoCorrector, a novel post-correction scheme for TSE. EmoCorrector leverages Retrieval-Augmented Generation (RAG) by extracting the edited text's emotional features, retrieving speech samples with matching emotions, and synthesizing speech that aligns with the desired emotion while preserving the speaker's identity and quality. To support the training and evaluation of emotional consistency modeling in TSE, we pioneer the benchmarking Emotion Correction Dataset for TSE (ECD-TSE). The prominent aspect of ECD-TSE is its inclusion of $<$text, speech$>$ paired data featuring diverse text variations and a range of emotional expressions. Subjective and objective experiments and comprehensive analysis on ECD-TSE confirm that EmoCorrector significantly enhances the expression of intended emotion while addressing emotion inconsistency limitations in current TSE methods. Code and audio examples are available at https://github.com/AI-S2-Lab/EmoCorrector.

eess.AS↗

arXiv2025

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization

Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using Long-CoT varies across problems: while some problems require elaborate reasoning, others show no improvement, or even degraded accuracy. This motivates adaptive reasoning strategies that tailor reasoning depth to the input. However, prior work primarily reduces redundancy within long reasoning paths, limiting exploration of more efficient strategies beyond the Long-CoT paradigm. To address this, we propose a novel two-stage framework for adaptive and efficient reasoning. First, we construct a hybrid reasoning model by merging long and short CoT models to enable diverse reasoning styles. Second, we apply bi-level preference training to guide the model to select suitable reasoning styles (group-level), and prefer concise and correct reasoning within each style group (instance-level). Experiments demonstrate that our method (Ada-R1) significantly reduces inference costs compared to other baseline approaches, while maintaining performance. Notably, on five mathematical datasets, the average length of reasoning is reduced by more than 50%, highlighting the potential of adaptive strategies to optimize reasoning efficiency in large language models. Our code is coming soon at https://github.com/StarDewXXX/AdaR1

cs.AI↗