arXiv subjects

Qiang Liu

Publications and source records attributed to Qiang Liu.

At least 127 records · Page 7Linked to original sources

arXiv2025

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation

Text-to-image synthesis has made remarkable progress, yet accurately interpreting complex and lengthy prompts remains challenging, often resulting in semantic inconsistencies and missing details. Existing solutions, such as fine-tuning, are model-specific and require training, while prior automatic prompt optimization (APO) approaches typically lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness. Meanwhile, test-time scaling methods operate on fixed prompts and on noise or sample numbers, limiting their interpretability and adaptability. To solve these, we introduce a flexible and efficient test-time prompt optimization strategy that operates directly on the input text. We propose a plug-and-play multi-agent system called GenPilot, integrating error analysis, clustering-based adaptive exploration, fine-grained verification, and a memory module for iterative optimization. Our approach is model-agnostic, interpretable, and well-suited for handling long and complex prompts. Simultaneously, we summarize the common patterns of errors and the refinement strategy, offering more experience and encouraging further exploration. Experiments on DPG-bench and Geneval with improvements of up to 16.9% and 5.7% demonstrate the strong capability of our methods in enhancing the text and image consistency and structural coherence of generated images, revealing the effectiveness of our test-time prompt optimization strategy. The code is available at https://github.com/27yw/GenPilot.

cs.CV↗

arXiv2025

Muon Optimizes Under Spectral Norm Constraints

The pursuit of faster optimization algorithms remains an active and important research direction in deep learning. Recently, the Muon optimizer [JJB+24] has demonstrated promising empirical performance, but its theoretical foundation remains less understood. In this paper, we bridge this gap and provide a theoretical analysis of Muon by placing it within the Lion-$\mathcal{K}$ family of optimizers [CLLL24]. Specifically, we show that Muon corresponds to Lion-$\mathcal{K}$ when equipped with the nuclear norm, and we leverage the theoretical results of Lion-$\mathcal{K}$ to establish that Muon (with decoupled weight decay) implicitly solves an optimization problem that enforces a constraint on the spectral norm of weight matrices. This perspective not only demystifies the implicit regularization effects of Muon but also leads to natural generalizations through varying the choice of convex map $\mathcal{K}$, allowing for the exploration of a broader class of implicitly regularized and constrained optimization algorithms.

cs.LG↗

arXiv2025

VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks

The "Reason-Then-Respond" paradigm, enhanced by Reinforcement Learning, has shown great promise in advancing Multimodal Large Language Models. However, its application to the video domain has led to specialized models that excel at either question answering (QA) or captioning tasks, but struggle to master both. Naively combining reward signals from these tasks results in mutual performance degradation, which we attribute to a conflict between their opposing task natures. To address this challenge, we propose a novel training framework built upon two intermediate proxy tasks: DarkEventInfer, which presents videos with masked event segments, requiring models to infer the obscured content based on contextual video cues; and MixVidQA, which presents interleaved video sequences composed of two distinct clips, challenging models to isolate and reason about one while disregarding the other. These proxy tasks compel the model to simultaneously develop both holistic, divergent understanding and precise, convergent reasoning capabilities. Embodying this framework, we present VidBridge-R1, the first versatile video reasoning model that effectively bridges the paradigm conflict. Extensive experiments show that VidBridge-R1 achieves significant performance gains on both QA and captioning within one model, demonstrating the efficacy of our approach in fostering more generalizable and powerful video understanding models.

cs.CV↗

arXiv2025

STRIVE: Structured Reasoning for Self-Improvement in Claim Verification

Claim verification is the task of determining whether a claim is supported or refuted by evidence. Self-improvement methods, where reasoning chains are generated and those leading to correct results are selected for training, have succeeded in tasks like mathematical problem solving. However, in claim verification, this approach struggles. Low-quality reasoning chains may falsely match binary truth labels, introducing faulty reasoning into the self-improvement process and ultimately degrading performance. To address this, we propose STRIVE: Structured Reasoning for Self-Improved Verification. Our method introduces a structured reasoning design with Claim Decomposition, Entity Analysis, and Evidence Grounding Verification. These components improve reasoning quality, reduce errors, and provide additional supervision signals for self-improvement. STRIVE begins with a warm-up phase, where the base model is fine-tuned on a small number of annotated examples to learn the structured reasoning design. It is then applied to generate reasoning chains for all training examples, selecting only those that are correct and structurally sound for subsequent self-improvement training. We demonstrate that STRIVE achieves significant improvements over baseline models, with a 31.4% performance gain over the base model and 20.7% over Chain of Thought on the HOVER datasets, highlighting its effectiveness.

cs.AI↗

arXiv2025

AgriDoctor: A Multimodal Intelligent Assistant for Agriculture

Accurate crop disease diagnosis is essential for sustainable agriculture and global food security. Existing methods, which primarily rely on unimodal models such as image-based classifiers and object detectors, are limited in their ability to incorporate domain-specific agricultural knowledge and lack support for interactive, language-based understanding. Recent advances in large language models (LLMs) and large vision-language models (LVLMs) have opened new avenues for multimodal reasoning. However, their performance in agricultural contexts remains limited due to the absence of specialized datasets and insufficient domain adaptation. In this work, we propose AgriDoctor, a modular and extensible multimodal framework designed for intelligent crop disease diagnosis and agricultural knowledge interaction. As a pioneering effort to introduce agent-based multimodal reasoning into the agricultural domain, AgriDoctor offers a novel paradigm for building interactive and domain-adaptive crop health solutions. It integrates five core components: a router, classifier, detector, knowledge retriever and LLMs. To facilitate effective training and evaluation, we construct AgriMM, a comprehensive benchmark comprising 400000 annotated disease images, 831 expert-curated knowledge entries, and 300000 bilingual prompts for intent-driven tool selection. Extensive experiments demonstrate that AgriDoctor, trained on AgriMM, significantly outperforms state-of-the-art LVLMs on fine-grained agricultural tasks, establishing a new paradigm for intelligent and sustainable farming applications.

cs.CV↗

arXiv2025

UPRPRC: Unified Pipeline for Reproducing Parallel Resources -- Corpus from the United Nations

The quality and accessibility of multilingual datasets are crucial for advancing machine translation. However, previous corpora built from United Nations documents have suffered from issues such as opaque process, difficulty of reproduction, and limited scale. To address these challenges, we introduce a complete end-to-end solution, from data acquisition via web scraping to text alignment. The entire process is fully reproducible, with a minimalist single-machine example and optional distributed computing steps for scalability. At its core, we propose a new Graph-Aided Paragraph Alignment (GAPA) algorithm for efficient and flexible paragraph-level alignment. The resulting corpus contains over 713 million English tokens, more than doubling the scale of prior work. To the best of our knowledge, this represents the largest publicly available parallel corpus composed entirely of human-translated, non-AI-generated content. Our code and corpus are accessible under the MIT License.

cs.CL↗

arXiv2025

D$^2$HScore: Reasoning-Aware Hallucination Detection via Semantic Breadth and Depth Analysis in LLMs

Although large Language Models (LLMs) have achieved remarkable success, their practical application is often hindered by the generation of non-factual content, which is called "hallucination". Ensuring the reliability of LLMs' outputs is a critical challenge, particularly in high-stakes domains such as finance, security, and healthcare. In this work, we revisit hallucination detection from the perspective of model architecture and generation dynamics. Leveraging the multi-layer structure and autoregressive decoding process of LLMs, we decompose hallucination signals into two complementary dimensions: the semantic breadth of token representations within each layer, and the semantic depth of core concepts as they evolve across layers. Based on this insight, we propose \textbf{D$^2$HScore (Dispersion and Drift-based Hallucination Score)}, a training-free and label-free framework that jointly measures: (1) \textbf{Intra-Layer Dispersion}, which quantifies the semantic diversity of token representations within each layer; and (2) \textbf{Inter-Layer Drift}, which tracks the progressive transformation of key token representations across layers. To ensure drift reflects the evolution of meaningful semantics rather than noisy or redundant tokens, we guide token selection using attention signals. By capturing both the horizontal and vertical dynamics of representation during inference, D$^2$HScore provides an interpretable and lightweight proxy for hallucination detection. Extensive experiments across five open-source LLMs and five widely used benchmarks demonstrate that D$^2$HScore consistently outperforms existing training-free baselines.

cs.CL↗

arXiv2025

Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models

Hallucination has emerged as a significant barrier to the effective application of Large Language Models (LLMs). In this work, we introduce a novel Attention-Guided SElf-Reflection (AGSER) approach for zero-shot hallucination detection in LLMs. The AGSER method utilizes attention contributions to categorize the input query into attentive and non-attentive queries. Each query is then processed separately through the LLMs, allowing us to compute consistency scores between the generated responses and the original answer. The difference between the two consistency scores serves as a hallucination estimator. In addition to its efficacy in detecting hallucinations, AGSER notably reduces computational overhead, requiring only three passes through the LLM and utilizing two sets of tokens. We have conducted extensive experiments with four widely-used LLMs across three different hallucination benchmarks, demonstrating that our approach significantly outperforms existing methods in zero-shot hallucination detection.

cs.CL↗

arXiv2025

Infrastructure-enabled risk assessment of hazardous road conditions on rural roads during inclement weather

Rural roadways often expose Commercial Motor Vehicle (CMV) drivers to hazardous conditions, such as heavy fog, rain, snow, black ice, and flash floods, many of which remain unreported in real time. This lack of timely information, coupled with limited infrastructure in rural areas, significantly increases the risk of crashes. Although various sensing technologies exist to monitor individual hazards like low visibility or surface friction, they rarely assess the combined driving risk posed by multiple simultaneous hazards, nor do they provide actionable recommendations such as safe advisory speeds. To address this critical gap, in this study, we present a roadway hazard risk assessment framework that provides an approach to quantify the probability and severity of crash occurrences due to specific roadway hazards. To evaluate this framework, we presented a case study by constructing a synthetic "year-long" dataset that encompasses every possible pairing of road surface and visibility conditions. Our analysis confirms that the combined ProbabilitySeverity scoring yields a coherent, stepwise risk profile across all hazard scenarios. These results validate the practicality of our risk assessment approach and provide a foundation for deploying graduated safety measures in real-world roadway operations.

cs.CE↗

arXiv2025

Logarithmic light cone, slow entanglement growth, and quantum memory

Effective light cones, characterized by Lieb-Robinson bounds, emerge in nonrelativistic local quantum systems. Here, we present several analytical results derived from logarithmic light cones (LLCs). Possible origins of LLCs include the one-dimensional (1D) disordered XXZ model and a phenomenological model of many-body localization (MBL). In the LLC regime, we prove that, for arbitrary spatial dimensions and any initial pure state, entanglement growth is upper-bounded by logarithmic time with an additional subleading \emph{double-logarithmic} correction -- arising from a real asymptotic solution of the \emph{Lambert W} function -- valid up to the asymptotic time limit. In the context of the 1D disordered XXZ model, this result resolves the ambiguity in distinguishing between logarithmic and power-law fits of entanglement growth in numerical studies; we also propose a falsifiable phenomenological functional form for the entanglement growth that agrees with existing numerical results. We show that information scrambling is logarithmically slow in the LLC regime. Furthermore, we demonstrate that the LLC supports long-lived quantum memories -- quantum codes with macroscopic code distance and lifetimes that scale exponentially with system size -- under unitary time evolution. Our analytical results provide benchmarks for future numerical studies of the MBL regime at large time scales.

quant-ph↗

arXiv2025

Mining the Social Fabric: Unveiling Communities for Fake News Detection in Short Videos

Short video platforms have become a major medium for information sharing, but their rapid content generation and algorithmic amplification also enable the widespread dissemination of fake news. Detecting misinformation in short videos is challenging due to their multi-modal nature and the limited context of individual videos. While recent methods focus on analyzing content signals-visual, textual, and audio-they often overlook implicit relationships among videos, uploaders, and events. To address this gap, we propose DugFND (Dual-community graph for fake news detection), a novel method that enhances existing video classifiers by modeling two key community patterns: (1) uploader communities, where uploaders with shared interests or similar content creation patterns group together, and (2) event-driven communities, where videos related to the same or semantically similar public events form localized clusters. We construct a heterogeneous graph connecting uploader, video, and event nodes, and design a time-aware heterogeneous graph attention network to enable effective message passing. A reconstruction-based pretraining phase further improves node representation learning. DugFND can be applied to any pre-trained classifier. Experiments on public datasets show that our method achieves significant performance gains, demonstrating the value of dual-community modeling for fake news detection in short videos.

cs.MM↗

arXiv2025

LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance

While large multi-modal models (LMMs) demonstrate promising capabilities in segmentation and comprehension, they still struggle with two limitations: inaccurate segmentation and hallucinated comprehension. These challenges stem primarily from constraints in weak visual comprehension and a lack of fine-grained perception. To alleviate these limitations, we propose LIRA, a framework that capitalizes on the complementary relationship between visual comprehension and segmentation via two key components: (1) Semantic-Enhanced Feature Extractor (SEFE) improves object attribute inference by fusing semantic and pixel-level features, leading to more accurate segmentation; (2) Interleaved Local Visual Coupling (ILVC) autoregressively generates local descriptions after extracting local features based on segmentation masks, offering fine-grained supervision to mitigate hallucinations. Furthermore, we find that the precision of object segmentation is positively correlated with the latent related semantics of the token. To quantify this relationship and the model's potential semantic inferring ability, we introduce the Attributes Evaluation (AttrEval) dataset. Our experiments show that LIRA achieves state-of-the-art performance in both segmentation and comprehension tasks. Code will be available at https://github.com/echo840/LIRA.

cs.CV↗

arXiv2025

Decoding Polyphenol-Protein Interactions with Deep Learning: From Molecular Mechanisms to Food Applications

Polyphenols and proteins are essential biomolecules that influence food functionality and, by extension, human health. Their interactions -- hereafter referred to as PhPIs (polyphenol-protein interactions) -- affect key processes such as nutrient bioavailability, antioxidant activity, and therapeutic efficacy. However, these interactions remain challenging due to the structural diversity of polyphenols and the dynamic nature of protein binding. Traditional experimental techniques like nuclear magnetic resonance (NMR) and mass spectrometry (MS), along with computational tools such as molecular docking and molecular dynamics (MD), have offered important insights but face constraints in scalability, throughput, and reproducibility. This review explores how deep learning (DL) is reshaping the study of PhPIs by enabling efficient prediction of binding sites, interaction affinities, and MD using high-dimensional bio- and chem-informatics data. While DL enhances prediction accuracy and reduces experimental redundancy, its effectiveness remains limited by data availability, quality, and representativeness, particularly in the context of natural products. We critically assess current DL frameworks for PhPIs analysis and outline future directions, including multimodal data integration, improved model generalizability, and development of domain-specific benchmark datasets. This synthesis offers guidance for researchers aiming to apply DL in unraveling structure-function relationships of polyphenols, accelerating discovery in nutritional science and therapeutic development.

q-bio.BM↗

arXiv2025

PRIME: Phase Reversed Interleaved Multi-Echo acquisition enables highly accelerated distortion-free diffusion MRI

Purpose: To develop and evaluate a new pulse sequence for highly accelerated distortion-free diffusion MRI (dMRI) by inserting additional echoes without prolonging TR, when generalized slice dithered enhanced resolution (gSlider) radiofrequency encoding is used for volumetric acquisition. Methods: A phase-reversed interleaved multi-echo acquisition (PRIME) was developed for rapid, high-resolution, and distortion-free dMRI, which includes several echoes where the first echo is for target diffusion-weighted imaging (DWI) acquisition with high-resolution and additional echoes are acquired with either lower resolution for 1) high-fidelity field map estimation, 2) phase navigation for shot-to-shot phase correction, 3) motion navigation across diffusion directions, or with high resolution to enable 4) high fidelity diffusion relaxometry acquisitions. The sequence was evaluated on in vivo data acquired from healthy volunteers on clinical and Connectome 2.0 scanners. Results: In vivo experiments demonstrated that 1) high in-plane acceleration (Rin-plane of 5-fold with 2D partial Fourier) was achieved using the high-fidelity field maps estimated from the second echo, which was made at a lower resolution/acceleration to increase its SNR while matching the effective echo spacing of the first readout, 2) high-resolution diffusion relaxometry parameters were estimated from triple-echo PRIME data using a white matter model of multi-TE spherical mean technique (MTE-SMT), and 3) high-fidelity mesoscale DWI at 490 um isotropic resolution was obtained in vivo by capitalizing on the high-performance gradients of the Connectome 2.0 scanner. Conclusion: The proposed PRIME sequence enabled highly accelerated, high-resolution, and distortion-free dMRI using additional echoes without prolonging scan time when gSlider encoding is utilized.

physics.med-ph↗

arXiv2025

PIPA: Preference Alignment as Prior-Informed Statistical Estimation

Offline preference alignment for language models such as Direct Preference Optimization (DPO) is favored for its effectiveness and simplicity, eliminating the need for costly reinforcement learning. Various offline algorithms have been developed for different data settings, yet they lack a unified understanding. In this study, we introduce Pior-Informed Preference Alignment (PIPA), a unified, RL-free probabilistic framework that formulates language model preference alignment as a Maximum Likelihood Estimation (MLE) problem with prior constraints. This method effectively accommodates both paired and unpaired data, as well as answer and step-level annotations. We illustrate that DPO and KTO are special cases with different prior constraints within our framework. By integrating different types of prior information, we developed two variations of PIPA: PIPA-M and PIPA-N. Both algorithms demonstrate a $3\sim10\%$ performance enhancement on the GSM8K and MATH benchmarks across all configurations, achieving these gains without additional training or computational costs compared to existing algorithms.

cs.LG↗

arXiv2025

Multishot Dual Polarity GRAPPA: Robust Nyquist Ghost Correction for multishot EPI

Purpose: This work aims to develop a robust Nyquist ghost correction method for multishot echo-planar imaging (EPI). The method helps correct challenging Nyquist ghosts, particularly on scanners with high-performance gradients or ultra-high fields. Methods: A method for multishot EPI ghost correction, called multishot dual-polarity GRAPPA (msDPG), is developed by extending the DPG concept to multishot readouts. msDPG employs tailored DPG kernels to address high-order phase differences between two EPI readout polarities, which cannot be fully addressed using linear phase correction (LPC). Advanced regularizers can be readily employed with the proposed msDPG for physiologic inter-shot phase variation correction during reconstruction. Additionally, a calibration refinement method is proposed to improve the quality of the DPG calibration data and enhance reconstruction performance. Results: Phantom and in vivo experiments on scanners with high-performance gradients and ultra-high fields demonstrated that msDPG achieved superior ghost correction performance than LPC, reducing the ghost-to-signal ratio (GSR) by over 50%. Compared to conventional DPG, msDPG provided images with lower noise amplification, particularly for acquisitions with large in-plane acceleration. Consequently, high-fidelity, submillimeter diffusion images were obtained using msDPG with regularized reconstruction. Conclusion: The proposed msDPG provides a robust Nyquist ghost correction method for multishot EPI, enabling submillimeter imaging with improved fidelity.

physics.med-ph↗

arXiv2025

Mapping ground-based coronagraphic images to Helioprojective-Cartesian coordinate system by image registration

A few ground-based solar coronagraphs have been installed in western China for observing the low-layer corona in recent years. However, determining the Helioprojective Coordinates for the coronagraphic data with high precision is an important but challenging step for further research with other multi-wavelength data. In this paper, we propose an automatic coronal image registration method that combines local statistical correlation and feature point matching to achieve accurate registration between ground-based coronal green-line images and space-based 211 Å images. Then, the accurate field of view information of the coronal green-line images can be derived, allowing the images to be mapped to the Helioprojective Cartesian Coordinates with an accuracy of no less than 0.1''. This method has been extensively validated using 100 days of coronal data spanning an 11-year period, demonstrating its broad applicability to ground-based coronagraphs equipped with green-line observations. It significantly enhances the scientific value of ground-based coronal data, enabling comprehensive studies of coronal transient activities and facilitating the joint analysis of data from multiple instruments. Additionally, it holds potential for future applications in improving the pointing accuracy of coronagraphs.

astro-ph.SR↗

arXiv2025

An Efficient Iterative Decoupling Method for Thermo-Poroelasticity Based on a Four-Field Formulation

This paper studies the thermo-poroelasticity model. By introducing an intermediate variable, we transform the original three-field model into a four-field model. Building upon this four-field model, we present both a coupled finite element method and a decoupled iterative finite element method. We prove the stability and optimal convergence of the coupled finite element method. Furthermore, we establish the convergence of the decoupled iterative method. This paper focuses primarily on analyzing the iterative decoupled algorithm. It demonstrates that the algorithm's convergence does not require any additional assumptions about physical parameters or stabilization parameters. Numerical results are provided to demonstrate the effectiveness and theoretical validity of these new methods.

math.NA↗