arXiv subjects

Zhaoyang Wang

Publications and source records attributed to Zhaoyang Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

EyeSim-VQA: A Free-Energy-Guided Eye Simulation Framework for Video Quality Assessment

Free-energy-guided self-repair mechanisms have shown promising results in image quality assessment (IQA), but remain under-explored in video quality assessment (VQA), where temporal dynamics and model constraints pose unique challenges. Unlike static images, video content exhibits richer spatiotemporal complexity, making perceptual restoration more difficult. Moreover, VQA systems often rely on pre-trained backbones, which limits the direct integration of enhancement modules without affecting model stability. To address these issues, we propose EyeSimVQA, a novel VQA framework that incorporates free-energy-based self-repair. It adopts a dual-branch architecture, with an aesthetic branch for global perceptual evaluation and a technical branch for fine-grained structural and semantic analysis. Each branch integrates specialized enhancement modules tailored to distinct visual inputs-resized full-frame images and patch-based fragments-to simulate adaptive repair behaviors. We also explore a principled strategy for incorporating high-level visual features without disrupting the original backbone. In addition, we design a biologically inspired prediction head that models sweeping gaze dynamics to better fuse global and local representations for quality prediction. Experiments on five public VQA benchmarks demonstrate that EyeSimVQA achieves competitive or superior performance compared to state-of-the-art methods, while offering improved interpretability through its biologically grounded design.

cs.CV↗

arXiv2025

Second-Order Linear Relaxation Schemes for Time-Fractional Phase-Field Models

This work uses a linear relaxation method to develop efficient numerical schemes for the time-fractional Allen-Cahn and Cahn-Hilliard equations. The L1+-CN formula is used to discretize the fractional derivative, and an auxiliary variable is introduced to approximate the nonlinear term by solving an algebraic equation rather than a differential equation as in the invariant energy quadratization (IEQ) and scalar auxiliary variable (SAV) approaches. The proposed semi-discrete scheme is linear, second-order accurate in time, and the inconsistency between the auxiliary and the original variables does not deteriorate over time. Furthermore, we prove that the scheme is unconditionally energy stable. Numerical results demonstrate the effectiveness of the proposed scheme.

math.NA↗

arXiv2025

TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries. These systems, however, remain susceptible to corpus poisoning attacks, which can severely impair the performance of LLMs. To address this challenge, we propose TrustRAG, a robust framework that systematically filters malicious and irrelevant content before it is retrieved for generation. Our approach employs a two-stage defense mechanism. The first stage implements a cluster filtering strategy to detect potential attack patterns. The second stage employs a self-assessment process that harnesses the internal capabilities of LLMs to detect malicious documents and resolve inconsistencies. TrustRAG provides a plug-and-play, training-free module that integrates seamlessly with any open- or closed-source language model. Extensive experiments demonstrate that TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance.

cs.CL↗

arXiv2025

Anyprefer: An Agentic Framework for Preference Data Synthesis

High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding approach, where the target model generates and annotates its own preference data, but this can lead to inaccuracies since the reward model shares weights with the target model, thereby amplifying inherent biases. To address these issues, we propose Anyprefer, a framework designed to synthesize high-quality preference data for aligning the target model. Anyprefer frames the data synthesis process as a cooperative two-player Markov Game, where the target model and the judge model collaborate together. Here, a series of external tools are introduced to assist the judge model in accurately rewarding the target model's responses, mitigating biases in the rewarding process. In addition, a feedback mechanism is introduced to optimize prompts for both models, enhancing collaboration and improving data quality. The synthesized data is compiled into a new preference dataset, Anyprefer-V1, consisting of 58K high-quality preference pairs. Extensive experiments show that Anyprefer significantly improves model alignment performance across four main applications, covering 21 datasets, achieving average improvements of 18.55% in five natural language generation datasets, 3.66% in nine vision-language understanding datasets, 30.05% in three medical image analysis datasets, and 16.00% in four visuo-motor control tasks.

cs.LG↗

arXiv2025

CREAM: Consistency Regularized Self-Rewarding Language Models

Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same LLM to act as both the policy model (which generates responses) and the reward model (which scores and ranks those responses). The ranked responses are then used as preference pairs to train the LLM via direct alignment technologies (e.g. DPO). However, it is noteworthy that throughout this process, there is no guarantee of accuracy in the rewarding and ranking, which is critical for ensuring accurate rewards and high-quality preference data. Empirical results from relatively small LLMs (e.g., 7B parameters) also indicate that improvements from self-rewarding may diminish after several iterations in certain situations, which we hypothesize is due to accumulated bias in the reward system. This bias can lead to unreliable preference data for training the LLM. To address this issue, we first formulate and analyze the generalized iterative preference fine-tuning framework for self-rewarding language model. We then introduce the regularization to this generalized framework to mitigate the overconfident preference labeling in the self-rewarding process. Based on this theoretical insight, we propose a Consistency Regularized sElf-rewarding lAnguage Model (CREAM) that leverages the consistency of rewards across different iterations to regularize the self-rewarding training, helping the model to learn from more reliable preference data. With this explicit regularization, our empirical results demonstrate the superiority of CREAM in improving both reward consistency and alignment performance. The code is publicly available at https://github.com/Raibows/CREAM.

cs.LG↗

arXiv2025

Synergistic Weak-Strong Collaboration by Aligning Preferences

Current Large Language Models (LLMs) excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge. Fine-tuning large models for every niche application is often infeasible due to black-box constraints and high computational overhead. To address this, we propose a collaborative framework that pairs a specialized weak model with a general strong model. The weak model, tailored to specific domains, produces initial drafts and background information, while the strong model leverages its advanced reasoning to refine these drafts, extending LLMs' capabilities to critical yet specialized tasks. To optimize this collaboration, we introduce a collaborative feedback to fine-tunes the weak model, which quantifies the influence of the weak model's contributions in the collaboration procedure and establishes preference pairs to guide preference tuning of the weak model. We validate our framework through experiments on three domains. We find that the collaboration significantly outperforms each model alone by leveraging complementary strengths. Moreover, aligning the weak model with the collaborative preference further enhances overall performance.

cs.AI↗

arXiv2025

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

Interleaved multimodal comprehension and generation, enabling models to produce and interpret both images and text in arbitrary sequences, have become a pivotal area in multimodal learning. Despite significant advancements, the evaluation of this capability remains insufficient. Existing benchmarks suffer from limitations in data scale, scope, and evaluation depth, while current evaluation metrics are often costly or biased, lacking in reliability for practical applications. To address these challenges, we introduce MMIE, a large-scale knowledge-intensive benchmark for evaluating interleaved multimodal comprehension and generation in Large Vision-Language Models (LVLMs). MMIE comprises 20K meticulously curated multimodal queries, spanning 3 categories, 12 fields, and 102 subfields, including mathematics, coding, physics, literature, health, and arts. It supports both interleaved inputs and outputs, offering a mix of multiple-choice and open-ended question formats to evaluate diverse competencies. Moreover, we propose a reliable automated evaluation metric, leveraging a scoring model fine-tuned with human-annotated data and systematic evaluation criteria, aimed at reducing bias and improving evaluation accuracy. Extensive experiments demonstrate the effectiveness of our benchmark and metrics in providing a comprehensive evaluation of interleaved LVLMs. Specifically, we evaluate eight LVLMs, revealing that even the best models show significant room for improvement, with most achieving only moderate results. We believe MMIE will drive further advancements in the development of interleaved LVLMs. We publicly release our benchmark and code in https://mmie-bench.github.io/.

cs.CV↗

arXiv2025

A thermodynamically consistent phase-field model for mass transport with interfacial reaction and deformation

In this paper, a thermodynamically consistent phase-field model is proposed to describe the mass transport and reaction processes of multiple species in a fluid. A key feature of this model is that reactions between different species occur only at the interface, and may induce deformation of the interface. For the governing equations derived based on the energy variational method, we propose a structure-preserving numerical scheme that satisfies the mass conservation and energy dissipation laws at the discrete level. Furthermore, we carry out a rigorous error analysis of the time-discrete scheme for a simplified case. A series of numerical experiments are conducted to validate the effectiveness of the model as well as the accuracy and stability of the scheme. In particular, we simulate microvessels with straight and bifurcated structures to illustrate the risk of microaneurysm formation.

math.NA↗

arXiv2025

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement

Large vision-language models (LVLMs) have achieved impressive results in visual question-answering and reasoning tasks through vision instruction tuning on specific datasets. However, there remains significant room for improvement in aligning visual and language modalities. Existing methods often depend on external models or data, leading to uncontrollable and unstable alignment results. In this paper, we propose SIMA, a self-improvement framework that enhances visual and language modality alignment without external dependencies. SIMA leverages existing vision instruction tuning datasets to self-generate responses, incorporating an in-context self-critic mechanism that constructs preference pairs for tuning. Crucially, our approach allows LVLMs to act as critics by designing effective critic prompts, eliminating the need for additional fine-tuning with external instruction data. We introduce three novel visual metrics within the self-critic process to guide judgment, significantly improving the accuracy of self-critic. Through extensive experiments across 14 hallucination and comprehensive benchmarks, we demonstrate that SIMA significantly improves LVLM's performance and outperforms previous approaches, achieving superior modality alignment.

cs.CV↗

arXiv2025

MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation

Recent advancements in video generation have significantly improved the ability to synthesize videos from text instructions. However, existing models still struggle with key challenges such as instruction misalignment, content hallucination, safety concerns, and bias. Addressing these limitations, we introduce MJ-BENCH-VIDEO, a large-scale video preference benchmark designed to evaluate video generation across five critical aspects: Alignment, Safety, Fineness, Coherence & Consistency, and Bias & Fairness. This benchmark incorporates 28 fine-grained criteria to provide a comprehensive evaluation of video preference. Building upon this dataset, we propose MJ-VIDEO, a Mixture-of-Experts (MoE)-based video reward model designed to deliver fine-grained reward. MJ-VIDEO can dynamically select relevant experts to accurately judge the preference based on the input text-video pair. This architecture enables more precise and adaptable preference judgments. Through extensive benchmarking on MJ-BENCH-VIDEO, we analyze the limitations of existing video reward models and demonstrate the superior performance of MJ-VIDEO in video preference assessment, achieving 17.58% and 15.87% improvements in overall and fine-grained preference judgments, respectively. Additionally, introducing MJ-VIDEO for preference tuning in video generation enhances the alignment performance. All our code, data, and models are available at https://aiming-lab.github.io/MJ-VIDEO.github.io/.

cs.CV↗

arXiv2025

Verifiable Format Control for Large Language Model Generations

Recent Large Language Models (LLMs) have demonstrated satisfying general instruction following ability. However, small LLMs with about 7B parameters still struggle fine-grained format following (e.g., JSON format), which seriously hinder the advancements of their applications. Most existing methods focus on benchmarking general instruction following while overlook how to improve the specific format following ability for small LLMs. Besides, these methods often rely on evaluations based on advanced LLMs (e.g., GPT-4), which can introduce the intrinsic bias of LLMs and be costly due to the API calls. In this paper, we first curate a fully verifiable format following dataset VFF. In contrast to existing works often adopting external LLMs for instruction-following validations, every sample of VFF can be easily validated with a Python function. Further, we propose to leverage this verifiable feature to synthesize massive data for progressively training small LLMs, in order to improve their format following abilities. Experimental results highlight the prevalent limitations in the format following capabilities of 7B level open-source LLMs and demonstrate the effectiveness of our method in enhancing this essential ability.

cs.CL↗

arXiv2024

Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment

Existing free-energy guided No-Reference Image Quality Assessment (NR-IQA) methods still suffer from finding a balance between learning feature information at the pixel level of the image and capturing high-level feature information and the efficient utilization of the obtained high-level feature information remains a challenge. As a novel class of state-of-the-art (SOTA) generative model, the diffusion model exhibits the capability to model intricate relationships, enabling a comprehensive understanding of images and possessing a better learning of both high-level and low-level visual features. In view of these, we pioneer the exploration of the diffusion model into the domain of NR-IQA. Firstly, we devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images, incorporating nonlinear features obtained during the denoising process of the diffusion model, as high-level visual information. Secondly, two visual evaluation branches are designed to comprehensively analyze the obtained high-level feature information. These include the visual compensation guidance branch, grounded in the transformer architecture and noise embedding strategy, and the visual difference analysis branch, built on the ResNet architecture and the residual transposed attention block. Extensive experiments are conducted on seven public NR-IQA datasets, and the results demonstrate that the proposed model outperforms SOTA methods for NR-IQA.

cs.CV↗

arXiv2024

CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models

Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to comprehensively evaluate the Trustworthiness of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness. We publicly release our benchmark and code in https://cares-ai.github.io/.

cs.LG↗

arXiv2024

Homogenization principle and numerical analysis for fractional stochastic differential equations with different scales

This work is concerned with fractional stochastic differential equations with different scales. We establish the existence and uniqueness of solutions for Caputo fractional stochastic differential systems under the non-Lipschitz condition. Based on the idea of temporal homogenization, we prove that the homogenization principle (averaging principle) holds in the sense of mean square ($L^2$ norm) convergence under a novel homogenization assumption. Furthermore, an Euler-Maruyama scheme for the non-autonomous system is constructed and its numerical error is analyzed. Finally, two numerical examples are presented to verify the theoretical results. Different from the existing literature, we demonstrate the computational advantages of the homogenized autonomous system from a numerical perspective.

math.NA↗

arXiv2024

Impurity-level induced broadband photoelectric response in wide-band semiconductor SrSnO3

Broadband spectrum detectors exhibit great promise in fields such as multispectral imaging and optical communications. Despite significant progress, challenges like materials instability, complex manufacturing process and high costs still hinder further application. Here we present a method that achieves broadband spectral detect by impurity-level in SrSnO3. We report over 200 mA/W photo-responsivity at 275 nm (ultraviolet C solar-bind) and 367 nm (ultraviolet A) and ~ 1 mA/W photo-responsivity at 532 nm and 700 nm (visible) with a voltage bias of 5V. Further transport and photoluminescence results indicate that the broadband response comes from the impurity levels and mutual interactions. Additionally, the photodetector demonstrates excellent robustness and stability under repeated tests and prolonged exposure in air. These findings show the potential of SSO photodetectors and propose a method to achieve broadband spectrum detection, creating new possibility for the development of single-phase, low-cost, simple structure and high-efficiency photodetectors.

physics.app-ph↗

arXiv2024

Photonic Landau levels in a high-dimensional frequency-degenerate cavity

Topological orders emerge in both microscopic quantum dynamics and macroscopic materials as a fundamental principle to characterize intricate properties in nature with vital significance, for instance, the Landau levels of electron systems in magnetic field. Whilst, recent advances of synthetic photonic systems enable generalized concepts of Landau levels across fermionic and bosonic systems, extending the modern physical frontier. However, the controls of Landau levels of photons were only confined in complex artificial metamaterials or multifolded cavities. Here, we exploit advanced structured light laser technology and propose the theory of high-dimensional frequency-degeneracy, which enables photonic Landau level control in a linear open laser cavity with simple displacement tuning of intracavity elements. This work not only create novel structured light with new topological effects but also provides broad prospects for Bose-analogue quantum Hall effects and topological physics.

physics.optics↗

arXiv2024

Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network

Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling complex relations and learning high and low-level visual features. The direct application of diffusion models to HSI SR is hampered by challenges such as difficulties in model convergence and protracted inference time. In this work, we introduce a novel Group-Autoencoder (GAE) framework that synergistically combines with the diffusion model to construct a highly effective HSI SR model (DMGASR). Our proposed GAE framework encodes high-dimensional HSI data into low-dimensional latent space where the diffusion model works, thereby alleviating the difficulty of training the diffusion model while maintaining band correlation and considerably reducing inference time. Experimental results on both natural and remote sensing hyperspectral datasets demonstrate that the proposed method is superior to other state-of-the-art methods both visually and metrically.

cs.CV↗

arXiv2023

Dynamically tunable electromagnetically induced transparency-like metamaterial structure based on polarization sensitivity

In this paper, we propose a plasmon-induced transparency (PIT) metamaterial structure composed of Ag nanomaterials with polarization sensitivity. The metamaterial model consists of three bright modes with different resonant frequencies. The optical properties of the structure are further investigated using finite difference time domain (FDTD) method. The results show that the conversion between single-band PIT and dual-band PIT effects can be achieved by changing the polarization degree of the incident light, the number of transparent windows can be changed from one to two, and the process is accompanied by the conversion of bright and dark modes and the change of the resonance wavelength of the transmission peak. In addition, When the light is polarized in the Y-direction, the two transparency windows have different refractive index sensitivities, with FOM values of 5.94/RIU and 5.65/RIU, respectively.

physics.optics↗