arXiv subjects

Jingwen Deng

Publications and source records attributed to Jingwen Deng.

6 recordsLinked to original sources

arXiv2026

Linking COPD Prevalence with Income Distribution: A Spatial Heterogeneous Compositional Regression via Geographically Weighted Penalized Approach

Income inequality is a major contributor to health disparities, yet its effects often vary by geography and are commonly represented as compositional distributions (e.g., proportions of households across income brackets). Existing spatial regression methods struggle in this setting: they typically assume smooth spatial variation, cannot accommodate abrupt spatial heterogeneity, and lack principled treatment of compositional covariates. We propose a geographically weighted penalized compositional regression model that addresses these challenges simultaneously. Our method adopts a pairwise fusion penalty that enables detection of both contiguous and noncontiguous regional clusters with shared regression effects, thereby relaxing strong assumptions of spatial smoothness and geographic contiguity. This allows regions with similar underlying socioeconomic structures to be identified even when they are not geographically adjacent. By incorporating nonconvex penalties, such as the minimax concave penalty (MCP), the approach achieves improved estimation accuracy, interpretability, and scalability in high-dimensional spatial settings. We illustrate the method through an analysis linking U.S. income composition to chronic obstructive pulmonary disease (COPD) prevalence, revealing spatially heterogeneous associations that are obscured by conventional models. The proposed framework provides a flexible and robust tool for spatial data analysis involving compositional predictors and region-specific heterogeneity.

stat.ME↗

arXiv2025

DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc scripts and loosely specified workflows, which lack principled abstractions, hinder reproducibility, and offer limited support for model-in-the-loop data generation. To address these challenges, we present DataFlow, a unified and extensible LLM-driven data preparation framework. DataFlow is designed with system-level abstractions that enable modular, reusable, and composable data transformations, and provides a PyTorch-style pipeline construction API for building debuggable and optimizable dataflows. The framework consists of nearly 200 reusable operators and six domain-general pipelines spanning text, mathematical reasoning, code, Text-to-SQL, agentic RAG, and large-scale knowledge extraction. To further improve usability, we introduce DataFlow-Agent, which automatically translates natural-language specifications into executable pipelines via operator synthesis, pipeline planning, and iterative verification. Across six representative use cases, DataFlow consistently improves downstream LLM performance. Our math, code, and text pipelines outperform curated human datasets and specialized synthetic baselines, achieving up to +3\% execution accuracy in Text-to-SQL over SynSQL, +7\% average improvements on code benchmarks, and 1--3 point gains on MATH, GSM8K, and AIME. Moreover, a unified 10K-sample dataset produced by DataFlow enables base models to surpass counterparts trained on 1M Infinity-Instruct data. These results demonstrate that DataFlow provides a practical and high-performance substrate for reliable, reproducible, and scalable LLM data preparation, and establishes a system-level foundation for future data-centric AI development.

cs.LG↗

arXiv2025

FlipVQA: Scaling Multi-modal Instruction Tuning via Textbook-to-Knowledge Synthesis

Textbooks are among the richest repositories of human-verified reasoning knowledge, yet their complex layouts contain multi-column typesetting, cross-page question answer separation, and interleaved figures, make automated extraction of structured QA and VQA pairs extremely challenging. Existing alternatives either synthesize data from scratch, which lacks authentic problem contexts, or rely on costly expert annotation that cannot scale. We propose $\textbf{FlipVQA-Miner}$, an automated pipeline that resolves long-range logical dependencies and cross-page discontinuities in OCR-parsed documents, recovering coherent question--answer--figure associations even when answers reside in separate companion volumes. A subsequent multi-stage curation pipeline transforms these raw extractions into AI-ready supervision signals. Using FlipVQA-Miner, we construct $\textbf{FlipVQA-83K}$, comprising 83K QA and VQA pairs spanning 11 academic disciplines, at a $\textbf{50$\times$}$ cost saving compared to manual annotation while maintaining high structural fidelity ($F_1 > 0.96$). Models fine-tuned on FlipVQA-83K demonstrate significantly improved reasoning ability and cross-domain generalization, establishing a scalable paradigm for human-knowledge-grounded data curation. Our dataset and the complete data generating and curating methods can be found in https://github.com/OpenDCAI/DataFlow-VQA .

cs.AI↗

arXiv2025

Height-Dependent Rotor Noise and Thrust in Urban Air Mobility: An Experimental Study

The present study investigates the aerodynamic and aeroacoustic characteristics of a propeller operating under varying rotational speeds (RPM) and heights ("H" ), with a particular focus on the effects of upstream obstruction modelled as a tall building. Unlike previous studies that primarily examined rotor noise under axial inflow conditions, this work explores how vortex shedding and flow ingestion from different elevations influence rotor performance and noise emissions. Experiments were carried out in an anechoic wind tunnel, where a tall cylinder was positioned above the propeller to replicate real-world obstruction scenarios. Results revealed that lower propeller heights led to increased broadband noise due to intensified turbulence interactions and reduced aerodynamic efficiency, while higher positions improved thrust performance and mitigated noise effects under certain conditions. The findings contribute to understanding noise sources in eVTOL propulsion systems and provide insights for optimizing propeller placement to enhance aerodynamic efficiency and noise reduction in urban environments

physics.flu-dyn↗

arXiv2025

LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning

Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specific heuristics rather than fostering general-purpose thinking strategies. In this work, we propose a "play to learn" framework that fine-tunes LLMs through reinforcement learning on a suite of seven custom logic puzzles, each designed to cultivate distinct reasoning skills such as constraint propagation, spatial consistency, and symbolic deduction. Using a reinforcement learning setup with verifiable rewards, models receive binary feedback based on puzzle correctness, encouraging iterative, hypothesis-driven problem solving. We demonstrate that this training approach significantly improves out-of-distribution performance on a range of mathematical benchmarks, especially for mid-difficulty problems that require multi-step reasoning. Analyses across problem categories and difficulty levels reveal that puzzle training promotes transferable reasoning routines, strengthening algebraic manipulation, geometric inference, and combinatorial logic, while offering limited gains on rote or highly specialized tasks. These findings show that reinforcement learning over logic puzzles reshapes the internal reasoning of LLMs, enabling more robust and compositional generalization without relying on task-specific symbolic tools.

cs.LG↗

arXiv2025

Open-World Skill Discovery from Unsegmented Demonstrations

Learning skills in open-world environments is essential for developing agents capable of handling a variety of tasks by combining basic skills. Online demonstration videos are typically long but unsegmented, making them difficult to segment and label with skill identifiers. Unlike existing methods that rely on sequence sampling or human labeling, we have developed a self-supervised learning-based approach to segment these long videos into a series of semantic-aware and skill-consistent segments. Drawing inspiration from human cognitive event segmentation theory, we introduce Skill Boundary Detection (SBD), an annotation-free temporal video segmentation algorithm. SBD detects skill boundaries in a video by leveraging prediction errors from a pretrained unconditional action-prediction model. This approach is based on the assumption that a significant increase in prediction error indicates a shift in the skill being executed. We evaluated our method in Minecraft, a rich open-world simulator with extensive gameplay videos available online. Our SBD-generated segments improved the average performance of conditioned policies by 63.7% and 52.1% on short-term atomic skill tasks, and their corresponding hierarchical agents by 11.3% and 20.8% on long-horizon tasks. Our method can leverage the diverse YouTube videos to train instruction-following agents. The project page can be found in https://craftjarvis.github.io/SkillDiscovery.

cs.CV↗