Searcharxiv⌕ Search

arXiv subjects

Jianwen Sun

Publications and source records attributed to Jianwen Sun.

At least 37 records · Page 2Linked to original sources
arXiv2025

From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration

Scientific illustrations demand both high information density and post-editability. However, current generative models have two major limitations: Frist, image generation models output rasterized images lacking semantic structure, making it impossible to access, edit, or rearrange independent visual components in the images. Second, code-based generation methods (TikZ or SVG), although providing element-level control, force users into the cumbersome cycle of "writing-compiling-reviewing" and lack the intuitiveness of manipulation. Neither of these two approaches can well meet the needs for efficiency, intuitiveness, and iterative modification in scientific creation. To bridge this gap, we introduce VisPainter, a multi-agent framework for scientific illustration built upon the model context protocol. VisPainter orchestrates three specialized modules-a Manager, a Designer, and a Toolbox-to collaboratively produce diagrams compatible with standard vector graphics software. This modular, role-based design allows each element to be explicitly represented and manipulated, enabling true element-level control and any element can be added and modified later. To systematically evaluate the quality of scientific illustrations, we introduce VisBench, a benchmark with seven-dimensional evaluation metrics. It assesses high-information-density scientific illustrations from four aspects: content, layout, visual perception, and interaction cost. To this end, we conducted extensive ablation experiments to verify the rationality of our architecture and the reliability of our evaluation methods. Finally, we evaluated various vision-language models, presenting fair and credible model rankings along with detailed comparisons of their respective capabilities. Additionally, we isolated and quantified the impacts of role division, step control,and description on the quality of illustrations.

cs.CV↗
arXiv2025

InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

LLMs have shown strong performance on human-centric reasoning tasks. While previous evaluations have explored whether LLMs can infer intentions or detect deception, they often overlook the individualized reasoning styles that influence how people interpret and act in social contexts. Social deduction games (SDGs) provide a natural testbed for evaluating individualized reasoning styles, where different players may adopt diverse but contextually valid reasoning strategies under identical conditions. To address this, we introduce InMind, a cognitively grounded evaluation framework designed to assess whether LLMs can capture and apply personalized reasoning styles in SDGs. InMind enhances structured gameplay data with round-level strategy traces and post-game reflections, collected under both Observer and Participant modes. It supports four cognitively motivated tasks that jointly evaluate both static alignment and dynamic adaptation. As a case study, we apply InMind to the game Avalon, evaluating 11 state-of-the-art LLMs. General-purpose LLMs, even GPT-4o frequently rely on lexical cues, struggling to anchor reflections in temporal gameplay or adapt to evolving strategies. In contrast, reasoning-enhanced LLMs like DeepSeek-R1 exhibit early signs of style-sensitive reasoning. These findings reveal key limitations in current LLMs' capacity for individualized, adaptive reasoning, and position InMind as a step toward cognitively aligned human-AI interaction.

cs.AI↗
arXiv2025

MDK12-Bench: A Comprehensive Evaluation of Multimodal Large Language Models on Multidisciplinary Exams

Multimodal large language models (MLLMs), which integrate language and visual cues for problem-solving, are crucial for advancing artificial general intelligence (AGI). However, current benchmarks for measuring the intelligence of MLLMs suffer from limited scale, narrow coverage, and unstructured knowledge, offering only static and undifferentiated evaluations. To bridge this gap, we introduce MDK12-Bench, a large-scale multidisciplinary benchmark built from real-world K-12 exams spanning six disciplines with 141K instances and 6,225 knowledge points organized in a six-layer taxonomy. Covering five question formats with difficulty and year annotations, it enables comprehensive evaluation to capture the extent to which MLLMs perform over four dimensions: 1) difficulty levels, 2) temporal (cross-year) shifts, 3) contextual shifts, and 4) knowledge-driven reasoning. We propose a novel dynamic evaluation framework that introduces unfamiliar visual, textual, and question form shifts to challenge model generalization while improving benchmark objectivity and longevity by mitigating data contamination. We further evaluate knowledge-point reference-augmented generation (KP-RAG) to examine the role of knowledge in problem-solving. Key findings reveal limitations in current MLLMs in multiple aspects and provide guidance for enhancing model robustness, interpretability, and AI-assisted education.

cs.AI↗
arXiv2025

ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability

Unified multimodal understanding and generation have recently received much attention in the area of vision and language. Existing UniMs are designed to simultaneously learn both multimodal understanding and generation capabilities, demanding substantial computational resources, and often struggle to generate interleaved text-image. We present ARMOR, a resource-efficient and pure autoregressive framework that achieves both understanding and generation by fine-tuning existing multimodal large language models (MLLMs). Specifically, ARMOR extends existing MLLMs from three perspectives: (1) For model architecture, an asymmetric encoder-decoder architecture with a forward-switching mechanism is introduced to unify embedding space integrating textual and visual modalities for enabling natural text-image interleaved generation with minimal computational overhead. (2) For training data, a meticulously curated, high-quality interleaved dataset is collected for fine-tuning MLLMs. (3) For the training algorithm, we propose a ``what or how to generate'' algorithm to empower existing MLLMs with multimodal generation capabilities while preserving their multimodal understanding capabilities, through three progressive training stages based on the collected dataset. Experimental results demonstrate that ARMOR upgrades existing MLLMs to UniMs with promising image generation capabilities, using limited training resources. Our code will be released soon at https://github.com/finyorko/armor.

cs.CV↗
arXiv2025

SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model

Recent years have seen rapid advances in AI-driven image generation. Early diffusion models emphasized perceptual quality, while newer multimodal models like GPT-4o-image integrate high-level reasoning, improving semantic understanding and structural composition. Scientific illustration generation exemplifies this evolution: unlike general image synthesis, it demands accurate interpretation of technical content and transformation of abstract ideas into clear, standardized visuals. This task is significantly more knowledge-intensive and laborious, often requiring hours of manual work and specialized tools. Automating it in a controllable, intelligent manner would provide substantial practical value. Yet, no benchmark currently exists to evaluate AI on this front. To fill this gap, we introduce SridBench, the first benchmark for scientific figure generation. It comprises 1,120 instances curated from leading scientific papers across 13 natural and computer science disciplines, collected via human experts and MLLMs. Each sample is evaluated along six dimensions, including semantic fidelity and structural accuracy. Experimental results reveal that even top-tier models like GPT-4o-image lag behind human performance, with common issues in text/visual clarity and scientific correctness. These findings highlight the need for more advanced reasoning-driven visual generation capabilities.

cs.CV↗
arXiv2025

IA-T2I: Internet-Augmented Text-to-Image Generation

Current text-to-image (T2I) generation models achieve promising results, but they fail on the scenarios where the knowledge implied in the text prompt is uncertain. For example, a T2I model released in February would struggle to generate a suitable poster for a movie premiering in April, because the character designs and styles are uncertain to the model. To solve this problem, we propose an Internet-Augmented text-to-image generation (IA-T2I) framework to compel T2I models clear about such uncertain knowledge by providing them with reference images. Specifically, an active retrieval module is designed to determine whether a reference image is needed based on the given text prompt; a hierarchical image selection module is introduced to find the most suitable image returned by an image search engine to enhance the T2I model; a self-reflection mechanism is presented to continuously evaluate and refine the generated image to ensure faithful alignment with the text prompt. To evaluate the proposed framework's performance, we collect a dataset named Img-Ref-T2I, where text prompts include three types of uncertain knowledge: (1) known but rare. (2) unknown. (3) ambiguous. Moreover, we carefully craft a complex prompt to guide GPT-4o in making preference evaluation, which has been shown to have an evaluation accuracy similar to that of human preference evaluation. Experimental results demonstrate the effectiveness of our framework, outperforming GPT-4o by about 30% in human evaluation.

cs.CV↗
arXiv2025

MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models

Multimodal reasoning, which integrates language and visual cues into problem solving and decision making, is a fundamental aspect of human intelligence and a crucial step toward artificial general intelligence. However, the evaluation of multimodal reasoning capabilities in Multimodal Large Language Models (MLLMs) remains inadequate. Most existing reasoning benchmarks are constrained by limited data size, narrow domain coverage, and unstructured knowledge distribution. To close these gaps, we introduce MDK12-Bench, a multi-disciplinary benchmark assessing the reasoning capabilities of MLLMs via real-world K-12 examinations. Spanning six disciplines (math, physics, chemistry, biology, geography, and information science), our benchmark comprises 140K reasoning instances across diverse difficulty levels from primary school to 12th grade. It features 6,827 instance-level knowledge point annotations based on a well-organized knowledge structure, detailed answer explanations, difficulty labels and cross-year partitions, providing a robust platform for comprehensive evaluation. Additionally, we present a novel dynamic evaluation framework to mitigate data contamination issues by bootstrapping question forms, question types, and image styles during evaluation. Extensive experiment on MDK12-Bench reveals the significant limitation of current MLLMs in multimodal reasoning. The findings on our benchmark provide insights into the development of the next-generation models. Our data and codes are available at https://github.com/LanceZPF/MDK12.

cs.CV↗
arXiv2025

EduPlanner: LLM-Based Multi-Agent Systems for Customized and Intelligent Instructional Design

Large Language Models (LLMs) have significantly advanced smart education in the Artificial General Intelligence (AGI) era. A promising application lies in the automatic generalization of instructional design for curriculum and learning activities, focusing on two key aspects: (1) Customized Generation: generating niche-targeted teaching content based on students' varying learning abilities and states, and (2) Intelligent Optimization: iteratively optimizing content based on feedback from learning effectiveness or test scores. Currently, a single large LLM cannot effectively manage the entire process, posing a challenge for designing intelligent teaching plans. To address these issues, we developed EduPlanner, an LLM-based multi-agent system comprising an evaluator agent, an optimizer agent, and a question analyst, working in adversarial collaboration to generate customized and intelligent instructional design for curriculum and learning activities. Taking mathematics lessons as our example, EduPlanner employs a novel Skill-Tree structure to accurately model the background mathematics knowledge of student groups, personalizing instructional design for curriculum and learning activities according to students' knowledge levels and learning abilities. Additionally, we introduce the CIDDP, an LLM-based five-dimensional evaluation module encompassing clarity, Integrity, Depth, Practicality, and Pertinence, to comprehensively assess mathematics lesson plan quality and bootstrap intelligent optimization. Experiments conducted on the GSM8K and Algebra datasets demonstrate that EduPlanner excels in evaluating and optimizing instructional design for curriculum and learning activities. Ablation studies further validate the significance and effectiveness of each component within the framework. Our code is publicly available at https://github.com/Zc0812/Edu_Planner

cs.AI↗
arXiv2025

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

As multi-modal large language models (MLLMs) frequently exhibit errors when solving scientific problems, evaluating the validity of their reasoning processes is critical for ensuring reliability and uncovering fine-grained model weaknesses. Since human evaluation is laborious and costly, prompting MLLMs as automated process judges has become a common practice. However, the reliability of these model-based judges remains uncertain. To address this, we introduce ProJudgeBench, the first comprehensive benchmark specifically designed for evaluating abilities of MLLM-based process judges. ProJudgeBench comprises 2,400 test cases and 50,118 step-level labels, spanning four scientific disciplines with diverse difficulty levels and multi-modal content. In ProJudgeBench, each step is meticulously annotated by human experts for correctness, error type, and explanation, enabling a systematic evaluation of judges' capabilities to detect, classify and diagnose errors. Evaluation on ProJudgeBench reveals a significant performance gap between open-source and proprietary models. To bridge this gap, we further propose ProJudge-173k, a large-scale instruction-tuning dataset, and a Dynamic Dual-Phase fine-tuning strategy that encourages models to explicitly reason through problem-solving before assessing solutions. Both contributions significantly enhance the process evaluation capabilities of open-source models. All the resources will be released to foster future research of reliable multi-modal process evaluation.

cs.AI↗
arXiv2024

Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates

In recent years, large language models have shown exceptional performance in fulfilling diverse human needs. However, their training data can introduce harmful content, underscoring the necessity for robust value alignment. Mainstream methods, which depend on feedback learning and supervised training, are resource-intensive and may constrain the full potential of the models. Multi-Agent Debate (MAD) offers a more efficient and innovative solution by enabling the generation of reliable answers through agent interactions. To apply MAD to value alignment, we examine the relationship between the helpfulness and harmlessness of debate outcomes and individual responses, and propose a MAD based framework Gradual Vigilance and Interval Communication (GVIC). GVIC allows agents to assess risks with varying levels of vigilance and to exchange diverse information through interval communication. We theoretically prove that GVIC optimizes debate efficiency while reducing communication overhead. Experimental results demonstrate that GVIC consistently outperforms baseline methods across various tasks and datasets, particularly excelling in harmfulness mitigation and fraud prevention. Additionally, GVIC exhibits strong adaptability across different base model sizes, including both unaligned and aligned models, and across various task types.

cs.AI↗
arXiv2024

Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis

Generalizable 3D Gaussian splitting (3DGS) can reconstruct new scenes from sparse-view observations in a feed-forward inference manner, eliminating the need for scene-specific retraining required in conventional 3DGS. However, existing methods rely heavily on epipolar priors, which can be unreliable in complex realworld scenes, particularly in non-overlapping and occluded regions. In this paper, we propose eFreeSplat, an efficient feed-forward 3DGS-based model for generalizable novel view synthesis that operates independently of epipolar line constraints. To enhance multiview feature extraction with 3D perception, we employ a selfsupervised Vision Transformer (ViT) with cross-view completion pre-training on large-scale datasets. Additionally, we introduce an Iterative Cross-view Gaussians Alignment method to ensure consistent depth scales across different views. Our eFreeSplat represents an innovative approach for generalizable novel view synthesis. Different from the existing pure geometry-free methods, eFreeSplat focuses more on achieving epipolar-free feature matching and encoding by providing 3D priors through cross-view pretraining. We evaluate eFreeSplat on wide-baseline novel view synthesis tasks using the RealEstate10K and ACID datasets. Extensive experiments demonstrate that eFreeSplat surpasses state-of-the-art baselines that rely on epipolar priors, achieving superior geometry reconstruction and novel view synthesis quality. Project page: https://tatakai1.github.io/efreesplat/.

cs.CV↗
arXiv2024

Evolvable Psychology Informed Neural Network for Memory Behavior Modeling

Memory behavior modeling is a core issue in cognitive psychology and education. Classical psychological theories typically use memory equations to describe memory behavior, which exhibits insufficient accuracy and controversy, while data-driven memory modeling methods often require large amounts of training data and lack interpretability. Knowledge-informed neural network models have shown excellent performance in fields like physics, but there have been few attempts in the domain of behavior modeling. This paper proposed a psychology theory informed neural networks for memory behavior modeling named PsyINN, where it constructs a framework that combines neural network with differentiating sparse regression, achieving joint optimization. Specifically, to address the controversies and ambiguity of descriptors in memory equations, a descriptor evolution method based on differentiating operators is proposed to achieve precise characterization of descriptors and the evolution of memory theoretical equations. Additionally, a buffering mechanism for the sparse regression and a multi-module alternating iterative optimization method are proposed, effectively mitigating gradient instability and local optima issues. On four large-scale real-world memory behavior datasets, the proposed method surpasses the state-of-the-art methods in prediction accuracy. Ablation study demonstrates the effectiveness of the proposed refinements, and application experiments showcase its potential in inspiring psychological research.

cs.LG↗
arXiv2024

COMET: "Cone of experience" enhanced large multimodal model for mathematical problem generation

The automatic generation of high-quality mathematical problems is practically valuable in many educational scenarios. Large multimodal model provides a novel technical approach for the mathematical problem generation because of its wide success in cross-modal data scenarios. However, the traditional method of separating problem solving from problem generation and the mainstream fine-tuning framework of monotonous data structure with homogeneous training objectives limit the application of large multimodal model in mathematical problem generation. Addressing these challenges, this paper proposes COMET, a "Cone of Experience" enhanced large multimodal model for mathematical problem generation. Firstly, from the perspective of mutual ability promotion and application logic, we unify stem generation and problem solving into mathematical problem generation. Secondly, a three-stage fine-turning framework guided by the "Cone of Experience" is proposed. The framework divides the fine-tuning data into symbolic experience, iconic experience, and direct experience to draw parallels with experiences in the career growth of teachers. Several fine-grained data construction and injection methods are designed in this framework. Finally, we construct a Chinese multimodal mathematical problem dataset to fill the vacancy of Chinese multimodal data in this field. Combined with objective and subjective indicators, experiments on multiple datasets fully verify the effectiveness of the proposed framework and model.

cs.AI↗
arXiv2024

Automated discovery of symbolic laws governing skill acquisition from naturally occurring data

Skill acquisition is a key area of research in cognitive psychology as it encompasses multiple psychological processes. The laws discovered under experimental paradigms are controversial and lack generalizability. This paper aims to unearth the laws of skill learning from large-scale training log data. A two-stage algorithm was developed to tackle the issues of unobservable cognitive states and algorithmic explosion in searching. Initially a deep learning model is employed to determine the learner's cognitive state and assess the feature importance. Subsequently, symbolic regression algorithms are utilized to parse the neural network model into algebraic equations. Experimental results show the algorithm can accurately restore preset laws within a noise range in continuous feedback settings. When applied to Lumosity training data, the method outperforms traditional and recent models in fitness terms. The study reveals two new forms of skill acquisition laws and reaffirms some previous findings.

cs.LG↗
arXiv2023

Software Architecture Recovery with Information Fusion

Understanding the architecture is vital for effectively maintaining and managing large software systems. However, as software systems evolve over time, their architectures inevitably change. To keep up with the change, architects need to track the implementation-level changes and update the architectural documentation accordingly, which is time-consuming and error-prone. Therefore, many automatic architecture recovery techniques have been proposed to ease this process. Despite efforts have been made to improve the accuracy of architecture recovery, existing solutions still suffer from two limitations. First, most of them only use one or two type of information for the recovery, ignoring the potential usefulness of other sources. Second, they tend to use the information in a coarse-grained manner, overlooking important details within it. To address these limitations, we propose SARIF, a fully automated architecture recovery technique, which incorporates three types of comprehensive information, including dependencies, code text and folder structure. SARIF can recover architecture more accurately by thoroughly analyzing the details of each type of information and adaptively fusing them based on their relevance and quality. To evaluate SARIF, we collected six projects with published ground-truth architectures and three open-source projects labeled by our industrial collaborators. We compared SARIF with nine state-of-the-art techniques using three commonly-used architecture similarity metrics and two new metrics. The experimental results show that SARIF is 36.1% more accurate than the best of the previous techniques on average. By providing comprehensive architecture, SARIF can help users understand systems effectively and reduce the manual effort of obtaining ground-truth architectures.

cs.SE↗
arXiv2023

Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation

Video-based scene graph generation (VidSGG) is an approach that aims to represent video content in a dynamic graph by identifying visual entities and their relationships. Due to the inherently biased distribution and missing annotations in the training data, current VidSGG methods have been found to perform poorly on less-represented predicates. In this paper, we propose an explicit solution to address this under-explored issue by supplementing missing predicates that should be appear in the ground-truth annotations. Dubbed Trico, our method seeks to supplement the missing predicates by exploring three complementary spatio-temporal correlations. Guided by these correlations, the missing labels can be effectively supplemented thus achieving an unbiased predicate predictions. We validate the effectiveness of Trico on the most widely used VidSGG datasets, i.e., VidVRD and VidOR. Extensive experiments demonstrate the state-of-the-art performance achieved by Trico, particularly on those tail predicates.

cs.CV↗
arXiv2020

Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning

Adversarial attacks against conventional Deep Learning (DL) systems and algorithms have been widely studied, and various defenses were proposed. However, the possibility and feasibility of such attacks against Deep Reinforcement Learning (DRL) are less explored. As DRL has achieved great success in various complex tasks, designing effective adversarial attacks is an indispensable prerequisite towards building robust DRL algorithms. In this paper, we introduce two novel adversarial attack techniques to \emph{stealthily} and \emph{efficiently} attack the DRL agents. These two techniques enable an adversary to inject adversarial samples in a minimal set of critical moments while causing the most severe damage to the agent. The first technique is the \emph{critical point attack}: the adversary builds a model to predict the future environmental states and agent's actions, assesses the damage of each possible attack strategy, and selects the optimal one. The second technique is the \emph{antagonist attack}: the adversary automatically learns a domain-agnostic model to discover the critical moments of attacking the agent in an episode. Experimental results demonstrate the effectiveness of our techniques. Specifically, to successfully attack the DRL agent, our critical point technique only requires 1 (TORCS) or 2 (Atari Pong and Breakout) steps, and the antagonist technique needs fewer than 5 steps (4 Mujoco tasks), which are significant improvements over state-of-the-art methods.

cs.CR↗