arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 523 records · Page 29Linked to original sources

arXiv2026

TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning

Travel planning is a sophisticated decision-making process that requires synthesizing multifaceted information to construct itineraries. However, existing travel planning approaches face several challenges: (1) Pruning candidate points of interest (POIs) while maintaining a high recall rate; (2) A single reasoning path restricts the exploration capability within the feasible solution space for travel planning; (3) Simultaneously optimizing hard constraints and soft constraints remains a significant difficulty. To address these challenges, we propose TourPlanner, a comprehensive framework featuring multi-path reasoning and constraint-gated reinforcement learning. Specifically, we first introduce a Personalized Recall and Spatial Optimization (PReSO) workflow to construct spatially-aware candidate POIs' set. Subsequently, we propose Competitive consensus Chain-of-Thought (CCoT), a multi-path reasoning paradigm that improves the ability of exploring the feasible solution space. To further refine the plan, we integrate a sigmoid-based gating mechanism into the reinforcement learning stage, which dynamically prioritizes soft-constraint satisfaction only after hard constraints are met. Experimental results on travel planning benchmarks demonstrate that TourPlanner achieves state-of-the-art performance, significantly surpassing existing methods in both feasibility and user-preference alignment.

cs.AI↗

arXiv2026

AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives

Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g. generating text not grounded in the audio input. We analyze these grounding failures and identify a distinct taxonomy: Event Omission, False Event Identity, Temporal Relation Error, and Quantitative Temporal Error. To address this, we introduce the AHA (Audio Hallucination Alignment) framework. By leveraging counterfactual hard negative mining, our pipeline constructs a high-quality preference dataset that forces models to distinguish strict acoustic evidence from linguistically plausible fabrications. Additionally, we establish AHA-Eval, a diagnostic benchmark designed to rigorously test these fine-grained temporal reasoning capabilities. We apply this data to align Qwen2.5-Omni. The resulting model, Qwen-Audio-AHA, achieves a 13.7% improvement on AHA-Eval. Crucially, this benefit generalizes beyond our diagnostic set. Our model shows substantial gains on public benchmarks, including 1.3% on MMAU-Test and 1.6% on MMAR, outperforming latest SOTA methods. The model and dataset are open-sourced at https://github.com/LLM-VLM-GSL/AHA.

cs.SD↗

arXiv2026

DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoring

The process monitoring task is characterized by stringent demands for accuracy and efficiency. Current transformer-based methods, characterized by self-attention for temporal fusion, exhibit limitations in accurately understanding the semantic context and efficiently processing monitoring logs, rendering them inadequate for process monitoring. To address these limitations, we introduce DeepFilter, which revises the self-attention mechanism to improve both accuracy and efficiency. As a straightforward yet versatile approach, DeepFilter provides an instrumental baseline for practitioners in process monitoring, whether initiating new projects or enhancing existing capabilities.

cs.AI↗

arXiv2025

VersaSlot: Efficient Fine-grained FPGA Sharing with Big.Little Slots and Live Migration in FPGA Cluster

As FPGAs gain popularity for on-demand application acceleration in data center computing, dynamic partial reconfiguration (DPR) has become an effective fine-grained sharing technique for FPGA multiplexing. However, current FPGA sharing encounters partial reconfiguration contention and task execution blocking problems introduced by the DPR, which significantly degrade application performance. In this paper, we propose VersaSlot, an efficient spatio-temporal FPGA sharing system with novel Big{.}Little slot architecture that can effectively resolve the contention and task blocking while improving resource utilization. For the heterogeneous Big{.}Little architecture, we introduce an efficient slot allocation and scheduling algorithm, along with a seamless cross-board switching and live migration mechanism, to maximize FPGA multiplexing across the cluster. We evaluate the VersaSlot system on an FPGA cluster composed of the latest Xilinx UltraScale+ FPGAs (ZCU216) and compare its performance against four existing scheduling algorithms. The results demonstrate that VersaSlot achieves up to 13.66x lower average response time than the traditional temporal FPGA multiplexing, and up to 2.19x average response time improvement over the state-of-the-art spatio-temporal sharing systems. Furthermore, VersaSlot enhances the LUT and FF resource utilization by 35% and 29% on average, respectively.

cs.DC↗

arXiv2025

Learning Coupled System Dynamics under Incomplete Physical Constraints and Missing Data

Advances in data acquisition and computational methods have accelerated the use of differential equation based modelling for complex systems. Such systems are often described by coupled (or more) variables, yet governing equation is typically available for one variable, while the remaining variable can be accessed only through data. This mismatch between known physics and observed data poses a fundamental challenge for existing physics-informed machine learning approaches, which generally assume either complete knowledge of the governing equations or full data availability across all variables. In this paper, we introduce MUSIC (Multitask Learning Under Sparse and Incomplete Constraints), a sparsity induced multitask neural network framework that integrates partial physical constraints with data-driven learning to recover full-dimensional solutions of coupled systems when physics-constrained and data-informed variables are mutually exclusive. MUSIC employs mesh-free (random) sampling of training data and sparsity regularization, yielding highly compressed models with improved training and evaluation efficiency. We demonstrate that MUSIC accurately learns solutions (shock wave solutions, discontinuous solutions, pattern formation solutions) to complex coupled systems under data-scarce and noisy conditions, consistently outperforming non-sparse formulations. These results highlight MUSIC as a flexible and effective approach for modeling partially observed systems with incomplete physical knowledge.

cs.LG↗

arXiv2025

Search for Light Dark Matter with 259-day data in PandaX-4T

We present a search for light dark matter particles through their interactions with atomic electrons and nucleons, utilizing PandaX-4T data with an effective exposure of 1.04 tonne$\cdot$year for ionization-only data and 1.20 tonne$\cdot$year for paired data. Our analysis focuses on the energy range (efficiency$>$0.01) of approximately 0.33 to 3 keV for nuclear recoils, and from 0.04 to 0.39 keV for electronic recoils. We establish the most stringent constraints on spin-independent dark matter-nucleon interactions within a mass range of 2.5 to 5.0 GeV/$c^2$, spin-dependent neutron-only interactions within 2.0 to 5.3 GeV/$c^2$, and spin-dependent proton-only interactions within 2.0 to 3.8 GeV/$c^2$. Their corresponding limits at 3\,GeV/$c^2$ are $1.1 \times 10^{-43}$, $1.6 \times 10^{-38}$, and $5.6 \times 10^{-37}$\,cm$^2$, respectively. Additionally, our results improve the upper limits on the dark matter-electron scattering cross-section by a factor of 1.5 and 9.3 for heavy and light mediator scenarios respectively within 50 MeV/$c^2$ to 10 GeV/$c^2$, compared with previous best results.

hep-ex↗

arXiv2025

Fun-ASR Technical Report

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model size scaling, and deep integration with large language models (LLMs). However, LLMs are prone to hallucination, which can significantly degrade user experience in real-world ASR applications. In this paper, we present Fun-ASR, a large-scale, LLM-based ASR system that synergistically combines massive data, large model capacity, LLM integration, and reinforcement learning to achieve state-of-the-art performance across diverse and complex speech recognition scenarios. Moreover, Fun-ASR is specifically optimized for practical deployment, with enhancements in streaming capability, noise robustness, code-switching, hotword customization, and satisfying other real-world application requirements. Experimental results show that while most LLM-based ASR systems achieve strong performance on open-source benchmarks, they often underperform on real industry evaluation sets. Thanks to production-oriented optimizations, Fun-ASR achieves state-of-the-art performance on real application datasets, demonstrating its effectiveness and robustness in practical settings. The code and models are accessible at https://github.com/FunAudioLLM/Fun-ASR .

cs.CL↗

arXiv2025

Atomically-precise synthesis and simultaneous integration of 2D transition metal dichalcogenides enabled by nano-confinement

Two-dimensional (2D) materials, such as graphene, transition metal dichalcogenides (TMDs), and hBN, exhibit intriguing properties that are sensitive to their atomic-scale structures and can be further enriched through van der Waals (vdW) integration. However, the precise synthesis and clean integration of 2D materials remain challenging. Here, using graphene or hBN as a vdW capping layer, we create a nano-confined environment that directs the growth kinetics of 2D TMDs (e.g., NbSe2 and MoS2), enabling precise formation of TMD monolayers with tailored morphologies, from isolated monolayer domains to large-scale continuous films and intrinsically-patterned rings. Moreover, Janus S-Mo-Se monolayers are synthesized with atomic precision via vdW-protected bottom-plane chalcogen substitution. Importantly, our approach simultaneously produces ultraclean vdW interfaces. This in situ encapsulation reliably preserves air-sensitive materials, as evidenced by the enhanced superconductivity of nano-confined NbSe2 monolayers. Altogether, our study establishes a versatile platform for the controlled synthesis and integration of 2D TMDs for advanced applications.

cond-mat.mtrl-sci↗

arXiv2025

TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models

To address the severe data scarcity in Tibetan, a low-resource language spoken by over six million people, we introduce TIBSTC-CoT, the large-scale, multi-domain Tibetan dataset automatically constructed via chain-of-thought prompting with large language models (LLMs). TIBSTC-CoT establishes a scalable and reproducible framework for dataset creation in low-resource settings, covering diverse domains and reasoning patterns essential for language understanding and generation. Building on this dataset, we develop the Sunshine-thinking LLM family, a series of Tibetan-centric LLMs equipped with chain-of-thought capabilities. Trained entirely on TIBSTC-CoT, Sunshine-thinking has demonstrated strong reasoning and generation performance, comparable to state-of-the-art (SOTA) multilingual LLMs. Our work marks a significant step toward inclusive AI by enabling high-quality Tibetan language processing through both resource creation and model innovation. All data are available: https://github.com/Vicentvankor/sun-shine.

cs.CL↗

arXiv2025

From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models

Click-Through Rate (CTR) prediction, a core task in recommendation systems, aims to estimate the probability of users clicking on items. Existing models predominantly follow a discriminative paradigm, which relies heavily on explicit interactions between raw ID embeddings. However, this paradigm inherently renders them susceptible to two critical issues: embedding dimensional collapse and information redundancy, stemming from the over-reliance on feature interactions \emph{over raw ID embeddings}. To address these limitations, we propose a novel \emph{Supervised Feature Generation (SFG)} framework, \emph{shifting the paradigm from discriminative ``feature interaction" to generative ``feature generation"}. Specifically, SFG comprises two key components: an \emph{Encoder} that constructs hidden embeddings for each feature, and a \emph{Decoder} tasked with regenerating the feature embeddings of all features from these hidden representations. Unlike existing generative approaches that adopt self-supervised losses, we introduce a supervised loss to utilize the supervised signal, \ie, click or not, in the CTR prediction task. This framework exhibits strong generalizability: it can be seamlessly integrated with most existing CTR models, reformulating them under the generative paradigm. Extensive experiments demonstrate that SFG consistently mitigates embedding collapse and reduces information redundancy, while yielding substantial performance gains across various datasets and base models. The code is available at https://github.com/USTC-StarTeam/GE4Rec.

cs.IR↗

arXiv2025

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models are progressively endowed with strong general capabilities, standard Vision Transformer (ViT) encoders remain a critical bottleneck, suffering from excessive latency and memory consumption when processing high-resolution inputs.To address these challenges, we introduce HyperVL, an efficient multimodal large language model tailored for on-device inference. HyperVL adopts an image-tiling strategy to cap peak memory usage and incorporates two novel techniques: (1) a Visual Resolution Compressor (VRC) that adaptively predicts optimal encoding resolutions to eliminate redundant computation, and (2) Dual Consistency Learning (DCL), which aligns multi-scale ViT encoders within a unified framework, enabling dynamic switching between visual branches under a shared LLM. Extensive experiments demonstrate that HyperVL achieves state-of-the-art performance among models of comparable size across multiple benchmarks. Furthermore, it significantly significantly reduces latency and power consumption on real mobile devices, demonstrating its practicality for on-device multimodal inference.

cs.CV↗

arXiv2025

Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping

Accurately mapping legal terminology across languages remains a significant challenge, especially for language pairs like Chinese and Japanese, which share a large number of homographs with different meanings. Existing resources and standardized tools for these languages are limited. To address this, we propose a human-AI collaborative approach for building a multilingual legal terminology database, based on a multi-agent framework. This approach integrates advanced large language models and legal domain experts throughout the entire process-from raw document preprocessing, article-level alignment, to terminology extraction, mapping, and quality assurance. Unlike a single automated pipeline, our approach places greater emphasis on how human experts participate in this multi-agent system. Humans and AI agents take on different roles: AI agents handle specific, repetitive tasks, such as OCR, text segmentation, semantic alignment, and initial terminology extraction, while human experts provide crucial oversight, review, and supervise the outputs with contextual knowledge and legal judgment. We tested the effectiveness of this framework using a trilingual parallel corpus comprising 35 key Chinese statutes, along with their English and Japanese translations. The experimental results show that this human-in-the-loop, multi-agent workflow not only improves the precision and consistency of multilingual legal terminology mapping but also offers greater scalability compared to traditional manual methods.

cs.CL↗

arXiv2025

Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior

As generative models become increasingly capable of producing high-fidelity visual content, the demand for efficient, interpretable, and editable image representations has grown substantially. Recent advances in 2D Gaussian Splatting (2DGS) have emerged as a promising solution, offering explicit control, high interpretability, and real-time rendering capabilities (>1000 FPS). However, high-quality 2DGS typically requires post-optimization. Existing methods adopt random or heuristics (e.g., gradient maps), which are often insensitive to image complexity and lead to slow convergence (>10s). More recent approaches introduce learnable networks to predict initial Gaussian configurations, but at the cost of increased computational and architectural complexity. To bridge this gap, we present Fast-2DGS, a lightweight framework for efficient Gaussian image representation. Specifically, we introduce Deep Gaussian Prior, implemented as a conditional network to capture the spatial distribution of Gaussian primitives under different complexities. In addition, we propose an attribute regression network to predict dense Gaussian properties. Experiments demonstrate that this disentangled architecture achieves high-quality reconstruction in a single forward pass, followed by minimal fine-tuning. More importantly, our approach significantly reduces computational cost without compromising visual quality, bringing 2DGS closer to industry-ready deployment.

cs.CV↗

arXiv2025

Towards Task-Oriented Flying: Framework, Infrastructure, and Principles

Deploying robot learning methods to aerial robots in unstructured environments remains both challenging and promising. While recent advances in deep reinforcement learning (DRL) have enabled end-to-end flight control, the field still lacks systematic design guidelines and a unified infrastructure to support reproducible training and real-world deployment. We present a task-oriented framework for end-to-end DRL in quadrotors that integrates design principles for complex task specification and reveals the interdependencies among simulated task definition, training design principles, and physical deployment. Our framework involves software infrastructure, hardware platforms, and open-source firmware to support a full-stack learning infrastructure and workflow. Extensive empirical results demonstrate robust flight and sim-to-real generalization under real-world disturbances. By reducing the entry barrier for deploying learning-based controllers on aerial robots, our work lays a practical foundation for advancing autonomous flight in dynamic and unstructured environments.

cs.RO↗

arXiv2025

Dual-wavelength Fourier Ptychographic Topography

We introduce a dual-wavelength Fourier ptychographic topography (FPT) method that extends the lambda/2 height-range limit of single-wavelength FPT. By reconstructing complex fields at two illumination wavelengths and exploiting their phase difference, the method achieves an effective synthetic wavelength lambda_s and an unambiguous range of lambda_s/2 without reducing lateral resolution. A noise-robust wrapped-number search is used to select per-pixel integer pairs (k1, k2), and a global refinement with circular TV regularization and soft bounds improves stability and preserves height discontinuities. The approach is validated through rigorous scattering-model-based simulations and experiments on structured silicon samples, demonstrating accurate height recovery in regimes where single-wavelength FPT exhibits phase wrapping. We analyze the limits of the FPT forward model and identify aspect ratio (AR) and phase modulation transfer function (ph-MTF) as key predictors of reconstruction fidelity. Simulations and experiments show that increasing AR beyond a practical threshold causes loss of high-frequency phase transfer and destabilizes dual-wavelength unwrapping. Within this AR range, dual-wavelength FPT provides robust, high-resolution topography suitable for semiconductor and industrial metrology.

physics.optics↗

arXiv2025

EP241217a: a likely Type II GRB with an achromatic bump at z = 4.59

EP241217a is an X-ray transient detected by the Einstein Probe (EP) lasting for about 100 seconds and without accompanying $γ$-ray detection. The optical spectroscopy reveals the redshift of EP241217a is 4.59. By combining the $γ$-ray upper limit provided by GECAM-C, there is a considerable possibility that EP241217a is a typical Type II gamma-ray burst (GRB), but it is fainter than the detection threshold of any available $γ$-ray monitors (i.e., $E_{γ,{\rm iso}}\lesssim10^{53}$ erg). The X-ray light curve exhibits a plateau lasting for $\sim5\times10^4$ seconds. However, the joint analysis with optical data suggests the presence of an achromatic bump peaking at $\sim3\times10^4$ s after the trigger, indicating the actual duration of the X-ray plateau may be significantly shorter than it appears. To interpret the achromatic bump, we adopt the scenario of a mildly relativistic jet coasting in a wind-like medium and encountering a rapid density enhancement of the circumburst medium, which is likely induced by the the interaction of the progenitor's stellar wind and the interstellar medium. However, this model cannot fully explain observed data, and some issues do exist, e.g., the observed spectrum is harder than the model prediction. Consequently, we conclude that the scenario of a mildly relativistic jet coasting in the wind-like medium cannot explain all observed features of EP241217a. In addition, some alternative models commonly invoked to explain X-ray plateaus are discussed, but there are more or less issues when they are applied to EP241217a. Therefore, further theoretical modeling is encouraged to explore the origin of EP241217a.

astro-ph.HE↗

arXiv2025

ZeroMat: Solving Cold-start Problem of Recommender System with No Input Data

Recommender system is an applicable technique in most E-commerce commercial product technical designs. However, nearly all recommender system faces a challenge called the cold-start problem. The problem is so notorious that almost every industrial practitioner needs to resolve this issue when building recommender systems. Most cold-start problem solvers need some kind of data input as the starter of the system. On the other hand, many real-world applications place popular items or random items as recommendation results. In this paper, we propose a new technique called ZeroMat that requries no input data at all and predicts the user item rating data that is competitive in Mean Absolute Error and fairness metric compared with the classic matrix factorization with affluent data, and much better performance than random placement.

cs.IR↗

arXiv2025

Compare Similarities Between DNA Sequences Using Permutation-Invariant Quantum Kernel

Computing the similarity between two DNA sequences is of vital importance in bioscience, yet it can be computationally expensive on classical hardware. For example, the edit distance with move operations (EDM), a DNA similarity measure of interest in biology, is proven to be NP-Complete to compute exactly on classical hardware. Recently, applied quantum algorithms have been anticipated to offer potential advantages over classical approaches. In this paper, we propose a novel variational quantum kernel model served as a surrogate model for estimating similarity between DNA sequences defined by EDM. Since the EDM metric exhibits a pairwise permutation-insensitive property, we incorporate a permutation-invariant structure into the variational quantum kernel to approximate this symmetry. Furthermore, to encode the four nucleotide bases as quantum states, we introduce a theoretically motivated encoding scheme based on symmetric informationally complete positive operator-valued measure (SIC-POVM) states. This encoding ensures mutual equivalence among bases, as each pair of symbols is mapped to quantum states that are equidistant on the Bloch sphere. We experimentally show that, equipped with the permutation-invariant circuit design and mutual-equivalence encoding, the proposed quantum kernel model achieves strong performance in approximating the similarity defined by EDM. Compared with classical kernel learning methods, our quantum approach achieves significantly higher accuracy while using substantially fewer trainable parameters.

quant-ph↗