arXiv subjects

Jingwen Li

Publications and source records attributed to Jingwen Li.

At least 19 recordsLinked to original sources

arXiv2026

Communication in modular robotic motor control: Bilateral controllers under realistic constraints

Robotic motor control in musculoskeletal systems requires fast, accurate movement and robust postural stabilization under signal-dependent noise (where motor command variance scales with command magnitude) and energetic cost. Modular controllers can distribute these competing demands across interacting submodules, but it remains unclear whether they outperform monolithic architectures under realistic constraints, and how inter-module communication shapes the resulting strategy. Inspired by the bilateral hemispheric organization of the brain, we introduce a recurrent controller of two GRU-based modules connected by a learnable, delayed inter-hemispheric channel, trained end-to-end in a differentiable two-arm musculoskeletal simulator. Across reaching and holding tasks, the modular architecture substantially outperforms a capacity-matched monolithic baseline. Compared to a matched modular controller without communication, learned inter-hemispheric communication reshapes the solution: improved endpoint precision, lower energetic cost in non-zero-delay regimes, and reduced muscle co-contraction. Our findings show that for robotics, biologically inspired modular controllers offer a practical route to robust movement under noise and energetic constraints, with inter-module communication providing a mechanism to tune trade-offs between precision, stability, and actuation cost.

cs.RO↗

arXiv2026

Fast and Accurate: An Adaptive VLA Inference Framework through Environment-aware Model Selection

Embodied intelligence demands both long-horizon reasoning and real-time closed-loop responsiveness. Recent dual-system Vision-Language-Action (VLA) architectures combine fast reactive control with slow deliberative reasoning to balance inference speed and task success rate. However, existing dual-process VLAs tightly couple the fast module to intermediate representations of the slow module, necessitating end-to-end joint training and limiting modularity, extensibility and flexible system switching. In this paper, we propose Environment-aware Model Selection (EMS), an adaptive VLA inference framework that switches between two fully decoupled systems of different scales through environment-aware model selection. The large-scale deliberative system provides globally consistent trajectory planning to ensure task success, while a lightweight reactive system enables high-frequency closed-loop control. A reinforcement-learning-based switching policy dynamically selects which system to invoke based on real-time feedback, enabling sparse use of the slow system and thereby balancing pretrained knowledge utilisation with runtime efficiency. Our design offers three key advantages over prior hierarchical VLA frameworks: (1) a fully decoupled and modular dual-system architecture that supports plug-and-play model replacement; (2) an adaptive, environment-aware switching strategy; (3) high-frequency inference for responsive closed-loop control. We extensively evaluate EMS in both simulation and real-world environments. On the LIBERO benchmark, EMS achieves success rates comparable to the large-scale baseline while increasing the effective action frequency to 93.4 Hz. The framework further demonstrates strong extensibility in real-world dual-arm manipulation tasks, where it accelerates task completion while maintaining robust performance.

cs.RO↗

arXiv2026

Soft-mode nonlinearities away from ferroelectric phase transition

The interplay between ionic and electronic subsystems dictates the behavior of structural phase transitions in polar dielectrics, a coupling mediated by soft optical phonon modes. In incipient ferroelectrics such as SrTiO$_3$ (STO), strong local-field effects can drive the lattice into a non-perturbative regime near the phase boundary. However, disentangling the distinct contributions of local fields from those of spontaneous macroscopic polarization remains an experimental challenge. Here, we isolate these mechanisms by probing paraelectric STO deep within its symmetric phase, where macroscopic spontaneous polarization is suppressed. Linear terahertz (THz) spectroscopy reveals that the soft mode exhibits a hybrid character, predominantly driven by electronic polarizability. Utilizing two-dimensional THz spectroscopy, we map the underlying nonlinear signals, demonstrating that the system persists in a perturbative regime characterized by robust local-field coherence. By implementing a microscopic model of coupled electronic and lattice degrees of freedom mediated by local fields, we qualitatively reproduce these multidimensional coherent signatures. Our findings highlight that while local fields are necessary to initiate non-perturbative lattice dynamics, they are insufficient on their own. This reveals that spontaneous polarization plays a deterministic role in dictating soft-mode nonlinearities in strongly correlated polar dielectrics.

cond-mat.mtrl-sci↗

arXiv2026

Kohn anomaly in a topological phase transition

Topological crystalline insulators extend the concept of topological insulators by hosting surface states protected by crystallographic symmetry. Their topological phase transitions arise from spin-orbit-driven band inversion in the bulk electronic structure, reshaping the low-energy electronic environment and its coupling to lattice excitations. While the electronic aspects of band topology are well established, the corresponding dynamics of lattice and electron-phonon interactions remain largely unexplored. Here, we report a pronounced softening of a low-energy surface phonon mode across the topological phase transition in Pb0.77Sn0.23Se, revealed by temperature-dependent time-domain terahertz spectroscopy. Unlike the well-known phonon softening in ferroelectrics, this effect does not signal a structural instability but instead reflects electronic reconstruction. We attribute the softening to the Kohn anomaly, indicating a strong coupling between lattice vibrations and Dirac-like surface electrons in the topological phase. Consistently, the phonon linewidth deviates from the standard anharmonic temperature dependence, further evidencing enhanced electron-phonon coupling. Our results establish phonon softening as a spectroscopic signature of topological phase transitions and provide a route to distinguish topological and trivial phases.

cond-mat.str-el↗

arXiv2026

MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration

Contrastive Language-Image Pre-training (CLIP) has demonstrated outstanding performance in global image understanding and zero-shot transfer through large-scale text-image alignment. However, the core of medical image analysis often lies in the fine-grained understanding of specific anatomical structures or lesion regions. Therefore, precisely comprehending region-of-interest (RoI) information provided by medical professionals or perception models becomes crucial. To address this need, we propose MedP-CLIP, a region-aware medical vision-language model (VLM). MedP-CLIP innovatively integrates medical prior knowledge and designs a feature-level region prompt integration mechanism, enabling it to flexibly respond to various prompt forms (e.g., points, bounding boxes, masks) while maintaining global contextual awareness when focusing on local regions. We pre-train the model on a meticulously constructed large-scale dataset (containing over 6.4 million medical images and 97.3 million region-level annotations), equipping it with cross-disease and cross-modality fine-grained spatial semantic understanding capabilities. Experiments demonstrate that MedP-CLIP significantly outperforms baseline methods in various medical tasks, including zero-shot recognition, interactive segmentation, and empowering multimodal large language models. This model provides a scalable, plug-and-play visual backbone for medical AI, combining holistic image understanding with precise regional analysis.

cs.CV↗

arXiv2026

SegMoTE: Token-Level Mixture of Experts for Medical Image Segmentation

Medical image segmentation is vital for clinical diagnosis and quantitative analysis, yet remains challenging due to the heterogeneity of imaging modalities and the high cost of pixel-level annotations. Although general interactive segmentation models like SAM have achieved remarkable progress, their transfer to medical imaging still faces two key bottlenecks: (i) the lack of adaptive mechanisms for modality- and anatomy-specific tasks, which limits generalization in out-of-distribution medical scenarios; and (ii) current medical adaptation methods fine-tune on large, heterogeneous datasets without selection, leading to noisy supervision, higher cost, and negative transfer. To address these issues, we propose SegMoTE, an efficient and adaptive framework for medical image segmentation. SegMoTE preserves SAM's original prompt interface, efficient inference, and zero-shot generalization while introducing only a small number of learnable parameters to dynamically adapt across modalities and tasks. In addition, we design a progressive prompt tokenization mechanism that enables fully automatic segmentation, significantly reducing annotation dependence. Trained on MedSeg-HQ, a curated dataset less than 1% of existing large-scale datasets, SegMoTE achieves SOTA performance across diverse imaging modalities and anatomical tasks. It represents the first efficient, robust, and scalable adaptation of general segmentation models to the medical domain under extremely low annotation cost, advancing the practical deployment of foundation vision models in clinical applications.

cs.CV↗

arXiv2025

Enhancing the Cross-Size Generalization for Solving Vehicle Routing Problems via Continual Learning

Exploring machine learning techniques for addressing vehicle routing problems has attracted considerable research attention. To achieve decent and efficient solutions, existing deep models for vehicle routing problems are typically trained and evaluated using instances of a single size. This substantially limits their ability to generalize across different problem sizes and thus hampers their practical applicability. To address the issue, we propose a continual learning based framework that sequentially trains a deep model with instances of ascending problem sizes. Specifically, on the one hand, we design an inter-task regularization scheme to retain the knowledge acquired from smaller problem sizes in the model training on a larger size. On the other hand, we introduce an intra-task regularization scheme to consolidate the model by imitating the latest desirable behaviors during training on each size. Additionally, we exploit the experience replay to revisit instances of formerly trained sizes for mitigating the catastrophic forgetting. Experimental results show that our approach achieves predominantly superior performance across various problem sizes (either seen or unseen in the training), as compared to state-of-the-art deep models including the ones specialized for generalizability enhancement. Meanwhile, the ablation studies on the key designs manifest their synergistic effect in the proposed framework.

cs.LG↗

arXiv2025

Lifelong Learner: Discovering Versatile Neural Solvers for Vehicle Routing Problems

Deep learning has been extensively explored to solve vehicle routing problems (VRPs), which yields a range of data-driven neural solvers with promising outcomes. However, most neural solvers are trained to tackle VRP instances in a relatively monotonous context, e.g., simplifying VRPs by using Euclidean distance between nodes and adhering to a single problem size, which harms their off-the-shelf application in different scenarios. To enhance their versatility, this paper presents a novel lifelong learning framework that incrementally trains a neural solver to manage VRPs in distinct contexts. Specifically, we propose a lifelong learner (LL), exploiting a Transformer network as the backbone, to solve a series of VRPs. The inter-context self-attention mechanism is proposed within LL to transfer the knowledge obtained from solving preceding VRPs into the succeeding ones. On top of that, we develop a dynamic context scheduler (DCS), employing the cross-context experience replay to further facilitate LL looking back on the attained policies of solving preceding VRPs. Extensive results on synthetic and benchmark instances (problem sizes up to 18k) show that our LL is capable of discovering effective policies for tackling generic VRPs in varying contexts, which outperforms other neural solvers and achieves the best performance for most VRPs.

cs.LG↗

arXiv2025

CLIProv: A Contrastive Log-to-Intelligence Multimodal Approach for Threat Detection and Provenance Analysis

With the increasing complexity of cyberattacks, the proactive and forward-looking nature of threat intelligence has become more crucial for threat detection and provenance analysis. However, translating high-level attack patterns described in Tactics, Techniques, and Procedures (TTP) intelligence into actionable security policies remains a significant challenge. This challenge arises from the semantic gap between high-level threat intelligence and low-level provenance log. To address this issue, this paper introduces CLIProv, a novel approach for detecting threat behaviors in a host system. CLIProv employs a multimodal framework that leverages contrastive learning to align the semantics of provenance logs with threat intelligence, effectively correlating system intrusion activities with attack patterns. Furthermore, CLIProv formulates threat detection as a semantic search problem, identifying attack behaviors by searching for threat intelligence that is most semantically similar to the log sequence. By leveraging attack pattern information in threat intelligence, CLIProv identifies TTPs and generates complete and concise attack scenarios. Experimental evaluations on standard datasets show that CLIProv effectively identifies attack behaviors in system provenance logs, offering valuable references for potential techniques. Compared to state-of-the-art methods, CLIProv achieves higher precision and significantly improved detection efficiency.

cs.CR↗

arXiv2025

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play

A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner. Rather than merely reacting to commands, it would continuously listen, reason, and respond proactively, fostering fluid, dynamic, and emotionally resonant interactions. We introduce Voila, a family of large voice-language foundation models that make a step towards this vision. Voila moves beyond traditional pipeline systems by adopting a new end-to-end architecture that enables full-duplex, low-latency conversations while preserving rich vocal nuances such as tone, rhythm, and emotion. It achieves a response latency of just 195 milliseconds, surpassing the average human response time. Its hierarchical multi-scale Transformer integrates the reasoning capabilities of large language models (LLMs) with powerful acoustic modeling, enabling natural, persona-aware voice generation -- where users can simply write text instructions to define the speaker's identity, tone, and other characteristics. Moreover, Voila supports over one million pre-built voices and efficient customization of new ones from brief audio samples as short as 10 seconds. Beyond spoken dialogue, Voila is designed as a unified model for a wide range of voice-based applications, including automatic speech recognition (ASR), Text-to-Speech (TTS), and, with minimal adaptation, multilingual speech translation. Voila is fully open-sourced to support open research and accelerate progress toward next-generation human-machine interactions.

cs.AI↗

arXiv2025

Controllable Segmentation-Based Text-Guided Style Editing

We present a novel approach for controllable, region-specific style editing driven by textual prompts. Building upon the state-space style alignment framework introduced by \emph{StyleMamba}, our method integrates a semantic segmentation model into the style transfer pipeline. This allows users to selectively apply text-driven style changes to specific segments (e.g., ``turn the building into a cyberpunk tower'') while leaving other regions (e.g., ``people'' or ``trees'') unchanged. By incorporating region-wise condition vectors and a region-specific directional loss, our method achieves high-fidelity transformations that respect both semantic boundaries and user-driven style descriptions. Extensive experiments demonstrate that our approach can flexibly handle complex scene stylizations in real-world scenarios, improving control and quality over purely global style transfer methods.

cs.GR↗

arXiv2025

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

While spatial reasoning has made progress in object localization relationships, it often overlooks object orientation-a key factor in 6-DoF fine-grained manipulation. Traditional pose representations rely on pre-defined frames or templates, limiting generalization and semantic grounding. In this paper, we introduce the concept of semantic orientation, which defines object orientations using natural language in a reference-frame-free manner (e.g., the "plug-in" direction of a USB or the "handle" direction of a cup). To support this, we construct OrienText300K, a large-scale dataset of 3D objects annotated with semantic orientations, and develop PointSO, a general model for zero-shot semantic orientation prediction. By integrating semantic orientation into VLM agents, our SoFar framework enables 6-DoF spatial reasoning and generates robotic actions. Extensive experiments demonstrated the effectiveness and generalization of our SoFar, e.g., zero-shot 48.7% successful rate on Open6DOR and zero-shot 74.9% successful rate on SIMPLER-Env.

cs.RO↗

arXiv2025

First experimental proof of PET imaging based on multi-anode MCP-PMTs with Cherenkov radiator-integrated window

Improving the coincidence time resolution (CTR) of time-of-flight positron emission tomography (TOF-PET) systems to achieve a higher signal-to-noise ratio (SNR) gain or even direct positron emission imaging (dPEI) is of paramount importance for many advanced new clinical applications of PET imaging. This places higher demands on the timing performance of all aspects of PET systems. One effective approach is to use microchannel plate photomultiplier tubes (MCP-PMTs) for prompt Cherenkov photon detection. In this study, we developed a dual-module Cherenkov PET imaging experimental platform, utilising our proprietary 8 * 8-anode Cherenkov radiator-integrated window MCP-PMTs in combination with custom-designed multi-channel electronics, and designed a specific calibration and correction method for the platform. Using this platform, a CTR of 103 ps FWHM was achieved. We overcame the limitations of single-anode detectors in previous experiments, significantly enhanced imaging efficiency and achieved module-level Cherenkov PET imaging for the first time. Imaging experiments involving radioactive sources and phantoms of various shapes and types were conducted, which preliminarily validated the feasibility and advancement of this imaging method. In addition, the effects of normalisation correction and the interaction probability between the gamma rays and the MCP on the images and experimental results were analysed and verified.

physics.ins-det↗

arXiv2024

Discovery of a non-Hermitian phase transition in a bulk condensed-matter system

Phase transitions are fundamental in nature. A small parameter change near a critical point leads to a qualitative change in system properties. Across a regular phase transition, the system remains in thermal equilibrium and, therefore, experiences a change of static properties, like the emergence of a magnetisation upon cooling a ferromagnet below the Curie temperature. When driving a system far from equilibrium, novel, otherwise inaccessible quantum states of matter may arise. Such states are typically non-Hermitian, that is, their dynamics break time-reversal symmetry, a basic law of equilibrium physics. Phase transitions in non-Hermitian systems are of fundamentally new nature in that the dynamical behaviour rather than static properties may undergo a qualitative change at a critical, here called exceptional point. Here we experimentally realize a non-Hermitian phase transition in a bulk condensed-matter system. Optical excitation creates charge carriers in the ferromagnetic semiconductor EuO. In a temperature-dependent interplay with the Hermitian transition to ferromagnetic order, a non-Hermitian change of the relaxation dynamics occurs, manifesting in our time-resolved reflection data as a transition from bi-exponential real to single-exponential complex decay. Our theory models this behavior and predicts non-Hermitian phase transitions for a large class of condensed-matter systems, where they may be exploited to sensitively control bulk-dynamic properties.

cond-mat.str-el↗

arXiv2024

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

Creating AI systems that can interact with environments over long periods, similar to human cognition, has been a longstanding research goal. Recent advancements in multimodal large language models (MLLMs) have made significant strides in open-world understanding. However, the challenge of continuous and simultaneous streaming perception, memory, and reasoning remains largely unexplored. Current MLLMs are constrained by their sequence-to-sequence architecture, which limits their ability to process inputs and generate responses simultaneously, akin to being unable to think while perceiving. Furthermore, relying on long contexts to store historical data is impractical for long-term interactions, as retaining all information becomes costly and inefficient. Therefore, rather than relying on a single foundation model to perform all functions, this project draws inspiration from the concept of the Specialized Generalist AI and introduces disentangled streaming perception, reasoning, and memory mechanisms, enabling real-time interaction with streaming video and audio input. The proposed framework InternLM-XComposer2.5-OmniLive (IXC2.5-OL) consists of three key modules: (1) Streaming Perception Module: Processes multimodal information in real-time, storing key details in memory and triggering reasoning in response to user queries. (2) Multi-modal Long Memory Module: Integrates short-term and long-term memory, compressing short-term memories into long-term ones for efficient retrieval and improved accuracy. (3) Reasoning Module: Responds to queries and executes reasoning tasks, coordinating with the perception and memory modules. This project simulates human-like cognition, enabling multimodal large language models to provide continuous and adaptive service over time.

cs.CV↗

arXiv2024

Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

Interactive Medical Image Segmentation (IMIS) has long been constrained by the limited availability of large-scale, diverse, and densely annotated datasets, which hinders model generalization and consistent evaluation across different models. In this paper, we introduce the IMed-361M benchmark dataset, a significant advancement in general IMIS research. First, we collect and standardize over 6.4 million medical images and their corresponding ground truth masks from multiple data sources. Then, leveraging the strong object recognition capabilities of a vision foundational model, we automatically generated dense interactive masks for each image and ensured their quality through rigorous quality control and granularity management. Unlike previous datasets, which are limited by specific modalities or sparse annotations, IMed-361M spans 14 modalities and 204 segmentation targets, totaling 361 million masks-an average of 56 masks per image. Finally, we developed an IMIS baseline network on this dataset that supports high-quality mask generation through interactive inputs, including clicks, bounding boxes, text prompts, and their combinations. We evaluate its performance on medical image segmentation tasks from multiple perspectives, demonstrating superior accuracy and scalability compared to existing interactive segmentation models. To facilitate research on foundational models in medical computer vision, we release the IMed-361M and model at https://github.com/uni-medical/IMIS-Bench.

cs.CV↗

arXiv2024

Global Alignment Reference Strategy for Laser Interference Lithography Pattern Arrays

Large-area gratings play a crucial role in various engineering fields. However, traditional interference lithography is limited by the size of optical component apertures, making large-area fabrication a challenging task. Here, a method for fabricating laser interference lithography pattern arrays with a global alignment reference strategy is proposed. This approach enables alignment of each area of the laser interference lithography pattern arrays, including phase, period, and tilt angle. Two reference gratings are utilized: one is detached from the substrate, while the other remains fixed to it. To achieve global alignment, the exposure area is adjusted by alternating between moving the beam and the substrate. In our experiment, a 3 $\times$ 3 regions grating array was fabricated, and the $-1$st-order diffraction wavefront measured by the Fizeau interferometer exhibited good continuity. This technique enables effective and efficient alignment with high accuracy across any regions in an interference lithography pattern array on large substrates.

physics.optics↗

arXiv2024

Functional control of anomalous reflection via engineered metagratings without polarization limitations

Metagratings (MGs) have emerged as a promising platform for manipulating the anomalous propagation of electromagnetic waves. However, traditional methods for designing functional MG-based devices face significant challenges, including complex model structures, time-consuming optimization processes, and specific polarization requirements. In this work, we propose an inverse-design approach to engineer simple MG structures comprising periodic air grooves on a flat metal surface, which can control anomalous reflection without polarization limitations. Through rigorous analytical methods, we derive solutions that achieve perfect retroreflection and perfect specular reflection, thereby leading to functional control over the linearly-polarized electromagnetic waves. Such capabilities enable intriguing functionalities including polarization-dependent retroreflection and polarization-independent retroreflection, as confirmed through full-wave simulations. Our work offers a simple and effective method to control freely electromagnetic waves, with potential applications spanning wavefront engineering, polarization splitting, cloaking technologies, and remote sensing.

physics.optics↗