Searcharxiv⌕ Search

arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 505 records · Page 28Linked to original sources
arXiv2026

Towards On-Device Personalization: Cloud-device Collaborative Data Augmentation for Efficient On-device Language Model

With the advancement of large language models (LLMs), significant progress has been achieved in various Natural Language Processing (NLP) tasks. However, existing LLMs still face two major challenges that hinder their broader adoption: (1) their responses tend to be generic and lack personalization tailored to individual users, and (2) they rely heavily on cloud infrastructure due to intensive computational requirements, leading to stable network dependency and response delay. Recent research has predominantly focused on either developing cloud-based personalized LLMs or exploring the on-device deployment of general-purpose LLMs. However, few studies have addressed both limitations simultaneously by investigating personalized on-device language models. To bridge this gap, we propose CDCDA-PLM, a framework for deploying personalized on-device language models on user devices with support from a powerful cloud-based LLM. Specifically, CDCDA-PLM leverages the server-side LLM's strong generalization capabilities to augment users' limited personal data, mitigating the issue of data scarcity. Using both real and synthetic data, A personalized on-device language models (LMs) is fine-tuned via parameter-efficient fine-tuning (PEFT) modules and deployed on users' local devices, enabling them to process queries without depending on cloud-based LLMs. This approach eliminates reliance on network stability and ensures high response speeds. Experimental results across six tasks in a widely used personalization benchmark demonstrate the effectiveness of CDCDA-PLM.

cs.IR↗
arXiv2026

A Gift from the Integration of Discriminative and Diffusion-based Generative Learning: Boundary Refinement Remote Sensing Semantic Segmentation

Remote sensing semantic segmentation must address both what the ground objects are within an image and where they are located. Consequently, segmentation models must ensure not only the semantic correctness of large-scale patches (low-frequency information) but also the precise localization of boundaries between patches (high-frequency information). However, most existing approaches rely heavily on discriminative learning, which excels at capturing low-frequency features, while overlooking its inherent limitations in learning high-frequency features for semantic segmentation. Recent studies have revealed that diffusion generative models excel at generating high-frequency details. Our theoretical analysis confirms that the diffusion denoising process significantly enhances the model's ability to learn high-frequency features; however, we also observe that these models exhibit insufficient semantic inference for low-frequency features when guided solely by the original image. Therefore, we integrate the strengths of both discriminative and generative learning, proposing the Integration of Discriminative and diffusion-based Generative learning for Boundary Refinement (IDGBR) framework. The framework first generates a coarse segmentation map using a discriminative backbone model. This map and the original image are fed into a conditioning guidance network to jointly learn a guidance representation subsequently leveraged by an iterative denoising diffusion process refining the coarse segmentation. Extensive experiments across five remote sensing semantic segmentation datasets (binary and multi-class segmentation) confirm our framework's capability of consistent boundary refinement for coarse results from diverse discriminative architectures.

cs.CV↗
arXiv2026

Momentum-integrated Multi-task Stock Recommendation with Converge-based Optimization

Stock recommendation is critical in Fintech applications, which leverage price series and alternative information to estimate future stock performance. Traditional time-series forecasting training often fails to capture stock trends and rankings simultaneously, which are essential factors for investors. To tackle this issue, we introduce a Multi-Task Learning (MTL) framework for stock recommendation, \textbf{M}omentum-\textbf{i}ntegrated \textbf{M}ulti-task \textbf{Stoc}k \textbf{R}ecommendation with Converge-based Optimization (\textbf{MiM-StocR}). To improve the model's ability to capture short-term trends, we incorporate a momentum line indicator in model training. To prioritize top-performing stocks and optimize investment allocation, we propose a listwise ranking loss function called Adaptive-k ApproxNDCG. Moreover, due to the volatility and uncertainty of the stock market, existing MTL frameworks face overfitting issues when applied to stock time series. To mitigate this issue, we introduce the Converge-based Quad-Balancing (CQB) method. We conducted extensive experiments on three stock benchmarks: SEE50, CSI 100, and CSI 300. MiM-StocR outperforms state-of-the-art MTL baselines across both ranking and profitability evaluations.

q-fin.ST↗
arXiv2026

Adaptively Point-weighting Curriculum Learning

Curriculum learning (CL) mimics human learning, in which easy samples are learned first, followed by harder samples, and has become an effective method for training deep networks. However, many existing automatic CL methods maintain a preference for easy samples during the entire training process regardless of the constantly evolving training state. This is just like a human curriculum that fails to provide individualized instruction, which can delay learning progress. To address this issue, we propose an adaptively point-weighting (APW) curriculum learning method that assigns a weight to each training sample based on its training loss. The weighting strategy of APW follows the easy-to-hard training paradigm, guided by the current training state of the network. We present a theoretical analysis of APW, including training effectiveness, training stability, and generalization performance. Experimental results validate these theoretical findings and demonstrate the superiority of the proposed APW method.

cs.LG↗
arXiv2026

BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling

Human cognition excels at transcending sensory input and forming latent representations that structure our understanding of the world. While Large Language Model (LLM) agents demonstrate emergent reasoning and decision-making abilities, they lack a principled framework for capturing latent structures and modeling uncertainty. In this work, we explore for the first time how to bridge LLM agents with probabilistic graphical models (PGMs) to address agentic reasoning under uncertainty. To this end, we introduce Verbalized Probabilistic Graphical Modeling (vPGM), a Bayesian agentic framework that (i) guides LLM agents in following key principles of PGMs through natural language and (ii) refines the resulting posterior distributions via numerical Bayesian inference. Unlike many traditional probabilistic methods requiring substantial domain expertise, vPGM bypasses expert-driven model design, making it well-suited for scenarios with limited assumptions. We evaluated our model on several agentic reasoning tasks, both close-ended and open-ended. Our results indicate that the model effectively enhances confidence calibration and text generation quality.

cs.LG↗
arXiv2026

On the radius of analyticity and Gevrey regularity for the Boltzmann equation

This paper investigates the non-cutoff Boltzmann equation for hard potentials in a perturbative setting. We first establish a sharp short-time estimate on the radius of analyticity and Gevrey regularity of mild solutions. Furthermore, we obtain a global-in-time radius estimate in Gevrey space. The proof combines hypoelliptic estimates with the macro-micro decomposition.

math.AP↗
arXiv2026

HyperWalker: Dynamic Hypergraph-Based Deep Diagnosis for Multi-Hop Clinical Modeling across EHR and X-Ray in Medical VLMs

Automated clinical diagnosis remains a core challenge in medical AI, which usually requires models to integrate multi-modal data and reason across complex, case-specific contexts. Although recent methods have advanced medical report generation (MRG) and visual question answering (VQA) with medical vision-language models (VLMs), these methods, however, predominantly operate under a sample-isolated inference paradigm, as such processing cases independently without access to longitudinal electronic health records (EHRs) or structurally related patient examples. This paradigm limits reasoning to image-derived information alone, which ignores external complementary medical evidence for potentially more accurate diagnosis. To overcome this limitation, we propose \textbf{HyperWalker}, a \textit{Deep Diagnosis} framework that reformulates clinical reasoning via dynamic hypergraphs and test-time training. First, we construct a dynamic hypergraph, termed \textbf{iBrochure}, to model the structural heterogeneity of EHR data and implicit high-order associations among multimodal clinical information. Within this hypergraph, a reinforcement learning agent, \textbf{Walker}, navigates to and identifies optimal diagnostic paths. To ensure comprehensive coverage of diverse clinical characteristics in test samples, we incorporate a \textit{linger mechanism}, a multi-hop orthogonal retrieval strategy that iteratively selects clinically complementary neighborhood cases reflecting distinct clinical attributes. Experiments on MRG with MIMIC and medical VQA on EHRXQA demonstrate that HyperWalker achieves state-of-the-art performance. Code is available at: https://github.com/Bean-Young/HyperWalker

cs.CL↗
arXiv2026

A Unified Variational Imputation Framework for Electric Vehicle Charging Data Using Retrieval-Augmented Language Model

The reliability of data-driven applications in electric vehicle (EV) infrastructure, such as charging demand forecasting, hinges on the availability of complete, high-quality charging data. However, real-world EV datasets are often plagued by missing records, and existing imputation methods are ill-equipped for the complex, multimodal context of charging data, often relying on a restrictive one-model-per-station paradigm that ignores valuable inter-station correlations. To address these gaps, we develop a novel PRobabilistic variational imputation framework that leverages the power of large lAnguage models and retrIeval-augmented Memory (PRAIM). PRAIM employs a pre-trained language model to encode heterogeneous data, spanning time-series demand, calendar features, and geospatial context, into a unified, semantically rich representation. This is dynamically fortified by retrieval-augmented memory that retrieves relevant examples from the entire charging network, enabling a single, unified imputation model empowered by variational neural architecture to overcome data sparsity. Extensive experiments on four public datasets demonstrate that PRAIM significantly outperforms established baselines in both imputation accuracy and its ability to preserve the original data's statistical distribution, leading to substantial improvements in downstream forecasting performance.

cs.LG↗
arXiv2026

Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions

Emotional text-to-speech (TTS) systems sturggle to capture the full spectrum of human emotions due to the inherent complexity of emotional expressions and the limited coverage of existing emotion labels. To address this, we propose a language model-based TTS framework that synthesizes speech across a broad range of emotional styles. Our approach enables flexible user control along three continuous dimensions - pleasure, arousal, and dominance (PAD). To enable this, we train an emotional dimension predictor that maps categorical emotion labels in speech datasets into the PAD space, grounded in established psychological research. Importantly, while the emotional dimension predictor leverages categorical labels, the TTS framework itself does not require explict emotion labels during training. Objective and subjective evaluations demonstrate that our framework effectively generates more expressive emotional styles and enhances both naturalness and diversity compared to baselines.

eess.AS↗
arXiv2026

Pollutant-induced changes in fish pigmentation and spatial patterns

Pigmentation abnormalities, ranging from hypo- to hyperpigmentation, can serve as biomarkers of developmental disruption in fish exposed to environmental contaminants. However, the mechanistic pathways underlying these alterations remain poorly understood. Studies have shown that pattern formation in fish development requires specific pigment cell interactions. Motivated by experimental observations of pigmentation alterations following contaminant exposure, we investigate how pollutants influence pigment cell self-organization using a continuum reaction-diffusion-advection framework. The model incorporates nonlocal Morse-type kernels to describe short- and long-range interactions among melanophores and xanthophores. Our results show that perturbations to the strengths of adhesion or repulsion can drive transitions between stripes, spots, and mixed patterns, reproducing phenotypes characteristic of fish pigmentation mutants. In particular, homotypic interactions are sensitive to contamination, leading to pronounced changes in melanophore density and resulting pigmentation patterns. Time-dependent simulations indicate that pigment changes from early short-term contaminant exposure may be recoverable, whereas prolonged exposure can lead to sustained pigment loss. In a growing fish, contaminant-induced changes in cell-cell interactions directly influence stripe formation rate, stripe number, and pigmentation levels. Overall, our study provides insight into the mechanistic link between experimentally observed pigmentation alterations and the changes in spatial patterns of adult fish.

q-bio.QM↗
arXiv2026

Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay

Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red teaming, utilizing fixed defense prompts or pre-collected adversarial datasets. This leads to a rigid defense that overfits known patterns and fails to generalize to novel, sophisticated threats. To address this critical limitation, we propose empowering the model to be its own red teamer, capable of achieving autonomous and evolving adversarial attacks. Specifically, we introduce Safety Self- Play (SSP), a system that utilizes a single LLM to act concurrently as both the Attacker (generating jailbreaks) and the Defender (refusing harmful requests) within a unified Reinforcement Learning (RL) loop, dynamically evolving attack strategies to uncover vulnerabilities while simultaneously strengthening defense mechanisms. To ensure the Defender effectively addresses critical safety issues during the self-play, we introduce an advanced Reflective Experience Replay Mechanism, which uses an experience pool accumulated throughout the process. The mechanism employs a Upper Confidence Bound (UCB) sampling strategy to focus on failure cases with low rewards, helping the model learn from past hard mistakes while balancing exploration and exploitation. Extensive experiments demonstrate that our SSP approach autonomously evolves robust defense capabilities, significantly outperforming baselines trained on static adversarial datasets and establishing a new benchmark for proactive safety alignment.

cs.CR↗
arXiv2026

Interpreting Fedspeak with Confidence: A LLM-Based Uncertainty-Aware Framework Guided by Monetary Policy Transmission Paths

"Fedspeak", the stylized and often nuanced language used by the U.S. Federal Reserve, encodes implicit policy signals and strategic stances. The Federal Open Market Committee strategically employs Fedspeak as a communication tool to shape market expectations and influence both domestic and global economic conditions. As such, automatically parsing and interpreting Fedspeak presents a high-impact challenge, with significant implications for financial forecasting, algorithmic trading, and data-driven policy analysis. In this paper, we propose an LLM-based, uncertainty-aware framework for deciphering Fedspeak and classifying its underlying monetary policy stance. Technically, to enrich the semantic and contextual representation of Fedspeak texts, we incorporate domain-specific reasoning grounded in the monetary policy transmission mechanism. We further introduce a dynamic uncertainty decoding module to assess the confidence of model predictions, thereby enhancing both classification accuracy and model reliability. Experimental results demonstrate that our framework achieves state-of-the-art performance on the policy stance analysis task. Moreover, statistical analysis reveals a significant positive correlation between perceptual uncertainty and model error rates, validating the effectiveness of perceptual uncertainty as a diagnostic signal.

cs.AI↗
arXiv2026

GPS-Synchronized Monitoring of Core-collapse Supernova Bursts with PandaX-4T via Coherent Elastic Neutrino Nuclear Scattering

The landmark detection of neutrinos from SN1987A marked the dawn of neutrino astrophysics. The neutrino burst provided essential insights into fundamental properties of neutrinos, and served as key probes of stellar evolution and supernova dynamics. The recent advancement in coherent elastic neutrino-nucleus scattering enables the detection of core-collapse supernova burst neutrinos using tonne-scale liquid xenon detectors originally designed for dark matter direct detection. Leveraging this capability, we developed and deployed an online supernova monitoring system for the PandaX-4T experiment. This system features a GPS module with millisecond-level timing precision, a low false-alarm rate, and high sensitivity to galactic core-collapse supernova explosion events. The methodology is robust, directly scalable, and planned for implementation in the next-generation PandaX-20T experiment.

hep-ex↗
arXiv2026

Towards Intelligent Systems for Battery Management: A Five-Tier Digital Twin Architecture

As digital twin technologies are increasingly incorporated into battery management systems to meet the growing need for transparent and lifecycle-aware operation, existing battery digital twins still suffer from fragmented operational processes and lack an architectural perspective to coordinate modeling, inference, and decision-making throughout the battery lifecycle. To this end, we develop a unified five-tier battery digital twin framework that integrates key functionalities into a coherent pipeline and facilitates a clearer architectural understanding of digital twins. The five-tier comprises geometric modeling, descriptive analytics, physics-informed prediction, prescriptive optimization, and autonomous control. In quantitative evaluation, the resulting architecture achieves high-fidelity multi-physics calibration with 0.92\% voltage and 0.18\% temperature prediction error, and provides state-of-health estimation with 1.09\% MAPE and calibrated uncertainty. As the first battery digital twin system empowered by the NVIDIA ecosystem with physics-AI technologies, our proposed five-tier framework shifts battery management from reactive protection to an interpretable, predictive, and autonomous paradigm, paving the path to develop next-generation battery management and energy management systems.

cs.NI↗
arXiv2026

EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent

As a cornerstone of the modern digital economy, 3D modeling and rendering demand substantial resources and manual effort when scene editing is performed in the traditional manner. Despite recent progress in VLM-based agents for 3D editing, the fundamental trade-off between editing precision and agent responsiveness remains unresolved. To overcome these limitations, we present EZBlender, a Blender agent with a hybrid framework that combines planning-based task decomposition and reactive local autonomy for efficient human AI collaboration and semantically faithful 3D editing. Specifically, this unexplored Plan-and-ReAct design not only preserves editing quality but also significantly reduces latency and computational cost. To further validate the efficiency and effectiveness of the proposed edge-autonomy architecture, we construct a dedicated multi-tasking benchmark that has not been systematically investigated in prior research. In addition, we provide a comprehensive analysis of language model preference, system responsiveness, and economic efficiency.

cs.HC↗
arXiv2026

Impact of a negative cosmological constant on the reconstruction of dark energy in light of DESI BAO data

An anti-de Sitter vacuum, corresponding to a negative cosmological constant (NCC), might coexist with one evolving positive dark energy component at low redshift and is hinted by the latest DESI observations. In this paper, we use two methods, \textit{redshift-binned} and \textit{Gaussian Process-based} reconstructions to investigate the effect of a NCC on the equation of state (EOS) $w(z)$ of evolving dark energy (DE) component. We find that a NCC is slightly preferred in both the two reconstructions by up to $\simeq1σ$. Although the degeneracy between the EOS of evolving DE component and NCC weakens the constraint on the reconstructed $w(z)$, this degeneracy leads to the phantom divide $w=-1$ more consistent with the 1$σ$ posterior of $w(z)$.

astro-ph.CO↗
arXiv2026

RobustFormer: Noise-Robust Pre-training for images and videos

While deep learning-based models like transformers, have revolutionized time-series and vision tasks, they remain highly susceptible to noise and often overfit on noisy patterns rather than robust features. This issue is exacerbated in vision transformers, which rely on pixel-level details that can easily be corrupt. To address this, we leverage the discrete wavelet transform (DWT) for its ability to decompose into multi-resolution layers, isolating noise primarily in the high frequency domain while preserving essential low-frequency information for resilient feature learning. Conventional DWT-based methods, however, struggle with computational inefficiencies due to the requirement for a subsequent inverse discrete wavelet transform (IDWT) step. In this work, we introduce RobustFormer, a novel framework that enables noise-robust masked autoencoder (MAE) pre-training for both images and videos by using DWT for efficient downsampling, eliminating the need for expensive IDWT reconstruction and simplifying the attention mechanism to focus on noise-resilient multi-scale representations. To our knowledge, RobustFormer is the first DWT-based method fully compatible with video inputs and MAE-style pre-training. Extensive experiments on noisy image and video datasets demonstrate that our approach achieves up to 8% increase in Top-1 classification accuracy under severe noise conditions in Imagenet-C and up to 2.7% in Imagenet-P standard benchmarks compared to the baseline and up to 13% higher Top-1 accuracy on UCF-101 under severe custom noise perturbations while maintaining similar accuracy scores for clean datasets. We also observe the reduction of computation complexity by up to 4.4% through IDWT removal compared to VideoMAE baseline without any performance drop.

cs.CV↗
arXiv2026

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?

Recent supervised fine-tuning (SFT) approaches have significantly improved language models' performance on mathematical reasoning tasks, even when models are trained at a small scale. However, the specific capabilities enhanced through such fine-tuning remain poorly understood. In this paper, we conduct a detailed analysis of model performance on the AIME24 dataset to understand how reasoning capabilities evolve. We discover a ladder-like structure in problem difficulty, categorize questions into four tiers (Easy, Medium, Hard, and Extremely Hard (Exh)), and identify the specific requirements for advancing between tiers. We find that progression from Easy to Medium tier requires adopting an R1 reasoning style with minimal SFT (500-1K instances), while Hard-level questions suffer from frequent model's errors at each step of the reasoning chain, with accuracy plateauing at around 65% despite logarithmic scaling. Exh-level questions present a fundamentally different challenge; they require unconventional problem-solving skills that current models uniformly struggle with. Additional findings reveal that carefully curated small-scale datasets offer limited advantage-scaling dataset size proves far more effective. Our analysis provides a clearer roadmap for advancing language model capabilities in mathematical reasoning.

cs.AI↗