arXiv subjects

Yifan Jiang

Publications and source records attributed to Yifan Jiang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Sensing for Reliable UAV Communication: Robust Trajectory and Resource Optimization in Low-Altitude Networks

In low-altitude wireless networks, sensing-aided communication has emerged as a promising integrated sensing and communication (ISAC) paradigm for unmanned aerial vehicle (UAV) tracking and communication. This paper investigates reliable sensing-aided communication for multiple cellular-connected UAVs under mobility uncertainties. Specifically, we maximize the minimum outage capacity among UAVs by jointly optimizing their real-time predicted positions, as well as the base station (BS) transmit power and bandwidth allocations. To address the non-convex and intractable maximum tolerable outage probability (OP) constraints, two robust optimization schemes are proposed based on a continuous confidence ellipse (CE) and discretized inverse-whitened sectors (IWSs), respectively. For the CE-based scheme, an efficient algorithm is proposed to optimize the predicted UAV positions individually via block successive convex approximation, followed by convex resource allocation. For the IWS-based scheme, an IWS-based OP approximation is proposed to facilitate the robust optimization, based on which a low-complexity IWS selection method is proposed to decouple the optimization variables. Then, a similar sequential optimization algorithm is proposed based on the projected gradient descent approach. The two algorithms are further unified into a common trajectory-resource optimization framework, revealing a low-complexity structure for robust UAV trajectory and resource management. Simulation results validate the effectiveness of our proposed OP approximation, demonstrate the significant outage capacity improvement of the proposed robust optimization schemes over benchmark schemes, and illustrate the superiority of the IWS-based scheme over the CE-based scheme.

eess.SP↗

arXiv2026

Deconfounding via Profiled Transfer Learning

Unmeasured confounders are a major source of bias in regression-based effect estimation and causal inference. In this paper, we propose a new profiled transfer learning framework, ProTrans, to address confounding effects in the target dataset, when additional source datasets with similar confounding structures are available. We introduce the concept of profiled residuals to characterize the shared confounding patterns between source and target datasets. By incorporating these profiled residuals into the target debiasing step, we effectively mitigate the latent confounding effects. We also propose a source selection strategy to enhance the robustness of ProTrans to noninformative sources. As a byproduct, ProTrans can also be used to estimate treatment effects in the presence of potential confounders, without the use of auxiliary features such as instrumental or proxy variables, which are often challenging to select in practice. Theoretically, we prove that the resulting estimated model shift from the sources to the target is confounding-free without imposing specific assumptions on the true confounding structure, and that the target parameter estimation achieves the minimax optimal rate under mild conditions. Simulated and real-world experiments validate the effectiveness of ProTrans and support the theoretical findings.

stat.ME↗

arXiv2026

Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes

Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation. To fill this void, we introduce Pix2Fact, a visual question-answering benchmark designed to assess expert-level visual perception and knowledge search. Pix2Fact comprises 1,000 high-resolution (4K+) images spanning eight scenarios. Its questions and answers are meticulously crafted by PhD-holding annotators from top global universities across diverse disciplines. Each question requires detailed visual grounding and the integration of external knowledge. Evaluating ten state-of-the-art VLMs, including proprietary models such as Gemini-3.1-Pro and GPT-5.4, we find that Pix2Fact poses a formidable challenge: the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools. Our analysis attributes this low accuracy to three factors, frequent visual grounding errors even with visual ground truth, shallow search harnessing, and VLM's inability to retrieve long-tail, unstructured local information. This striking gap exposes the limitations of current models in assisting humans with real-world scenarios that demand overwhelming visual comprehension. We believe Pix2Fact will serve as a critical benchmark to drive the next generation of language-vision agents that seamlessly integrate fine-grained perception with robust knowledge search.

cs.CV↗

arXiv2026

saCI: An R Package for Stochastic Approximation Confidence Intervals for Correlation Coefficients

This paper presents saCI, an R package that implements the stochastic approximation method for constructing nonparametric confidence intervals for Pearson's correlation coefficient. The package is based on the algorithm proposed by Garthwaite (1996) and further developed by Xiong & Xu (2016). The implementation provides both the stochastic approximation (SA) method and the bootstrap BCa method for comparison, along with an interactive Shiny application for exploratory analysis. The package has been successfully published on CRAN, demonstrating its compliance with R package standards and reproducibility.

stat.ME↗

arXiv2026

Miller-Index-Based Latent Crystallographic Fracture Plane Reasoning and generation with Vision-Language Models

We study whether multimodal large language models (MLLMs) can leverage crystallographic plane indices (Miller indices) as a structured latent representation for reasoning about fracture geometry. We formulate Miller indices $z = (h,k,l)$ as a latent variable governing idealized planar fracture and evaluate two complementary capabilities: (i) latent inference, where the model maps visual observations to plane hypotheses under physically valid conditions, and (ii) latent applicability assessment, where the model determines whether such a representation is meaningful for a given fracture image. Through extensive experiments spanning synthetic data, controlled 2D--3D geometric pairs, and real-world fracture images across multiple material classes -- including ceramics, glass, metals, and concrete -- we show that MLLMs can reliably perform latent inference in idealized settings and, critically, can reject the latent representation when the underlying physics does not support it. As an exploratory extension, we further examine AI-generated fracture sequences and observe qualitatively plausible brittle-fracture progression behaviors, suggesting that multimodal generative models may encode partial implicit physical priors related to material failure dynamics. These results suggest that MLLMs can act as physics-aware reasoning systems conditioned on structured latent priors, provided that the domain of validity is explicitly modeled.

cs.LG↗

arXiv2026

LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning

Video captioning models convert frames into visual tokens and generate descriptions with large language models (LLMs). Since encoding all frames is prohibitively expensive, uniform sampling is the default choice, but it enforces equal temporal coverage while ignoring the uneven events distribution. This motivates a Learnable Frame Selector (LFS) that selects temporally diverse and event-relevant frames. LFS explicitly models temporal importance to balance temporal diversity and event relevance, and employs a stratified strategy to ensure temporal coverage while avoiding clustering. Crucially, LFS leverages caption feedback from frozen video-LLMs to learn frame selection that directly optimizes downstream caption quality. Additionally, we identify the gap between existing benchmark and human's cognition. Thus, we introduce ICH-CC built from carefully designed questions by annotators that reflect human-consistent understanding of video. Experiments indicate that LFS consistently improves detailed video captioning across two representative community benchmarks and ICH-CC, achieving up to 2.0% gains on VDC and over 4% gains on ICH-CC. Moreover, we observe that enhanced captions with LFS leads to improved performance on video question answering. Overall, LFS provides an effective and easy-to-integrate solution for detailed video captioning.

cs.CV↗

arXiv2026

VIDEOP2R: Video Understanding from Perception to Reasoning

Reinforcement fine-tuning (RFT), a two-stage framework consisting of supervised fine-tuning (SFT) and reinforcement learning (RL) has shown promising results on improving reasoning ability of large language models (LLMs). Yet extending RFT to large video language models (LVLMs) remains challenging. We propose VideoP2R, a novel process-aware video RFT framework that enhances video reasoning by modeling perception and reasoning as distinct processes. In the SFT stage, we develop a three-step pipeline to generate VideoP2R-CoT-162K, a high-quality, process-aware chain-of-thought (CoT) dataset for perception and reasoning. In the RL stage, we introduce a novel process-aware group relative policy optimization (PA-GRPO) algorithm that supplies separate rewards for perception and reasoning. Extensive experiments show that VideoP2R achieves state-of-the-art (SotA) performance on six out of seven video reasoning and understanding benchmarks. Ablation studies further confirm the effectiveness of our process-aware modeling and PA-GRPO and demonstrate that model's perception output is information-sufficient for downstream reasoning. Our project page is available at https://videop2r.github.io/videop2r/.

cs.CV↗

arXiv2026

Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in various perception and reasoning tasks. Despite this success, ensuring their reliability in practical deployment necessitates robust confidence estimation. Prior works have predominantly focused on text-only LLMs, often relying on computationally expensive self-consistency sampling. In this paper, we extend this to multimodal settings and conduct a comprehensive evaluation of MLLMs' response confidence estimation. Our analysis reveals a significant instinct-reflection misalignment: the model's implicit token-level support frequently diverges from its verbal self-assessment confidence. To address this misalignment, we propose a monotone confidence fusion framework to merge dual-channel signals and cross-channel consistency to estimate correctness. Subsequently, an order-preserving mean alignment step is applied to correct global bias, which improves calibration while preserving the risk-coverage trade-off for selective prediction. Experiments on diverse open-source and closed-source MLLMs show that our method consistently yields more reliable confidence estimates and improves both calibration and failure prediction. Code will be available at https://github.com/Yunkaidang/Instinct-vs.-Reflection.

cs.CV↗

arXiv2026

CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address this issue using single-layer Vision Transformer (ViT) features and static pruning strategies. However, such fixed configurations are often brittle under diverse instructions. To overcome these limitations, we propose CLASP, a plug-and-play token reduction framework based on class-adaptive layer fusion and dual-stage pruning. Specifically, CLASP first constructs category-specific visual representations through multi-layer vision feature fusion. It then performs dual-stage pruning, allocating the token budget between attention-salient pivot tokens for relevance and redundancy-aware completion tokens for coverage. Through class-adaptive pruning, CLASP enables prompt-conditioned feature fusion and budget allocation, allowing aggressive yet robust visual token reduction. Extensive experiments demonstrate that CLASP consistently outperforms existing methods across a wide range of benchmarks, pruning ratios, and MLLM architectures. Code will be available at https://github.com/Yunkaidang/CLASP.

cs.CV↗

arXiv2026

Evolution of effective magnetic exchange interaction under spin dilution in SrIr$_{1-x}$Sn$_x$O$_3$

Resonant inelastic X-ray scattering measurements reveal robust magnetic excitations in the perovskite iridates SrIr$_{1-x}$Sn$_x$O$_3$. We analyzed the dispersions of the magnetic excitation with spin-dilution ratio $x$ = 0, 0.03, 0.06, 0.1, and 0.2, crossing from semi-metal to spin-diluted while antiferromagnetically ordered insulators. The extracted effective magnetic exchange interactions decrease continuously upon increasing spin dilution, and their evolution follows a simple spin-dilution scaling law. These results not only verify the strong electron-correlation nature of the metallic parent SrIrO$_3$, but also reveal the entanglement of the charge and spin dynamics in this system.

cond-mat.str-el↗

arXiv2026

Suppression of the tendency toward antiferromagnetic order in the Dirac semimetal SrIrO$_3$

The entangled charge and spin dynamics in strongly electron correlated system has been a fruitful playground for exploring new physical phenomena. Here with resonant inelastic X-ray scattering we studied the spin dynamics of SrIrO$_3$, a half-filled paramagnetic semimetal hosting highly itinerant Dirac Fermions due to its topological band structure. Our results show that its magnetic excitations share much similarity to the ordered compounds upon Sn substitution in exchange strength and AFM instability, while the system maintains spin non-ordered. Further, the non-ordered pristine SrIrO$_3$ hosts even longer lifetime magnetic excitations near the AFM zone center comparing to the Sn substituted ordered compounds, contrary to general expectation. These observations indicate an interesting connection between band topology and electron correlation in SrIrO$_3$.

cond-mat.str-el↗

arXiv2026

Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives

Analogical reasoning is a key driver of human generalization in problem-solving and argumentation. Yet, analogies between narrative structures remain challenging for machines. Cognitive engines for structural mapping are not directly applicable, as they assume pre-extracted entities, whereas LLMs' performance is sensitive to prompt format and the degree of surface similarity between narratives. This gap motivates a key question: What is the impact of enhancing structural mapping with LLM-derived abstractions on their analogical reasoning ability in narratives? To that end, we propose a modular framework named YARN (Yielding Abstractions for Reasoning in Narratives), which uses LLMs to decompose narratives into units, abstract these units, and then passes them to a mapping component that aligns elements across stories to perform analogical reasoning. We define and operationalize four levels of abstraction that capture both the general meaning of units and their roles in the story, grounded in prior work on framing. Our experiments reveal that abstractions consistently improve model performance, resulting in competitive or better performance than end-to-end LLM baselines. Closer error analysis reveals the remaining challenges in abstraction at the right level, in incorporating implicit causality, and an emerging categorization of analogical patterns in narratives. YARN enables systematic variation of experimental settings to analyze component contributions, and to support future work, we make the code for YARN openly available.

cs.CL↗

arXiv2026

Forward Regression via Gram-Schmidt Orthogonalization for Ultra-High Dimensional Linear Models

Forward regression is a classical and effective tool for variable screening in ultra-high dimensional linear models, but its standard projection-based implementation can be computationally costly and numerically unstable when predictors are strongly collinear. Motivated by this limitation, we propose an orthogonalized forward regression procedure, implemented recursively through Gram-Schmidt updates, that ranks predictors according to their unique contributions after removing the effects of variables already selected. This approach preserves the interpretability of forward regression while substantially reducing the cost of repeated projections. We further develop a path-based model size selection rule using statistics computed directly from the forward sequence, thereby avoiding cross-validation and extensive tuning. The resulting method is particularly well suited to settings in which the number of predictors far exceeds the sample size and strong collinearity renders the conventional forward fitting ineffective. Theoretically, we derive the optimal convergence rate for the proposed Gram-Schmidt forward regression, thereby extending existing results for projection-based forward regression, and further show that it enjoys sure screening property and variable selection consistency under suitable conditions. Simulation studies and empirical examples demonstrate that it provides a favorable balance among computational efficiency, numerical stability, screening accuracy, and predictive performance, especially in highly correlated ultra-high dimensional settings.

stat.ME↗

arXiv2026

Observation of a Reconstructed Chern Insulator in Twisted Bilayer MoTe2

Twisted bilayer MoTe2 is a prototypical moire material in which long-wavelength superlattices amplify electron correlations, enabling a wealth of emergent quantum phases. To date, experimental efforts have focused primarily on small twist angles (typically smaller than 4deg ), whereas the larger-angle regime-where moire bands become more dispersive and correlations are reduced-has remained largely unexplored. Here we chart the topological phase space of tMoTe2 at a relatively large twist angle of approximately 4.54deg, accessing a moderately correlated regime with enhanced bandwidth. In contrast to small-angle devices that predominantly host fractional quantum anomalous Hall or spin Hall responses, we uncover multiple Chern-insulating states with C = 1 at moire fillings v = -1, -0.53 and -1/2. Strikingly, at v = -2/3 a magnetic field induces a fractional Chern insulator accompanied by an insulator-metal transition. Our results broaden the topological phase diagram of tMoTe2 and establish large-angle moire superlattices as a versatile platform for engineering robust topological states beyond the strong-correlation limit.

cond-mat.mes-hall↗

arXiv2026

Schrödinger bridge with transport relaxation

Motivated by modern machine learning applications where we only have access to empirical measures constructed from finite samples, we relax the marginal constraints of the classical Schrödinger bridge problem by penalizing the transport cost between the bridge's marginals and the prescribed marginals. We derive a duality formula for this transport-relaxed bridge and demonstrate that it reduces to a finite-dimensional concave optimization problem when the prescribed marginals are discrete and the reference distribution is absolutely continuous. We establish the existence and uniqueness of solutions for both the primal and dual problems. Moreover, as the penalty blows up, we characterize the limiting bridge as the solution to a discrete Schrödinger bridge problem and identify a leading-order logarithmic divergence. Finally, we propose gradient ascent and Sinkhorn-type algorithms to numerically solve the transport-relaxed Schrödinger bridge, establishing a linear convergence rate for both algorithms.

math.PR↗

arXiv2025

FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing

Large vision-language models (VLMs) exhibit strong performance across various tasks. However, these VLMs encounter significant challenges when applied to the remote sensing domain due to the inherent differences between remote sensing images and natural images. Existing remote sensing VLMs often fail to extract fine-grained visual features and suffer from visual forgetting during deep language processing. To address this, we introduce MF-RSVLM, a Multi-Feature Fusion Remote Sensing Vision--Language Model that effectively extracts and fuses visual features for RS understanding. MF-RSVLM learns multi-scale visual representations and combines global context with local details, improving the capture of small and complex structures in RS scenes. A recurrent visual feature injection scheme ensures the language model remains grounded in visual evidence and reduces visual forgetting during generation. Extensive experiments on diverse RS benchmarks show that MF-RSVLM achieves state-of-the-art or highly competitive performance across remote sensing classification, image captioning, and VQA tasks. Our code is publicly available at https://github.com/Yunkaidang/RSVLM.

cs.CV↗

arXiv2025

Quality analysis and evaluation prediction of RAG retrieval based on machine learning algorithms

With the rapid evolution of large language models, retrieval enhanced generation technology has been widely used due to its ability to integrate external knowledge to improve output accuracy. However, the performance of the system is highly dependent on the quality of the retrieval module. If the retrieval results have low relevance to user needs or contain noisy information, it will directly lead to distortion of the generated content. In response to the performance bottleneck of existing models in processing tabular features, this paper proposes an XGBoost machine learning regression model based on feature engineering and particle swarm optimization. Correlation analysis shows that answer_quality is positively correlated with doc_delevance by 0.66, indicating that document relevance has a significant positive effect on answer quality, and improving document relevance may enhance answer quality; The strong negative correlations between semantic similarity, redundancy, and diversity were -0.89 and -0.88, respectively, indicating a tradeoff between semantic similarity, redundancy, and diversity. In other words, as the former two increased, diversity significantly decreased. The experimental results comparing decision trees, AdaBoost, etc. show that the VMD PSO BiLSTM model is superior in all evaluation indicators, with significantly lower MSE, RMSE, MAE, and MAPE compared to the comparison model. The R2 value is higher, indicating that its prediction accuracy, stability, and data interpretation ability are more outstanding. This achievement provides an effective path for optimizing the retrieval quality and improving the generation effect of RAG system, and has important value in promoting the implementation and application of related technologies.

cs.LG↗

arXiv2025

Lung-DDPM+: Efficient Thoracic CT Image Synthesis using Diffusion Probabilistic Model

Generative artificial intelligence (AI) has been playing an important role in various domains. Leveraging its high capability to generate high-fidelity and diverse synthetic data, generative AI is widely applied in diagnostic tasks, such as lung cancer diagnosis using computed tomography (CT). However, existing generative models for lung cancer diagnosis suffer from low efficiency and anatomical imprecision, which limit their clinical applicability. To address these drawbacks, we propose Lung-DDPM+, an improved version of our previous model, Lung-DDPM. This novel approach is a denoising diffusion probabilistic model (DDPM) guided by nodule semantic layouts and accelerated by a pulmonary DPM-solver, enabling the method to focus on lesion areas while achieving a better trade-off between sampling efficiency and quality. Evaluation results on the public LIDC-IDRI dataset suggest that the proposed method achieves 8$\times$ fewer FLOPs (floating point operations per second), 6.8$\times$ lower GPU memory consumption, and 14$\times$ faster sampling compared to Lung-DDPM. Moreover, it maintains comparable sample quality to both Lung-DDPM and other state-of-the-art (SOTA) generative models in two downstream segmentation tasks. We also conducted a Visual Turing Test by an experienced radiologist, showing the advanced quality and fidelity of synthetic samples generated by the proposed method. These experimental results demonstrate that Lung-DDPM+ can effectively generate high-quality thoracic CT images with lung nodules, highlighting its potential for broader applications, such as general tumor synthesis and lesion generation in medical imaging. The code and pretrained models are available at https://github.com/Manem-Lab/Lung-DDPM-PLUS.

cs.CV↗