arXiv subjects

Jia Liu

Publications and source records attributed to Jia Liu.

At least 109 records · Page 6Linked to original sources

arXiv2025

Resource Efficient Sleep Staging via Multi-Level Masking and Prompt Learning

Automatic sleep staging plays a vital role in assessing sleep quality and diagnosing sleep disorders. Most existing methods rely heavily on long and continuous EEG recordings, which poses significant challenges for data acquisition in resource-constrained systems, such as wearable or home-based monitoring systems. In this paper, we propose the task of resource-efficient sleep staging, which aims to reduce the amount of signal collected per sleep epoch while maintaining reliable classification performance. To solve this task, we adopt the masking and prompt learning strategy and propose a novel framework called Mask-Aware Sleep Staging (MASS). Specifically, we design a multi-level masking strategy to promote effective feature modeling under partial and irregular observations. To mitigate the loss of contextual information introduced by masking, we further propose a hierarchical prompt learning mechanism that aggregates unmasked data into a global prompt, serving as a semantic anchor for guiding both patch-level and epoch-level feature modeling. MASS is evaluated on four datasets, demonstrating state-of-the-art performance, especially when the amount of data is very limited. This result highlights its potential for efficient and scalable deployment in real-world low-resource sleep monitoring environments.

cs.LG↗

arXiv2025

Multi-Objective Bilevel Learning

As machine learning (ML) applications grow increasingly complex in recent years, modern ML frameworks often need to address multiple potentially conflicting objectives with coupled decision variables across different layers. This creates a compelling need for multi-objective bilevel learning (MOBL). So far, however, the field of MOBL remains in its infancy and many important problems remain under-explored. This motivates us to fill this gap and systematically investigate the theoretical and algorithmic foundation of MOBL. Specifically, we consider MOBL problems with multiple conflicting objectives guided by preferences at the upper-level subproblem, where part of the inputs depend on the optimal solution of the lower-level subproblem. Our goal is to develop efficient MOBL optimization algorithms to (1) identify a preference-guided Pareto-stationary solution with low oracle complexity; and (2) enable systematic Pareto front exploration. To this end, we propose a unifying algorithmic framework called weighted-Chebyshev multi-hyper-gradient-descent (WC-MHGD) for both deterministic and stochastic settings with finite-time Pareto-stationarity convergence rate guarantees, which not only implies low oracle complexity but also induces systematic Pareto front exploration. We further conduct extensive experiments to confirm our theoretical results.

cs.LG↗

arXiv2025

EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models

To address data locality and privacy restrictions, Federated Learning (FL) has recently been adopted to fine-tune large language models (LLMs), enabling improved performance on various downstream tasks without requiring aggregated data. However, the repeated exchange of model updates in FL can result in prohibitively high communication costs, hindering the distributed learning process. To address this challenge, we propose EcoLoRA, a novel communication-efficient federated fine-tuning framework for LLMs. Leveraging the modular structure, we propose a round-robin segment sharing scheme, where each client uploads only a complementary LoRA segment per round to reduce network bandwidth. It is further combined with adaptive sparsification methods tailored to LoRA's training dynamics and lossless encoding techniques. We conduct extensive evaluations on both question-answering and value-alignment tasks across multiple datasets and models. The results show that EcoLoRA significantly reduces communication overhead without compromising performance. For instance, it reduces communication time by up to 79% and total training time by up to 65%.

cs.DC↗

arXiv2025

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base.

cs.CL↗

arXiv2025

Accurate humidity and pH synchronized measurement with temperature compensation based on polarization maintaining fiber

Real-time and accurate monitoring of humidity and pH is of great significance in daily life and industrial production. Existing humidity and pH measurement suffer from limitations such as low sensitivity, signal crosstalk, complex system structures, and inability to achieve real-time monitoring. In this work, the surface of a polarization maintaining fiber (PMF) was functionalized with a composite humidity-sensitive polymer composed of polyvinyl alcohol (PVA) and carbon nanosheets (CNs). A humidity-sensitive film with a microporous structure was prepared on the PMF cladding through high-temperature rapid film formation and laser processing, enhancing humidity sensitivity and stability. To enable pH sensing, poly(allylamine hydrochloride) (PAH) and poly (acrylic acid) (PAA) were successively adsorbed onto the PMF surface via electrostatic self-assembly, forming a pH-sensitive nanofilm structure. By connecting a temperature-compensated PMF within the same Sagnac loop and combining it with a multi-wavelength matrix, simultaneous real-time monitoring of humidity, pH, and temperature was achieved, effectively solving the issue of temperature crosstalk and extending toward a universal optical fiber multi-parameter measurement platform.

physics.app-ph↗

arXiv2025

AI based signage classification for linguistic landscape studies

Linguistic Landscape (LL) research traditionally relies on manual photography and annotation of public signages to examine distribution of languages in urban space. While such methods yield valuable findings, the process is time-consuming and difficult for large study areas. This study explores the use of AI powered language detection method to automate LL analysis. Using Honolulu Chinatown as a case study, we constructed a georeferenced photo dataset of 1,449 images collected by researchers and applied AI for optical character recognition (OCR) and language classification. We also conducted manual validations for accuracy checking. This model achieved an overall accuracy of 79%. Five recurring types of mislabeling were identified, including distortion, reflection, degraded surface, graffiti, and hallucination. The analysis also reveals that the AI model treats all regions of an image equally, detecting peripheral or background texts that human interpreters typically ignore. Despite these limitations, the results demonstrate the potential of integrating AI-assisted workflows into LL research to reduce such time-consuming processes. However, due to all the limitations and mis-labels, we recognize that AI cannot be fully trusted during this process. This paper encourages a hybrid approach combining AI automation with human validation for a more reliable and efficient workflow.

cs.LG↗

arXiv2025

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning

As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forgetting specific knowledge in training data, has been widely used in privacy protection. However, MU for safety in MLLM has yet to be fully explored. To address this issue, we propose SAFEERASER, a safety unlearning benchmark for MLLMs, consisting of 3,000 images and 28.8K VQA pairs. We comprehensively evaluate unlearning methods from two perspectives: forget quality and model utility. Our findings show that existing MU methods struggle to maintain model performance while implementing the forget operation and often suffer from over-forgetting. Hence, we introduce Prompt Decouple (PD) Loss to alleviate over-forgetting through decouple prompt during unlearning process. To quantitatively measure over-forgetting mitigated by PD Loss, we propose a new metric called Safe Answer Refusal Rate (SARR). Experimental results demonstrate that combining PD Loss with existing unlearning methods can effectively prevent over-forgetting and achieve a decrease of 79.5% in the SARR metric of LLaVA-7B and LLaVA-13B, while maintaining forget quality and model utility. Our code and dataset will be released upon acceptance. Warning: This paper contains examples of harmful language and images, and reader discretion is recommended.

cs.CV↗

arXiv2025

An Axial-Vector Leptophilic Fifth Force Sourced by Solar Neutrinos

We investigate long-range, purely leptophilic axial-vector interactions mediated by a light gauge boson $A'$ that couples to charged leptons and, by weak symmetry, to left-handed neutrinos. We analyze two realizations, a minimal effective model with muon-only couplings and an anomaly-free axial $U(1)'$ with inter-generation cancellations. In both cases, the solar neutrino flux acts as an extended current that sources a macroscopic $A'$ field at Earth, with spatial components aligned along the Sun-Earth direction. This field produces a distinctive signature in storage-ring measurements of the muon anomalous magnetic moment, $(g-2)_μ$, namely a diurnal, sign-changing contribution that is positive during daytime and negative at night, superimposed on a time-independent positive offset. We obtain bounds $g' \lesssim {O}(10^{-19})$ in both model frameworks for a light, effectively massless mediator. For completeness, we map the solar-neutrino-sourced potential to electron spin-sensor experiments and find $g' \lesssim {O}(10^{-22})$ in the electron channel.

hep-ph↗

arXiv2025

Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models

Mixture-of-Experts (MoE) has become a dominant architecture for scaling Large Language Models (LLMs) efficiently by decoupling total parameters from computational cost. However, this decoupling creates a critical challenge: predicting the model capacity of a given MoE configurations (e.g., expert activation ratio and granularity) remains an unresolved problem. To address this gap, we introduce Efficiency Leverage (EL), a metric quantifying the computational advantage of an MoE model over a dense equivalent. We conduct a large-scale empirical study, training over 300 models up to 28B parameters, to systematically investigate the relationship between MoE architectural configurations and EL. Our findings reveal that EL is primarily driven by the expert activation ratio and the total compute budget, both following predictable power laws, while expert granularity acts as a non-linear modulator with a clear optimal range. We integrate these discoveries into a unified scaling law that accurately predicts the EL of an MoE architecture based on its configuration. To validate our derived scaling laws, we designed and trained Ling-mini-beta, a pilot model for Ling-2.0 series with only 0.85B active parameters, alongside a 6.1B dense model for comparison. When trained on an identical 1T high-quality token dataset, Ling-mini-beta matched the performance of the 6.1B dense model while consuming over 7x fewer computational resources, thereby confirming the accuracy of our scaling laws. This work provides a principled and empirically-grounded foundation for the scaling of efficient MoE models.

cs.CL↗

arXiv2025

Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter

In this work, we present Patch-Adapter, an effective framework for high-resolution text-guided image inpainting. Unlike existing methods limited to lower resolutions, our approach achieves 4K+ resolution while maintaining precise content consistency and prompt alignment, two critical challenges in image inpainting that intensify with increasing resolution and texture complexity. Patch-Adapter leverages a two-stage adapter architecture to scale the diffusion model's resolution from 1K to 4K+ without requiring structural overhauls: (1) Dual Context Adapter learns coherence between masked and unmasked regions at reduced resolutions to establish global structural consistency; and (2) Reference Patch Adapter implements a patch-level attention mechanism for full-resolution inpainting, preserving local detail fidelity through adaptive feature fusion. This dual-stage architecture uniquely addresses the scalability gap in high-resolution inpainting by decoupling global semantics from localized refinement. Experiments demonstrate that Patch-Adapter not only resolves artifacts common in large-scale inpainting but also achieves state-of-the-art performance on the OpenImages and Photo-Concept-Bucket datasets, outperforming existing methods in both perceptual quality and text-prompt adherence.

cs.CV↗

arXiv2025

Multi-objective Bayesian optimization for blocking in extreme value analysis and its application in additive manufacturing

Extreme value theory (EVT) is well suited to model extreme events, such as floods, heatwaves, or mechanical failures, which is required for reliability assessment of systems across multiple domains for risk management and loss prevention. The block maxima (BM) method, a particular approach within EVT, starts by dividing the historical observations into blocks. Then the sample of the maxima for each block can be shown, under some assumptions, to converge to a known class of distributions, which can then be used for analysis. The question of automatic (i.e., without explicit expert input) selection of the block size remains an open challenge. This work proposes a novel Bayesian framework, namely, multi-objective Bayesian optimization (MOBO-D*), to optimize BM blocking for accurate modeling and prediction of extremes in EVT. MOBO-D* formulates two objectives: goodness-of-fit of the distribution of extreme events and the accurate prediction of extreme events to construct an estimated Pareto front for optimal blocking choices. The efficacy of the proposed framework is illustrated by applying it to a real-world case study from the domain of additive manufacturing as well as a synthetic dataset. MOBO-D* outperforms a number of benchmarks and can be naturally extended to high-dimensional cases. The computational experiments show that it can be a promising approach in applications that require repeated automated block size selection, such as optimization or analysis of many datasets at once.

stat.AP↗

arXiv2025

New Physics Search at the CEPC: a General Perspective

The Circular Electron-Positron Collider (CEPC), a proposed next-generation Higgs factory, provides new opportunities to explore physics beyond the Standard Model (SM). With its clean electron-positron collision environment and the ability to collect large samples of Higgs, W, and Z bosons, the CEPC enables precision measurements and searches for new physics. This white paper outlines the CEPC's discovery potential, including studies of exotic decays of the Higgs, Z, and top quarks, dark matter and dark sector phenomena, long-lived particles, supersymmetry, and neutrino-related signatures. Advanced detector technologies and reconstruction techniques, such as one-to-one correspondence reconstruction and jet origin identification, significantly improve sensitivity to rare and weakly interacting processes. The CEPC is particularly well suited to probe the electroweak phase transition and test models of electroweak baryogenesis and dark sector interactions. In addition, global fit analyses highlight the CEPC's complementary role in constraining a wide range of new physics scenarios. These features position the CEPC as a powerful tool for exploring the next frontier in fundamental particle physics in the post-Higgs discovery era.

hep-ex↗

arXiv2025

Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine

In recent years, Multimodal Large Language Models (MLLM) have achieved notable advancements, demonstrating the feasibility of developing an intelligent biomedical assistant. However, current biomedical MLLMs predominantly focus on image-level understanding and restrict interactions to textual commands, thus limiting their capability boundaries and the flexibility of usage. In this paper, we introduce a novel end-to-end multimodal large language model for the biomedical domain, named MedPLIB, which possesses pixel-level understanding. Excitingly, it supports visual question answering (VQA), arbitrary pixel-level prompts (points, bounding boxes, and free-form shapes), and pixel-level grounding. We propose a novel Mixture-of-Experts (MoE) multi-stage training strategy, which divides MoE into separate training phases for a visual-language expert model and a pixel-grounding expert model, followed by fine-tuning using MoE. This strategy effectively coordinates multitask learning while maintaining the computational cost at inference equivalent to that of a single expert model. To advance the research of biomedical MLLMs, we introduce the Medical Complex Vision Question Answering Dataset (MeCoVQA), which comprises an array of 8 modalities for complex medical imaging question answering and image region understanding. Experimental results indicate that MedPLIB has achieved state-of-the-art outcomes across multiple medical visual language tasks. More importantly, in zero-shot evaluations for the pixel grounding task, MedPLIB leads the best small and large models by margins of 19.7 and 15.6 respectively on the mDice metric. The codes, data, and model checkpoints will be made publicly available at https://github.com/ShawnHuang497/MedPLIB.

cs.CV↗

arXiv2025

Probing Scalar-Mediated Sterile Neutrinos with Gravitational Wave and Colliders Signals

We propose a UV-complete extension of the Standard Model in which a gauge-singlet scalar $S$ acquires a vacuum expectation value, generates a Majorana mass for a sterile neutrino $N$, and mixes with the Higgs field. This framework addresses neutrino masses via a seesaw mechanism and, for sufficiently large scalar mixing, can also drive a strong first-order electroweak phase transition, producing gravitational-wave (GW) signals potentially detectable by GW observatories. The Higgs-$S$ mixing also enhances sterile-neutrino pair production at colliders through $s$-channel exchange of the Higgs and $S$. Owing to the small active-sterile mixing angle, $N$ is generically long-lived, yielding characteristic displaced-vertex signatures. The combination of GW observations and displaced-vertex searches at colliders provides complementary cross-checks of the model parameter space.

hep-ph↗

arXiv2025

VLA-Mark: A cross modal watermark for large vision-language alignment model

Vision-language models demand watermarking solutions that protect intellectual property without compromising multimodal coherence. Existing text watermarking methods disrupt visual-textual alignment through biased token selection and static strategies, leaving semantic-critical concepts vulnerable. We propose VLA-Mark, a vision-aligned framework that embeds detectable watermarks while preserving semantic fidelity through cross-modal coordination. Our approach integrates multiscale visual-textual alignment metrics, combining localized patch affinity, global semantic coherence, and contextual attention patterns, to guide watermark injection without model retraining. An entropy-sensitive mechanism dynamically balances watermark strength and semantic preservation, prioritizing visual grounding during low-uncertainty generation phases. Experiments show 7.4% lower PPL and 26.6% higher BLEU than conventional methods, with near-perfect detection (98.8% AUC). The framework demonstrates 96.1\% attack resilience against attacks such as paraphrasing and synonym substitution, while maintaining text-visual consistency, establishing new standards for quality-preserving multimodal watermarking

cs.CV↗

arXiv2025

The Power of the Cosmic Web

We study the cosmological information contained in the cosmic web, categorized as four structure types: nodes, filaments, walls, and voids, using the Quijote simulations and a modified nexus+ algorithm. We show that splitting the density field by the four structure types and combining the power spectrum in each provides much tighter constraints on cosmological parameters than using the power spectrum without splitting. We show the rich information contained in the cosmic web structures -- related to the Hessian of the density field -- for measuring all of the cosmological parameters, and in particular for constraining neutrino mass. We study the constraints as a function of Fourier scale, configuration space smoothing scale, and the underlying field. For the matter field with $k_{\rm max}=0.5\,h/{\rm Mpc}$, we find a factor of $\times20$ tighter constraints on neutrino mass when using smoothing scales larger than 12.5~Mpc/$h$, and $\times80$ tighter when using smoothing scales down to 1.95~Mpc/$h$. However, for the CDM+Baryon field we observe a more modest $\times1.7$ or $\times3.6$ improvement, for large and small smoothing scales respectively. We release our new python package for identifying cosmic structures pycosmmommf at https://github.com/James11222/pycosmommf to enable future studies of the cosmological information of the cosmic web.

astro-ph.CO↗

arXiv2025

Error-In-Variables Methods for Efficient System Identification with Finite-Sample Guarantees

This paper addresses the problem of learning linear dynamical systems from noisy observations. In this setting, existing algorithms either yield biased parameter estimates or have large sample complexities. We resolve these issues by adapting the instrumental variable method and the bias compensation method, originally proposed for error-in-variables models, to our setting. We provide refined non-asymptotic analysis for both methods. Under mild conditions, our algorithms achieve superior sample complexities that match the best-known sample complexity for learning a fully observable system without observation noise.

eess.SY↗

arXiv2025

Testing the Fifth Force on Lepton Spins through Neutrino Oscillations

We investigate a fifth force mediated by a light vector boson that couples to lepton spins, characterized by axial-vector couplings to leptons and vector couplings to nucleons. This interaction generates a potential proportional to the inner product of the lepton spin vector and the nucleon-lepton relative velocity vector, a feature extensively explored with precision spin sensors. Employing weak symmetry, we show that left-handed charged lepton couplings naturally extend to left-handed neutrinos, enabling this fifth force to influence neutrino oscillations. For electron-nucleon couplings, we find that solar and reactor neutrino experiments provide comparable constraints to those from spin sensors and surpass them in the short-range fifth force region. For muon-nucleon couplings, neutrino oscillation experiments exclude the fifth force as a viable explanation for the muon $ g-2 $ anomaly in the context of a vector mediator, tightening the bounds by two orders of magnitude in coupling strength by solar and atmospheric neutrino data. Our results highlight the critical role of neutrino oscillations in probing fifth forces acting across all three generations of lepton spins.

hep-ph↗