arXiv subjects

Hao Zhang

Publications and source records attributed to Hao Zhang.

At least 415 records · Page 23Linked to original sources

arXiv2025

Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategy

Current image generation systems produce high-quality images but struggle with ambiguous user prompts, making interpretation of actual user intentions difficult. Many users must modify their prompts several times to ensure the generated images meet their expectations. While some methods focus on enhancing prompts to make the generated images fit user needs, the model is still hard to understand users' real needs, especially for non-expert users. In this research, we aim to enhance the visual parameter-tuning process, making the model user-friendly for individuals without specialized knowledge and better understand user needs. We propose a human-machine co-adaption strategy using mutual information between the user's prompts and the pictures under modification as the optimizing target to make the system better adapt to user needs. We find that an improved model can reduce the necessity for multiple rounds of adjustments. We also collect multi-round dialogue datasets with prompts and images pairs and user intent. Various experiments demonstrate the effectiveness of the proposed method in our proposed dataset. Our dataset and annotation tools will be available.

cs.CV↗

arXiv2025

AMAZe: A Multi-Agent Zero-shot Index Advisor for Relational Databases

Index recommendation is one of the most important problems in database management system (DBMS) optimization. Given queries and certain index-related constraints, traditional methods rely on heuristic optimization or learning-based models to select effective indexes and improve query performance. However, heuristic optimization suffers from high computation time, and learning-based models lose generalisability due to training for different workloads and database schemas. With the recent rapid development of large language models (LLMs), methods using prompt tuning have been proposed to enhance the efficiency of index selection. However, such methods still can not achieve the state-of-the-art (SOTA) results, and preparing the index selection demonstrations is also resource-intensive. To address these issues, we propose AMAZe, a zero-shot LLM-based index advisor with a multi-agent framework. We decompose the index recommendation problem into sub-steps, including planning, selection, combination, revision, and reflection. A set of LLM-embedded agents is designed to handle each one of the different sub-steps. Our method utilizes high-level agents to control the index selection process and low-level agents to select and revise indexes. Through extensive experiments, we show that our proposed AMAZe not only achieves the SOTA performance compared to the heuristic methods, but also outperforms learning-based and prompt-based methods with higher efficiency and better zero-shot inference ability.

cs.DB↗

arXiv2025

Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

The creation of high-quality 3D assets, a cornerstone of modern game development, has long been characterized by labor-intensive and specialized workflows. This paper presents Hunyuan3D Studio, an end-to-end AI-powered content creation platform designed to revolutionize the game production pipeline by automating and streamlining the generation of game-ready 3D assets. At its core, Hunyuan3D Studio integrates a suite of advanced neural modules (such as Part-level 3D Generation, Polygon Generation, Semantic UV, etc.) into a cohesive and user-friendly system. This unified framework allows for the rapid transformation of a single concept image or textual description into a fully-realized, production-quality 3D model complete with optimized geometry and high-fidelity PBR textures. We demonstrate that assets generated by Hunyuan3D Studio are not only visually compelling but also adhere to the stringent technical requirements of contemporary game engines, significantly reducing iteration time and lowering the barrier to entry for 3D content creation. By providing a seamless bridge from creative intent to technical asset, Hunyuan3D Studio represents a significant leap forward for AI-assisted workflows in game development and interactive media.

cs.CV↗

arXiv2025

Cyclic Variational Quantum Eigensolver: Escaping Barren Plateaus through Staircase Descent

We introduce the Cyclic Variational Quantum Eigensolver (CVQE), a hardware-efficient framework for accurate ground-state quantum simulation on noisy intermediate-scale quantum (NISQ) devices. CVQE departs from conventional VQE by incorporating a measurement-driven feedback cycle: Slater determinants with significant sampling probability are iteratively added to the reference superposition, while a fixed entangler (e.g., single-layer UCCSD) is reused throughout. This adaptive reference growth systematically enlarges the variational space in most promising directions, avoiding manual ansatz or operator-pool design, costly searches, and preserving compile-once circuits. The strategy parallels multi-reference methods in quantum chemistry, while remaining fully automated on quantum hardware. Remarkably, CVQE exhibits a distinctive staircase-like descent pattern, where successive energy drops sharply signal efficient escape from barren plateaus. Benchmarks show that CVQE consistently maintains chemical precision across correlation regimes, outperforms fixed UCCSD by several orders of magnitude, and achieves favorable accuracy-cost trade-offs compared to the Selected Configuration Interaction. These results position CVQE as a scalable, interpretable, and resource-efficient paradigm for near-term quantum simulation.

quant-ph↗

arXiv2025

DOCUEVAL: An LLM-based AI Engineering Tool for Building Customisable Document Evaluation Workflows

Foundation models, such as large language models (LLMs), have the potential to streamline evaluation workflows and improve their performance. However, practical adoption faces challenges, such as customisability, accuracy, and scalability. In this paper, we present DOCUEVAL, an AI engineering tool for building customisable DOCUment EVALuation workflows. DOCUEVAL supports advanced document processing and customisable workflow design which allow users to define theory-grounded reviewer roles, specify evaluation criteria, experiment with different reasoning strategies and choose the assessment style. To ensure traceability, DOCUEVAL provides comprehensive logging of every run, along with source attribution and configuration management, allowing systematic comparison of results across alternative setups. By integrating these capabilities, DOCUEVAL directly addresses core software engineering challenges, including how to determine whether evaluators are "good enough" for deployment and how to empirically compare different evaluation strategies. We demonstrate the usefulness of DOCUEVAL through a real-world academic peer review case, showing how DOCUEVAL enables both the engineering of evaluators and scalable, reliable document evaluation.

cs.IR↗

arXiv2025

Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models

Large Language Models (LLMs) have transformed both everyday life and scientific research. However, adapting LLMs from general-purpose models to specialized tasks remains challenging, particularly in resource-constrained environments. Low-Rank Adaptation (LoRA), a prominent method within Parameter-Efficient Fine-Tuning (PEFT), has emerged as a promising approach to LLMs by approximating model weight updates using low-rank decomposition. However, LoRA is limited by its uniform rank ( r ) allocation to each incremental matrix, and existing rank allocation techniques aimed at addressing this issue remain computationally inefficient, complex, and unstable, hindering practical applications. To address these limitations, we propose Sensitivity-LoRA, an efficient fine-tuning method that dynamically allocates ranks to weight matrices based on both their global and local sensitivities. It leverages the second-order derivatives (Hessian Matrix) of the loss function to effectively capture weight sensitivity, enabling optimal rank allocation with minimal computational overhead. Our experimental results have demonstrated robust effectiveness, efficiency and stability of Sensitivity-LoRA across diverse tasks and benchmarks.

cs.LG↗

arXiv2025

Large character sums with multiplicative coefficients

In this paper, we investigate large values of Dirichlet character sums with multiplicative coefficients $\sum_{n\le N}f(n)χ(n)$. We prove a new Omega result in the region $\exp((\log q)^{\frac12+δ})\le N\le\sqrt q$, where $q$ is the prime modulus.

math.NT↗

arXiv2025

Large values of Dirichlet polynomials with multiplicative coefficients

In this paper, we investigate large values of Dirichlet polynomials with multiplicative coefficients $\sum_{n\le N}f(n)n^{it}$, where $1\ll t\le T$ for large $T$. We prove an improved Omega result in the region $\exp((\log T)^{\frac12+\varepsilon})\le N\le\sqrt T$, where $T$ is large. We also show an Omega result when $\log N$ is around $\sqrt{\log T\log_2T}$.

math.NT↗

arXiv2025

The Diophantine Frobenius Problem revisited

Let $k\ge 2$ and $a_1, a_2, \cdots, a_k$ be positive integers with \[ \gcd(a_1, a_2, \cdots, a_k)=1. \] It is proved that there exists a positive integer $G_{a_1, a_2, \cdots, a_k}$ such that every integer $n$ strictly greater than it can be represented as the form \[ n=a_1x_1+a_2x_2+\cdots+a_kx_k, \quad (x_1, x_2, \cdots, x_k\in\mathbb{Z}_{\ge 0},~\gcd(x_1, x_2, \cdots, x_k)=1). \] We then investigate the size of $G_{a_1, a_2}$ explicitly. Our result strengthens the primality requirement of $x$'s in the classical Diophantine Frobenius Problem.

math.NT↗

arXiv2025

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling

Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and the poor transferability of black-box methods, we propose an activations-guided prompt injection attack framework. We first construct an Energy-based Model (EBM) using activations from a surrogate model to evaluate the quality of adversarial prompts. Guided by the trained EBM, we employ the token-level Markov Chain Monte Carlo (MCMC) sampling to adaptively optimize adversarial prompts, thereby enabling gradient-free black-box attacks. Experimental results demonstrate our superior cross-model transferability, achieving 49.6% attack success rate (ASR) across five mainstream LLMs and 34.6% improvement over human-crafted prompts, and maintaining 36.6% ASR on unseen task scenarios. Interpretability analysis reveals a correlation between activations and attack effectiveness, highlighting the critical role of semantic patterns in transferable vulnerability exploitation.

cs.AI↗

arXiv2025

Optimal Anchor Deployment and Topology Design for Large-Scale AUV Navigation

Seafloor acoustic anchors are an important component of AUV navigation, providing absolute updates that correct inertial dead-reckoning. Unlike terrestrial positioning systems, the deployment of underwater anchor nodes is usually sparse due to the uneven distribution of underwater users, as well as the high economic cost and difficult maintenance of underwater equipment. These anchor nodes lack satellite coverage and cannot form ubiquitous backhaul as terrestrial nodes do. In this paper, we investigate the optimal anchor deployment topology to provide high-quality AUV navigation and positioning services. We first analyze the possible deployment mode in large-scale underwater navigation system, and formulate a topology optimization for underwater anchor node deployment. Then, we derive a scaling law about the influence of anchors in each cluster on the navigation performance within a given area and demonstrate a service area coverage condition with a high probability of reaching the destination. Finally, the optimization performance is evaluated through experimental results.

eess.SP↗

arXiv2025

Analytic Conformal Blocks of $C_2$-cofinite Vertex Operator Algebras II: Convergence of Sewing and Higher Genus Pseudo-$q$-traces

Let $\mathbb V=\bigoplus_{n\in\mathbb N}\mathbb V(n)$ be a $C_2$-cofinite vertex operator algebra. We prove the convergence of Segal's sewing of conformal blocks associated to analytic families of pointed compact Riemann surfaces and grading-restricted generalized $\mathbb V^{\otimes N}$-modules (where $N=1,2,\dots$) that are not necessarily tensor products of $\mathbb V$-modules, generalizing significantly the results on convergence in [Gui24]. We show that ``higher genus pseudo-$q$-traces" (called pseudo-sewing in this article) can be recovered from the above generalization of Segal's sewing to $\mathbb{V}^{\otimes N}$-modules. Therefore, our result on the convergence of the generalized Segal's sewing implies the convergence of pseudo-sewing, and hence covers both the convergence of genus-$0$ sewing in [Hua05a,HLZ12] and the convergence of pseudo-$q$-traces in [Miy04] and [Fio16]. Using a similar method, we also prove the convergence of Virasoro uniformization, i.e., the convergence of conformal blocks deformed by non-automomous meromorphic vector fields near the marked points. The local freeness of the analytic sheaves of conformal blocks is a consequence of this convergence. It will be used in the third paper of this series to prove the sewing-factorization theorem.

math.QA↗

arXiv2025

Spectrum Cognition: Semantic Situation for Next-Generation Spectrum Management

In response to the growing complexity and demands of future wireless communication networks, spectrum cognition has emerged as an essential technique for optimizing spectrum utilization in next-generation wireless networks. This article presents a comprehensive overview of spectrum cognition, underscoring its critical role in enhancing the efficiency and security of future wireless systems through the innovative perspective of "data processing to signal analysis to semantic situation". Semantic situation, as the highest level of spectrum cognition, enables the extraction of meaningful information from raw spectrum data to provide intelligent support for network decisions. We formally define spectrum cognition, clearly distinguishing it from traditional spectrum sensing, and delve into the latest advancements in both traditional and intelligent spectrum cognition frameworks, addressing key challenges in spectrum cognition. Furthermore, we propose concrete technical solutions to address these challenges, highlighting the transformative potential of semantic situation in shaping next-generation wireless systems. Our findings not only contribute to the theoretical understanding of spectrum cognition but also offer practical insights for its implementation in real-world scenarios.

eess.SP↗

arXiv2025

SolEval: Benchmarking Large Language Models for Repository-level Solidity Code Generation

Large language models (LLMs) have transformed code generation. However, most existing approaches focus on mainstream languages such as Python and Java, neglecting the Solidity language, the predominant programming language for Ethereum smart contracts. Due to the lack of adequate benchmarks for Solidity, LLMs' ability to generate secure, cost-effective smart contracts remains unexplored. To fill this gap, we construct SolEval, the first repository-level benchmark designed for Solidity smart contract generation, to evaluate the performance of LLMs on Solidity. SolEval consists of 1,507 samples from 28 different repositories, covering 6 popular domains, providing LLMs with a comprehensive evaluation benchmark. Unlike the existing Solidity benchmark, SolEval not only includes complex function calls but also reflects the real-world complexity of the Ethereum ecosystem by incorporating Gas@k and Vul@k. We evaluate 16 LLMs on SolEval, and our results show that the best-performing LLM achieves only 26.29% Pass@10, highlighting substantial room for improvement in Solidity code generation by LLMs. Additionally, we conduct supervised fine-tuning (SFT) on Qwen-7B using SolEval, resulting in a significant performance improvement, with Pass@5 increasing from 16.67% to 58.33%, demonstrating the effectiveness of fine-tuning LLMs on our benchmark. We release our data and code at https://github.com/pzy2000/SolEval.

cs.SE↗

arXiv2025

Enhanced superconductivity in PbTe-In hybrids

We report the realization of epitaxial indium thin films on PbTe nanowires. The film is continuous and forms an atomically sharp interface with PbTe. Tunneling devices reveal a hard superconducting gap. The gap size, 1.08 to 1.18 meV, is twice as large as bulk indium's ($\sim$ 0.5 meV), due to the presence of PbTe. A similar enhancement is also observed in the critical temperature of In on a PbTe substrate. Subgap peaks appear at finite magnetic fields. The effective $g$-factor (15-45) is notably enhanced compared to bare PbTe wires ($<$ 10) due to the presence of In, differing from Al-hybrids. Josephson devices exhibit gate-tunable supercurrents. The PbTe-In hybrid enhances the properties of both, the superconductivity of In and g-factors of PbTe, and thus may enable exotic phases of matter such as topological superconductivity.

cond-mat.mes-hall↗

arXiv2025

TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration

Existing multi-modal fusion methods typically apply static frame-based image fusion techniques directly to video fusion tasks, neglecting inherent temporal dependencies and leading to inconsistent results across frames. To address this limitation, we propose the first video fusion framework that explicitly incorporates temporal modeling with visual-semantic collaboration to simultaneously ensure visual fidelity, semantic accuracy, and temporal consistency. First, we introduce a visual-semantic interaction module consisting of a semantic branch and a visual branch, with Dinov2 and VGG19 employed for targeted distillation, allowing simultaneous enhancement of both the visual and semantic representations. Second, we pioneer integrate the video degradation enhancement task into the video fusion pipeline by constructing a temporal cooperative module, which leverages temporal dependencies to facilitate weak information recovery. Third, to ensure temporal consistency, we embed a temporal-enhanced mechanism into the network and devise a temporal loss to guide the optimization process. Finally, we introduce two innovative evaluation metrics tailored for video fusion, aimed at assessing the temporal consistency of the generated fused videos. Extensive experimental results on public video datasets demonstrate the superiority of our method. Our code is released at https://github.com/Meiqi-Gong/TemCoCo.

cs.CV↗

arXiv2025

Cooperative Suppression Strategy for Dual Thermal Transport Channels in Crystalline Materials

We propose a novel design principle for achieving ultralow thermal conductivity in crystalline materials via a "heavy-light and soft-stiff" structural motif. By combining heavy and light atomic species with soft and stiff bonding networks, both particle-like ($κ_p$) and wave-like ($κ_c$) phonon transport channels are concurrently suppressed. First-principles calculations show that this architecture induces a hierarchical phonon spectrum: soft-bonded heavy atoms generate dense low-frequency modes that enhance scattering and reduce $κ_p$, while stiff-bonded light atoms produce sparse high-frequency optical branches that disrupt coherence and lower $κ_c$. High-throughput screening identifies Tl$_4$SiS$_4$ ($κ_p$ = 0.10, $κ_c$ = 0.06 W/mK) and Tl$_4$GeS$_4$ ($κ_p$ = 0.09, $κ_c$ = 0.06 W/mK) as representative candidates with strongly suppressed transport in both channels. A minimal 1D triatomic chain model further demonstrates the generality of this mechanism, offering a new paradigm for phonon engineering beyond the conventional $κ_p$-$κ_c$ trade-off.

cond-mat.mtrl-sci↗

arXiv2025

DreamSwapV: Mask-guided Subject Swapping for Any Customized Video Editing

With the rapid progress of video generation, demand for customized video editing is surging, where subject swapping constitutes a key component yet remains under-explored. Prevailing swapping approaches either specialize in narrow domains--such as human-body animation or hand-object interaction--or rely on some indirect editing paradigm or ambiguous text prompts that compromise final fidelity. In this paper, we propose DreamSwapV, a mask-guided, subject-agnostic, end-to-end framework that swaps any subject in any video for customization with a user-specified mask and reference image. To inject fine-grained guidance, we introduce multiple conditions and a dedicated condition fusion module that integrates them efficiently. In addition, an adaptive mask strategy is designed to accommodate subjects of varying scales and attributes, further improving interactions between the swapped subject and its surrounding context. Through our elaborate two-phase dataset construction and training scheme, our DreamSwapV outperforms existing methods, as validated by comprehensive experiments on VBench indicators and our first introduced DreamSwapV-Benchmark.

cs.CV↗