arXiv subjects

Yuntao Zou

Publications and source records attributed to Yuntao Zou.

7 recordsLinked to original sources

arXiv2026

FinBoardBench: Benchmarking Dynamic Wealth Management and Strategic Financial Reasoning of LLMs via Board Game Simulations

Recently, large language models (LLMs) have achieved superior performance in static financial reasoning and simple dynamic trading tasks. However, existing static financial benchmarks are insufficient to assess the dynamic wealth management and financial decision-making capabilities of LLMs in real-world environments. To bridge this gap, we present FinBoardBench, an evaluation suite based on three classic financial board games: Cashflow, Acquire, and Monopoly. FinBoardBench assesses a comprehensive set of financial skills, including personal cash flow management with debt balancing, corporate investment and acquisition forecasting, and competitive trade negotiations with asset auctions. Our experiments with 9 advanced LLMs reveal that while exhibiting basic long-term planning and investment logic, they fail to effectively leverage complex interactions for profit, and their strong static reasoning performance does not transform into successful dynamic decision-making. Notably, they tend to prioritize immediate asset acquisition over maintaining sufficient liquidity, making them vulnerable to financial crises triggered by random events. We hope that FinBoardBench can provide a valuable reference for more intelligent LLM-based decision-making systems in the future.

cs.CL↗

arXiv2026

Can Large Language Models Resolve Semantic Discrepancy in Self-Destructive Subcultures? Evidence from Jirai Kei

Self-destructive behaviors are linked to complex psychological states and can be challenging to diagnose. These behaviors may be even harder to identify within subcultural groups due to their unique expressions. As large language models (LLMs) being deployed across various fields, some researchers have begun exploring their application for detecting self-destructive behaviors. Motivated by this, we investigate self-destructive behavior detection within subcultures using current LLM-based methods. However, these methods have two main challenges: (1) Knowledge Lag: Subcultural slang evolves rapidly, faster than LLMs' training cycles; and (2) Semantic Misalignment: it is challenging to grasp the specific and nuanced expressions unique to subcultures. To address these issues, we propose Subcultural Alignment Solver (SAS), a multi-agent framework that incorporates automatic retrieval and subculture alignment, significantly boosting the performance of LLMs in detecting self-destructive behavior. Our experimental results show that SAS outperforms the current advanced multi-agent framework OWL. Notably, it competes well with fine-tuned LLMs. We hope that SAS will advance the field of self-destructive behavior detection in subcultural contexts and serve as a valuable resource for future researchers.

cs.CL↗

arXiv2026

What Factors Affect LLMs and RLLMs in Financial Question Answering?

Recently, large language models (LLMs) and reasoning large language models (RLLMs) have gained considerable attention from many researchers. RLLMs enhance the reasoning capabilities of LLMs through Long Chain-of-Thought (Long CoT) processes, significantly improving the performance of LLMs in addressing complex problems. However, there are few works that systematically explore what methods can fully unlock the performance of LLMs and RLLMs within the financial domain. To investigate the impact of various methods on LLMs and RLLMs, we utilize five LLMs and four RLLMs to assess the effects of prompting methods, agentic frameworks, and multilingual alignment methods on financial question-answering tasks. Our research findings indicate: (1) Current prompting methods and agent frameworks enhance the performance of LLMs in financial question answering by simulating Long CoT; (2) RLLMs possess inherent Long CoT capabilities, which limits the effectiveness of conventional methods in further enhancing their performance; (3) Current advanced multilingual alignment methods primarily improve the multilingual performance of LLMs by extending the reasoning length, which yields minimal benefits for RLLMs. Additionally, we discuss strategies for enhancing the performance of LLMs and RLLMs in financial question answering, which may serve as a inspiration for future improvements. We hope that this study can serve as an important reference for LLMs and RLLMs in the field of financial question answering.

cs.CL↗

arXiv2025

LinkTo-Anime: A 2D Animation Optical Flow Dataset from 3D Model Rendering

Existing optical flow datasets focus primarily on real-world simulation or synthetic human motion, but few are tailored to Celluloid(cel) anime character motion: a domain with unique visual and motion characteristics. To bridge this gap and facilitate research in optical flow estimation and downstream tasks such as anime video generation and line drawing colorization, we introduce LinkTo-Anime, the first high-quality dataset specifically designed for cel anime character motion generated with 3D model rendering. LinkTo-Anime provides rich annotations including forward and backward optical flow, occlusion masks, and Mixamo Skeleton. The dataset comprises 395 video sequences, totally 24,230 training frames, 720 validation frames, and 4,320 test frames. Furthermore, a comprehensive benchmark is constructed with various optical flow estimation methods to analyze the shortcomings and limitations across multiple datasets.

cs.CV↗

arXiv2025

Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion

Generative models are widely used in visual content creation. However, current text-to-image models often face challenges in practical applications-such as textile pattern design and meme generation-due to the presence of unwanted elements that are difficult to separate with existing methods. Meanwhile, subject-reference generation has emerged as a key research trend, highlighting the need for techniques that can produce clean, high-quality subject images while effectively removing extraneous components. To address this challenge, we introduce a framework for reliable subject-centric image generation. In this work, we propose an entropy-based feature-weighted fusion method to merge the informative cross-attention features obtained from each sampling step of the pretrained text-to-image model FLUX, enabling a precise mask prediction and subject-centric generation. Additionally, we have developed an agent framework based on Large Language Models (LLMs) that translates users' casual inputs into more descriptive prompts, leading to highly detailed image generation. Simultaneously, the agents extract primary elements of prompts to guide the entropy-based feature fusion, ensuring focused primary element generation without extraneous components. Experimental results and user studies demonstrate our methods generates high-quality subject-centric images, outperform existing methods or other possible pipelines, highlighting the effectiveness of our approach.

cs.CV↗

arXiv2023

IH-ViT: Vision Transformer-based Integrated Circuit Appear-ance Defect Detection

For the problems of low recognition rate and slow recognition speed of traditional detection methods in IC appearance defect detection, we propose an IC appearance defect detection algo-rithm IH-ViT. Our proposed model takes advantage of the respective strengths of CNN and ViT to acquire image features from both local and global aspects, and finally fuses the two features for decision making to determine the class of defects, thus obtaining better accuracy of IC defect recognition. To address the problem that IC appearance defects are mainly reflected in the dif-ferences in details, which are difficult to identify by traditional algorithms, we improved the tra-ditional ViT by performing an additional convolution operation inside the batch. For the problem of information imbalance of samples due to diverse sources of data sets, we adopt a dual-channel image segmentation technique to further improve the accuracy of IC appearance defects. Finally, after testing, our proposed hybrid IH-ViT model achieved 72.51% accuracy, which is 2.8% and 6.06% higher than ResNet50 and ViT models alone. The proposed algorithm can quickly and accurately detect the defect status of IC appearance and effectively improve the productivity of IC packaging and testing companies.

cs.CV↗

arXiv2020

Estimation of Stability Regions of Droop Control Slopes for MMC-based MTDC Systems

This paper proposes a computational method to efficiently and quickly estimate stability regions of droop control slopes for modular multilevel converter (MMC)-based multiterminal dc (MTDC) systems. The proposed method is based on a general small-signal model consisting of a dc grid with arbitrary topology and MMCs with dq controllers. The general small-signal model developed by a systematic way can be used for small-disturbance stability analysis. To verify the developed small-signal model, a comparison between the developed model calculated in MATLAB and the detailed switching model simulated in PSCAD/EMTDC is conducted, which demonstrates the accuracy of the developed small-signal model. Based on the eigenvalues sensitivity and the Taylor Series of eigenvalues, a set of inequality constraints are derived and used to efficiently estimate the stability regions of all coupled slopes of the droop characteristics. It is helpful for efficiently designing and adjusting the droop controller parameters for the MMC-MTDC systems. The effectiveness of the proposed method is demonstrated by the several examinations including the supremum test and the stability region sketch on accuracy and feasibility.

eess.SY↗