arXiv subjects

Zhe Xu

Publications and source records attributed to Zhe Xu.

At least 73 records · Page 4Linked to original sources

arXiv2025

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and better preserve these cues, yet still rely on text intermediates, creating a fundamental bottleneck. We present MOSS-Speech, a true speech-to-speech large language model that directly understands and generates speech without relying on text guidance. Our approach combines a modality-based layer-splitting architecture with a frozen pre-training strategy, preserving the reasoning and knowledge of pretrained text LLMs while adding native speech capabilities. Experiments show that our model achieves state-of-the-art results in spoken question answering and delivers comparable speech-to-speech performance relative to existing text-guided systems, while still maintaining competitive text performance. By narrowing the gap between text-guided and direct speech generation, our work establishes a new paradigm for expressive and efficient end-to-end speech interaction.

cs.CL↗

arXiv2025

Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context

Partial point cloud registration is essential for autonomous perception and 3D scene understanding, yet it remains challenging owing to structural ambiguity, partial visibility, and noise. We address these issues by proposing Confidence Estimation under Global Context (CEGC), a unified, confidence-driven framework for robust partial 3D registration. CEGC enables accurate alignment in complex scenes by jointly modeling overlap confidence and correspondence reliability within a shared global context. Specifically, the hybrid overlap confidence estimation module integrates semantic descriptors and geometric similarity to detect overlapping regions and suppress outliers early. The context-aware matching strategy smitigates ambiguity by employing global attention to assign soft confidence scores to correspondences, improving robustness. These scores guide a differentiable weighted singular value decomposition solver to compute precise transformations. This tightly coupled pipeline adaptively down-weights uncertain regions and emphasizes contextually reliable matches. Experiments on ModelNet40, ScanObjectNN, and 7Scenes 3D vision datasets demonstrate that CEGC outperforms state-of-the-art methods in accuracy, robustness, and generalization. Overall, CEGC offers an interpretable and scalable solution to partial point cloud registration under challenging conditions.

cs.CV↗

arXiv2025

An Adaptive ICP LiDAR Odometry Based on Reliable Initial Pose

As a key technology for autonomous navigation and positioning in mobile robots, light detection and ranging (LiDAR) odometry is widely used in autonomous driving applications. The Iterative Closest Point (ICP)-based methods have become the core technique in LiDAR odometry due to their efficient and accurate point cloud registration capability. However, some existing ICP-based methods do not consider the reliability of the initial pose, which may cause the method to converge to a local optimum. Furthermore, the absence of an adaptive mechanism hinders the effective handling of complex dynamic environments, resulting in a significant degradation of registration accuracy. To address these issues, this paper proposes an adaptive ICP-based LiDAR odometry method that relies on a reliable initial pose. First, distributed coarse registration based on density filtering is employed to obtain the initial pose estimation. The reliable initial pose is then selected by comparing it with the motion prediction pose, reducing the initial error between the source and target point clouds. Subsequently, by combining the current and historical errors, the adaptive threshold is dynamically adjusted to accommodate the real-time changes in the dynamic environment. Finally, based on the reliable initial pose and the adaptive threshold, point-to-plane adaptive ICP registration is performed from the current frame to the local map, achieving high-precision alignment of the source and target point clouds. Extensive experiments on the public KITTI dataset demonstrate that the proposed method outperforms existing approaches and significantly enhances the accuracy of LiDAR odometry.

cs.RO↗

arXiv2025

Properties of Chromospheric Fibrils Around a Quiescent Filament

Fibrils are dynamic plasma structures in the solar chromosphere. Studying these structures is critical for understanding solar atmospheric heating and mass transportation. The purpose of this study is to obtain the characteristics of fibrils surrounding the filament. By employing high-resolution H-alpha data obtained from the New Vacuum Solar Telescope (NVST), we undertake a detailed analysis of the properties of 63 fibrils situated in the vicinity of the filament. Comparing the fibrils on both sides of the filament demonstrates that these fibrils have similar physical properties except for their orientation. The properties of fibrils are statistically measured, including lifetimes of 150-650 s, widths of 320-850 km, maximum lengths of 3-8.5 Mm, projection velocities of 7-29 km/s, and decelerations of 45-474 m/s2. The dominant oscillation period of fibrils is predominantly concentrated in the range of 4.8-6.6 minutes (2.5-3.5 mHz). Transverse oscillations are identified in a subset of fibrils, with periodicities of 269-289 s and phase speeds of 13.7-25.8 km/s, indicating the presence of kink-mode magnetohydrodynamic (MHD) waves.

astro-ph.SR↗

arXiv2025

TwinTac: A Wide-Range, Highly Sensitive Tactile Sensor with Real-to-Sim Digital Twin Sensor Model

Robot skill acquisition processes driven by reinforcement learning often rely on simulations to efficiently generate large-scale interaction data. However, the absence of simulation models for tactile sensors has hindered the use of tactile sensing in such skill learning processes, limiting the development of effective policies driven by tactile perception. To bridge this gap, we present TwinTac, a system that combines the design of a physical tactile sensor with its digital twin model. Our hardware sensor is designed for high sensitivity and a wide measurement range, enabling high quality sensing data essential for object interaction tasks. Building upon the hardware sensor, we develop the digital twin model using a real-to-sim approach. This involves collecting synchronized cross-domain data, including finite element method results and the physical sensor's outputs, and then training neural networks to map simulated data to real sensor responses. Through experimental evaluation, we characterized the sensitivity of the physical sensor and demonstrated the consistency of the digital twin in replicating the physical sensor's output. Furthermore, by conducting an object classification task, we showed that simulation data generated by our digital twin sensor can effectively augment real-world data, leading to improved accuracy. These results highlight TwinTac's potential to bridge the gap in cross-domain learning tasks.

cs.RO↗

arXiv2025

A Unified Low-level Foundation Model for Enhancing Pathology Image Quality

Foundation models have revolutionized computational pathology by achieving remarkable success in high-level diagnostic tasks, yet the critical challenge of low-level image enhancement remains largely unaddressed. Real-world pathology images frequently suffer from degradations such as noise, blur, and low resolution due to slide preparation artifacts, staining variability, and imaging constraints, while the reliance on physical staining introduces significant costs, delays, and inconsistency. Although existing methods target individual problems like denoising or super-resolution, their task-specific designs lack the versatility to handle the diverse low-level vision challenges encountered in practice. To bridge this gap, we propose the first unified Low-level Pathology Foundation Model (LPFM), capable of enhancing image quality in restoration tasks, including super-resolution, deblurring, and denoising, as well as facilitating image translation tasks like virtual staining (H&E and special stains), all through a single adaptable architecture. Our approach introduces a contrastive pre-trained encoder that learns transferable, stain-invariant feature representations from 190 million unlabeled pathology images, enabling robust identification of degradation patterns. A unified conditional diffusion process dynamically adapts to specific tasks via textual prompts, ensuring precise control over output quality. Trained on a curated dataset of 87,810 whole slied images (WSIs) across 34 tissue types and 5 staining protocols, LPFM demonstrates statistically significant improvements (p<0.01) over state-of-the-art methods in most tasks (56/66), achieving Peak Signal-to-Noise Ratio (PSNR) gains of 10-15% for image restoration and Structural Similarity Index Measure (SSIM) improvements of 12-18% for virtual staining.

cs.CV↗

arXiv2025

PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis

Modern power systems are becoming increasingly dynamic, with changing topologies and time-varying loads driven by renewable energy variability, electric vehicle adoption, and active grid reconfiguration. Despite these changes, publicly available test cases remain scarce, due to security concerns and the significant effort required to anonymize real systems. Such limitations call for generative tools that can jointly synthesize grid structure and nodal dynamics. However, modeling the joint distribution of network topology, branch attributes, bus properties, and dynamic load profiles remains a major challenge, while preserving physical feasibility and avoiding prohibitive computational costs. We present PowerGrow, a co-generative framework that significantly reduces computational overhead while maintaining operational validity. The core idea is dependence decomposition: the complex joint distribution is factorized into a chain of conditional distributions over feasible grid topologies, time-series bus loads, and other system attributes, leveraging their mutual dependencies. By constraining the generation process at each stage, we implement a hierarchical graph beta-diffusion process for structural synthesis, paired with a temporal autoencoder that embeds time-series data into a compact latent space, improving both training stability and sample fidelity. Experiments across benchmark settings show that PowerGrow not only outperforms prior diffusion models in fidelity and diversity but also achieves a 98.9\% power flow convergence rate and improved N-1 contingency resilience. This demonstrates its ability to generate operationally valid and realistic power grid scenarios.

cs.LG↗

arXiv2025

A Versatile Pathology Co-pilot via Reasoning Enhanced Multimodal Large Language Model

Multimodal large language models (MLLMs) have emerged as powerful tools for computational pathology, offering unprecedented opportunities to integrate pathological images with language context for comprehensive diagnostic analysis. These models hold particular promise for automating complex tasks that traditionally require expert interpretation of pathologists. However, current MLLM approaches in pathology demonstrate significantly constrained reasoning capabilities, primarily due to their reliance on expensive chain-of-thought annotations. Additionally, existing methods remain limited to simplex application of visual question answering (VQA) at the region-of-interest (ROI) level, failing to address the full spectrum of diagnostic needs such as ROI classification, detection, segmentation, whole-slide-image (WSI) classification and VQA in clinical practice. In this study, we present SmartPath-R1, a versatile MLLM capable of simultaneously addressing both ROI-level and WSI-level tasks while demonstrating robust pathological reasoning capability. Our framework combines scale-dependent supervised fine-tuning and task-aware reinforcement fine-tuning, which circumvents the requirement for chain-of-thought supervision by leveraging the intrinsic knowledge within MLLM. Furthermore, SmartPath-R1 integrates multiscale and multitask analysis through a mixture-of-experts mechanism, enabling dynamic processing for diverse tasks. We curate a large-scale dataset comprising 2.3M ROI samples and 188K WSI samples for training and evaluation. Extensive experiments across 72 tasks validate the effectiveness and superiority of the proposed approach. This work represents a significant step toward developing versatile, reasoning-enhanced AI systems for precision pathology.

eess.IV↗

arXiv2025

A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems

This survey provides a comprehensive review of research on multi-turn dialogue systems, with a particular focus on multi-turn dialogue systems based on large language models (LLMs). This paper aims to (a) give a summary of existing LLMs and approaches for adapting LLMs to downstream tasks; (b) elaborate recent advances in multi-turn dialogue systems, covering both LLM-based open-domain dialogue (ODD) and task-oriented dialogue (TOD) systems, along with datasets and evaluation metrics; (c) discuss some future emphasis and recent research problems arising from the development of LLMs and the increasing demands on multi-turn dialogue systems.

cs.CL↗

arXiv2025

Attention Basin: Why Contextual Position Matters in Large Language Models

The performance of Large Language Models (LLMs) is significantly sensitive to the contextual position of information in the input. To investigate the mechanism behind this positional bias, our extensive experiments reveal a consistent phenomenon we term the attention basin: when presented with a sequence of structured items (e.g., retrieved documents or few-shot examples), models systematically assign higher attention to the items at the beginning and end of the sequence, while neglecting those in the middle. Crucially, our analysis further reveals that allocating higher attention to critical information is key to enhancing model performance. Based on these insights, we introduce Attention-Driven Reranking (AttnRank), a two-stage framework that (i) estimates a model's intrinsic positional attention preferences using a small calibration set, and (ii) reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions. AttnRank is a model-agnostic, training-free, and plug-and-play method with minimal computational overhead. Experiments on multi-hop QA and few-shot in-context learning tasks demonstrate that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures.

cs.CL↗

arXiv2025

FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation

Medical image segmentation is challenging due to the diversity of medical images and the lack of labeled data, which motivates recent developments in federated semi-supervised learning (FSSL) to leverage a large amount of unlabeled data from multiple centers for model training without sharing raw data. However, what remains under-explored in FSSL is the domain shift problem which may cause suboptimal model aggregation and low effectivity of the utilization of unlabeled data, eventually leading to unsatisfactory performance in unseen domains. In this paper, we explore this previously ignored scenario, namely domain generalized federated semi-supervised learning (FedSemiDG), which aims to learn a model in a distributed manner from multiple domains with limited labeled data and abundant unlabeled data such that the model can generalize well to unseen domains. We present a novel framework, Federated Generalization-Aware SemiSupervised Learning (FGASL), to address the challenges in FedSemiDG by effectively tackling critical issues at both global and local levels. Globally, we introduce Generalization-Aware Aggregation (GAA), assigning adaptive weights to local models based on their generalization performance. Locally, we use a Dual-Teacher Adaptive Pseudo Label Refinement (DR) strategy to combine global and domain-specific knowledge, generating more reliable pseudo labels. Additionally, Perturbation-Invariant Alignment (PIA) enforces feature consistency under perturbations, promoting domain-invariant learning. Extensive experiments on four medical segmentation tasks (cardiac MRI, spine MRI, bladder cancer MRI and colorectal polyp) demonstrate that our method significantly outperforms state-of-the-art FSSL and domain generalization approaches, achieving robust generalization on unseen domains.

cs.CV↗

arXiv2025

Successor Features for Transfer in Alternating Markov Games

This paper explores successor features for knowledge transfer in zero-sum, complete-information, and turn-based games. Prior research in single-agent systems has shown that successor features can provide a ``jump start" for agents when facing new tasks with varying reward structures. However, knowledge transfer in games typically relies on value and equilibrium transfers, which heavily depends on the similarity between tasks. This reliance can lead to failures when the tasks differ significantly. To address this issue, this paper presents an application of successor features to games and presents a novel algorithm called Game Generalized Policy Improvement (GGPI), designed to address Markov games in multi-agent reinforcement learning. The proposed algorithm enables the transfer of learning values and policies across games. An upper bound of the errors for transfer is derived as a function the similarity of the task. Through experiments with a turn-based pursuer-evader game, we demonstrate that the GGPI algorithm can generate high-reward interactions and one-shot policy transfer. When further tested in a wider set of initial conditions, the GGPI algorithm achieves higher success rates with improved path efficiency compared to those of the baseline algorithms.

cs.MA↗

arXiv2025

Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models

While AI for Science (AI4S) serves as an analytical tool in the current research paradigm, it doesn't solve its core inefficiency. We propose "Agent for Science" (Agent4S)-the use of LLM-driven agents to automate the entire research workflow-as the true Fifth Scientific Paradigm. This paper introduces a five-level classification for Agent4S, outlining a clear roadmap from simple task automation to fully autonomous, collaborative "AI Scientists." This framework defines the next revolutionary step in scientific discovery.

cs.AI↗

arXiv2025

High-resolution Observations of a C9.3 White-light Flare and Its Impact on the Solar Photosphere

We present a detailed analysis of a C9.3 white-light flare using high-resolution observations from the New Vacuum Solar Telescope (NVST). The flare occurred near the eastern solar limb on September 11, 2023, within NOAA AR 13431, and produced beam electrons with energies just below 50 keV as observed by the the Hard X-ray Imager (HXI) onboard the Advanced Space-based Solar Observatory (ASO-S). Two white-light flare kernels were detected in the TiO band, connected by filamentary brightenings aligned with penumbral fibrils, suggesting a photospheric contribution to the white-light emission. Notably, the impact of the flare on the solar photosphere was characterized by sudden vortex flows and significant amplification of magnetic field in the white-light flare kernel region. We infer that this impact is driven by the propagation of flare-generated Alfvén wave pulses, which deposited energy into the photosphere. These observations support the potential role of the Alfvén wave mechanism in driving energy transport and heating during white-light flares.

astro-ph.SR↗

arXiv2025

The Observations of Magnetic Reconnection During the Interaction Process of Two Active Region Filaments

We investigate the interaction between two filaments (F1 and F2) and their subsequent magnetic reconnection in active region (AR) NOAA 13296 and AR NOAA 13293 on May 9, 2023, utilizing high spatial and temporal resolution and multi-wavelength observational data from the Solar Dynamics Observatory, the New Vacuum Solar Telescope, and the Chinese Hα Solar Explorer. The movement of F1 from the southeast toward the northwest, driven by the motion of the positive magnetic polarity (P1), leads to a collision and reconnection with F2. This reconnection exchanges their footpoints, resulting in the formation of two new filaments (F3 and F4) consistent with "slingshot" type filament interaction. During the interaction, the current sheet moving due to the motion of F1 and the reconnection outflows moving along F3 and F4 were both observed. The current sheet is rarely observed in the slingshot type filament interaction, measuring approximately 2.17 Mm in length and 0.84 Mm in width. After the interaction, the F1 disappears whereas a portion of F2 remains, indicating that the interaction involves partial slingshot reconnection, due to the unequal magnetic flux between the filaments. The residual part of F2 will undergo another magnetic reconnection in the same interaction region with the magnetic loops connecting polarities N1 and P1. The material generated by the reconnection is continuously injected into F4, leading to its final morphology. The findings enhance our understanding of slingshot-type filament interactions, indicating that partial slingshot reconnections between filaments may be more common than full slingshot events.

astro-ph.SR↗

arXiv2025

MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning

Text Image Machine Translation (TIMT)-the task of translating textual content embedded in images-is critical for applications in accessibility, cross-lingual information access, and real-world document understanding. However, TIMT remains a complex challenge due to the need for accurate optical character recognition (OCR), robust visual-text reasoning, and high-quality translation, often requiring cascading multi-stage pipelines. Recent advances in large-scale Reinforcement Learning (RL) have improved reasoning in Large Language Models (LLMs) and Multimodal LLMs (MLLMs), but their application to end-to-end TIMT is still underexplored. To bridge this gap, we introduce MT$^{3}$, the first framework to apply Multi-Task RL to MLLMs for end-to-end TIMT. MT$^{3}$ adopts a multi-task optimization paradigm targeting three key sub-skills: text recognition, context-aware reasoning, and translation. It is trained using a novel multi-mixed reward mechanism that adapts rule-based RL strategies to TIMT's intricacies, offering fine-grained, non-binary feedback across tasks. Furthermore, to facilitate the evaluation of TIMT in authentic cross-cultural and real-world social media contexts, we introduced XHSPost, the first social media TIMT benchmark. Our MT$^{3}$-7B-Zero achieves state-of-the-art results on the latest in-domain MIT-10M benchmark, outperforming strong baselines such as Qwen2.5-VL-72B and InternVL2.5-78B by notable margins across multiple metrics. Additionally, the model shows strong generalization to out-of-distribution language pairs and datasets. In-depth analyses reveal how multi-task synergy, reinforcement learning initialization, curriculum design, and reward formulation contribute to advancing MLLM-driven TIMT.

cs.CL↗

arXiv2025

Discovering Pathology Rationale and Token Allocation for Efficient Multimodal Pathology Reasoning

Multimodal pathological image understanding has garnered widespread interest due to its potential to improve diagnostic accuracy and enable personalized treatment through integrated visual and textual data. However, existing methods exhibit limited reasoning capabilities, which hamper their ability to handle complex diagnostic scenarios. Additionally, the enormous size of pathological images leads to severe computational burdens, further restricting their practical deployment. To address these limitations, we introduce a novel bilateral reinforcement learning framework comprising two synergistic branches. One reinforcement branch enhances the reasoning capability by enabling the model to learn task-specific decision processes, i.e., pathology rationales, directly from labels without explicit reasoning supervision. While the other branch dynamically allocates a tailored number of tokens to different images based on both their visual content and task context, thereby optimizing computational efficiency. We apply our method to various pathological tasks such as visual question answering, cancer subtyping, and lesion detection. Extensive experiments show an average +41.7 absolute performance improvement with 70.3% lower inference costs over the base models, achieving both reasoning accuracy and computational efficiency.

cs.CV↗

arXiv2025

Recurrent Jetlets Associated with the Disappearance of a Satellite Spot

Recurrent small-scale eruptions are fascinating phenomena in the solar atmosphere. However, their underlying physical mechanisms remain unclear. On 2021 May 23, five recurrent jetlets (J1-J5) were observed continuously ejecting from a satellite spot located at the north edge of AR 12824. Using high-resolution, multi-wavelength data from NVST, SDO, and IRIS, we investigate the physical characteristics of these jetlets and their relationship with the satellite spot. The widths of these jetlets range from 1300 to 2900 km, their lifetimes range span 3 to 10 minutes, and their projection speeds vary from 152.8 to 406.0 km s$^{-1}$. During the eruptions, the satellite spot moved northwest at a low speed of 376 $\pm$ 12 m s$^{-1}$. Its area gradually decreased due to magnetic cancellation with surrounding positive magnetic field, resulting in an average cancellation rate of 1.3$\times$10$^{18}$ Mx hr$^{-1}$. Dark lanes that separated from the satellite spot and small pores were observed to move toward nearby these features or dark lanes with opposite polarities, eventually disappearing during the magnetic cancellation process. J4 was driven by an eruption of a micro-filament. Spectral observations revealed a redshift on the right side of J4 and a blueshift on the left side of its base, suggesting a counterclockwise rotation. The horizontal magnetic field of the satellite spot consistently exhibited a vortex structure throughout its evolution until it vanished. The nonlinear force-free field extrapolation confirms that the satellite spot serves as one footpoint of a mini-flux rope. These observations reveal that these jetlets might result from three-dimensional null-point magnetic reconnection, initiated by the continuous eruption of a mini-flux-rope or multiple mini-flux-ropes, driven by sustained magnetic cancellation.

astro-ph.SR↗