Searcharxiv⌕ Search

arXiv subjects

Xin Xiao

Publications and source records attributed to Xin Xiao.

At least 19 recordsLinked to original sources

Strain Controlled Hydrogen Interstitial Site Preference and Hydride Phase Suppression in Epitaxial Vanadium

Understanding hydrogen behavior in transition metals is crucial for energy storage and sensing technologies. Here we combine density functional theory (DFT) calculations with in-situ electrical measurements to reveal how epitaxial strain governs hydrogen interstitial site selection and phase stability in vanadium. Our calculations demonstrate a robust thermodynamic preference for tetrahedral (T) over octahedral (O) sites, with the energy difference modulated by lattice anisotropy through strain-tunable H 1s-V 3d orbital hybridization. Experimentally, epitaxial V films on MgO(001) exhibit a critical thickness-dependent crossover: 50 nm films show characteristic first-order alpha-beta hydride transitions, while 10 nm films display continuous solid-solution behavior with complete transition suppression. This crossover is governed by the progressive relaxation of epitaxial strain with increasing film thickness: the 10 nm films retain strong coherent strain that flattens the free-energy landscape and suppresses hydride nucleation, whereas the 50 nm films approach the strain-relaxed bulk limit where long-range elastic interactions restore first-order phase behavior. Finite-size truncation of elastic fields and interfacial electronic reconstruction further reinforce this dimensional crossover. Our work establishes a unified framework connecting atomic-scale orbital physics to mesoscopic phase thermodynamics, providing design principles for strain-engineered metal-hydride systems.

cond-mat.mtrl-sci↗

Global Trends and Heterogeneity in Modified Adjusted Net Savings

Modified adjusted net savings is a derived weak sustainability indicator obtained by subtracting education expenditure from adjusted net savings (ANS). Because ANS equals net national savings plus education expenditure minus natural-resource depletion and carbon dioxide damage, MANS isolates the savings and depletion components and is useful when education expenditure would otherwise dominate cross-country comparisons. This study documents the global distribution, long-run trends, and cross-country heterogeneity of MANS excluding particulate emission damage over 1990-2021. The accounting base is the World Bank World Development Indicators series NY.ADJ.SVNX.CD, and MANS is constructed by subtracting education expenditure from this series. We combine global maps, aggregate time series, country-level heatmaps, distributional statistics, and income group comparisons. The results show that global MANS has increased substantially in aggregate, but its evolution as a share of nominal GDP has been more volatile and uneven across countries. Per capita MANS and global MANS totals remain concentrated in high-income and large economies, whereas low-income and lower-middle-income groups display persistently lower and more volatile outcomes. Country rankings are highly persistent, and some populous countries exhibit pronounced fluctuations associated with natural-resource dependence and structural change. The study provides a reproducible descriptive benchmark for monitoring sustainable development and highlights the need to interpret MANS in current US dollars alongside income-group and country-specific contexts. The findings are relevant for macroeconomic policy, natural-capital accounting, and the design of sustainability-oriented investment strategies.

econ.GN↗

Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation

Embodied chain-of-thought (CoT) aims to bridge linguistic reasoning with robotic control, yet its effective form and integration remain underexplored. In this paper, we revisit embodied CoT for robotic control at an unprecedented scale. We curate the largest embodied CoT corpus to date, comprising 978,743 trajectories, 226.3M samples, and 2592.5 hours of data. Through extensive experiments, we show that effective CoT must ground high-level semantic understaning in concrete linguistic action guidance -- such as end-effector movement and image-space trajectories -- whereas high-level reasoning alone yields marginal gains. More importantly, we identify that explicit CoT does not scale reliably as an autoregressive action prefix, suffering from compounding errors during inference. To address these challenges, we propose ERVLA, a vision-language-action (VLA) model that effectively leverages linguistic reasoning in generalizable robot manipulation. ERVLA is trained using a CoT-dropout strategy, allowing the model to leverage rich reasoning traces during training while predicting actions directly without CoT during inference to bypass autoregressive instability. This approach enables reliable scaling with increasing pre-training data. ERVLA achieves state-of-the-art results on LIBERO-Plus with an 86.9\% success rate and reaches 53.2\% on VLABench, showcasing superior performance in out-of-distribution settings. Furthermore, ERVLA outperforms competitive state-of-the-art baselines in real-robot experiments, especially in handling semantic ambiguity and long-horizon tasks. Code, data, and model checkpoints are available on the project website: https://taoshuaiz.github.io/ERVLA/.

cs.RO↗

SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies neglect one or both aspects. They often rely on 2D visual observations or backbones pretrained on static image--text pairs, which leads to high data requirements and limited comprehension of environment dynamics. To address this, we introduce SpatialVAM, the first 3D Video Action Model that simultaneously predict spatial-aware multi-view heatmap videos and RGB videos. Our key insight is that this design naturally injects 3D information into video foundation models while aligning the representation format between video pretraining and action finetuning. Extensive experiments demonstrate that SpatialVAM enables data-efficient, robust, generalizable, and interpretable manipulation. With only ten demonstration trajectories and no additional pretraining, SpatialVAM handles challenging long-horizon and contact-rich tasks, generalizes to out-of-distribution settings, and predicts realistic future videos. Evaluations on Meta-World (22\%$\uparrow$), RoboCasa (15\%$\uparrow$) and real-world robotic platforms (16\%$\uparrow$) show that SpatialVAM consistently outperforms other video action models, vision language action models and 3D-based policies, establishing a new state-of-the-art in data-efficient multi-task manipulation.

cs.RO↗

GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning

Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challenging because EO workflows are constrained by sensing semantics, product dependencies, spatial and temporal compatibility, and parameter requirements. Existing agents often search a broad operation space for each query, while recent self-evolving systems do not fully organize heterogeneous EO trajectories into reusable knowledge across different decision levels. To solve this problem, we present GeoForge, a training-free, self-evolving framework that transforms completed trajectories into a structured nonparametric execution state. GeoForge constrains the operation space according to the sensing context, then retrieves a task-conditioned prior from three complementary memories. Workflow Graph Memory captures global operation order, Action-Level Experiences provide local corrections, and the Adapted Skill Standard Operating Procedure preserves procedural and data constraints. The retrieved prior guides tool execution, while current observations remain the basis of the final answer. After each task, a safety-gated distillation process converts grounded trajectories into reusable execution knowledge for future retrieval. This execution, distillation, and reuse loop improves planning without updating the backbone LLM. Experiments on multiple geospatial benchmarks demonstrate that GeoForge consistently improves both task accuracy and tool-use trajectory quality across diverse LLM backbones, while substantially reducing tool-planning and reasoning errors for most LLMs.

cs.AI↗

Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement

The increasing complexity of modern software systems has made automated code generation a fundamental task in software engineering. However, existing approaches often fail to adequately capture the intricate, multi-level dependencies among code entities, leading to generated code that is logically incomplete or difficult to integrate into real-world systems. To address this limitation, we propose a dependency-aware code generation framework that explicitly models interactions among code entities through a graph-based representation. We decompose dependencies into two complementary components: a quantized matrix that captures strong, explicit relations, and a sparse low-rank factorization that models weaker, implicit interactions. The decomposition is efficiently learned via an alternating optimization procedure. During code generation, the learned dependency structure is incorporated as a constraint, ensuring both semantic coherence and structural consistency of the generated code. Furthermore, we introduce a sparse triplet representation for strong dependencies, significantly improving storage efficiency and computational scalability. Extensive experiments demonstrate that our approach consistently produces code with superior semantic alignment and structural fidelity compared to existing methods.

cs.SE↗

BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding

Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model, enabling lossless acceleration. Recently, diffusion-based speculative decoding further improves parallelism by generating multiple tokens per forward pass via block-level diffusion, achieving state-of-the-art (SOTA) performance. However, existing methods adopt a fixed inference block size and assume a uniform optimal decoding strategy across all inputs. In this paper, we show that this assumption is suboptimal, as the optimal block size varies across samples and plays a critical role in speculative decoding performance. Moreover, these values exhibit a clear local structure, concentrating around the training block size, which reduces the problem to a low-dimensional and structured decision space. Based on these insights, we propose BlockPilot, a sample-adaptive policy that predicts the optimal block size from the prefilling representation. Specifically, we formulate block size selection as a lightweight policy learning problem and propose an instance-adaptive decision mechanism that predicts the optimal block size based on the representation of the prefilling stage. The prediction is performed only once after prefilling, allowing for seamless integration. Extensive experiments demonstrate that our method is plug-and-play, introduces minimal overhead, and consistently improves efficiency, achieving an acceptance length of 5.92 and a 4.20$\times$ speedup on Qwen3-4B under temperature $T=1$.

cs.CL↗

From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation

Curvilinear object segmentation, including vessels and cracks, is challenging due to extreme spatial sparsity and topological fragility, where small local errors can cause severe structural disconnections. Meanwhile, modern segmentation pipelines increasingly rely on strong but hard-to-modify foundation encoders whose heavy downsampling limits fine structural recovery. Motivated by this, we focus on the post-encoder stage and study two recurring and actionable failure modes: a reconstruction bottleneck in high-resolution feature restoration and a decision bottleneck in binarization. We present PEPA, a lightweight Post-Encoder Plug-in Adapter for 2D curvilinear segmentation pipelines with accessible decoder/head features and target, query, or class descriptors. PEPA couples (i) Target-Conditioned Snake Upsampling (TCSU), which uses target-conditioned continuous snake-like sampling to better recover thin and tortuous structures during upsampling, and (ii) Target-Adaptive Differentiable Thresholding (TADT), which predicts target-specific thresholds and optimizes a soft-threshold surrogate with explicit safeguards against trivial bias shifting. Under this post-encoder interface, PEPA can be attached to both prompt-based decoders and conventional dense predictors. Experiments on five medical and industrial benchmarks show that adding PEPA to frozen-encoder baselines yields consistent improvements, with gains in topological connectivity (clDice) typically exceeding those in region overlap (IoU), indicating improved structural continuity. With only $\sim$0.26M additional parameters, PEPA offers a practical post-encoder enhancement for structure-centric segmentation.

cs.CV↗

Do Models See in Line with Human Vision? Probing the Correspondence Between LVLM Representations and EEG Signals

Large Vision Language Models (LVLMs) exhibit strong visual understanding and reasoning abilities. However, whether their internal representations reflect human visual cognition is still under-explored. In this paper, we address this by quantifying LVLM-brain alignment using image-evoked Electroencephalogram (EEG) signals, analyzing the effects of model architecture, scale, and image type. Specifically, by using ridge regression and representational similarity analysis, we compare visual representations from 32 open-source LVLMs with corresponding EEG responses. We observe a structured LVLM-brain correspondence: First, intermediate layers (8-16) show peak alignment with EEG activity in the 100-300 ms window, consistent with hierarchical human visual processing. Secondly, multimodal architectural design contributes 3.4 more to brain alignment than parameter scaling, and models with stronger downstream visual performance exhibit higher EEG similarity. Thirdly, spatiotemporal patterns further align with known cortical visual pathways. These results demonstrate that LVLMs learn human-aligned visual representations and establish neural alignment as a biologically grounded benchmark for evaluating and improving LVLMs. In addition, those results could provide insights that may inform the development of neuro-inspired applications.

cs.HC↗

Do Models Hear Like Us? Probing the Representational Alignment of Audio LLMs and Naturalistic EEG

Audio Large Language Models (Audio LLMs) have demonstrated strong capabilities in integrating speech perception with language understanding. However, whether their internal representations align with human neural dynamics during naturalistic listening remains largely unexplored. In this work, we systematically examine layer-wise representational alignment between 12 open-source Audio LLMs and Electroencephalogram (EEG) signals across 2 datasets. Specifically, we employ 8 similarity metrics, such as Spearman-based Representational Similarity Analysis (RSA), to characterize within-sentence representational geometry. Our analysis reveals 3 key findings: (1) we observe a rank-dependence split, in which model rankings vary substantially across different similarity metrics; (2) we identify spatio-temporal alignment patterns characterized by depth-dependent alignment peaks and a pronounced increase in RSA within the 250-500 ms time window, consistent with N400-related neural dynamics; (3) we find an affective dissociation whereby negative prosody, identified using a proposed Tri-modal Neighborhood Consistency (TNC) criterion, reduces geometric similarity while enhancing covariance-based dependence. These findings provide new neurobiological insights into the representational mechanisms of Audio LLMs.

cs.SD↗

Exploring Similarity between Neural and LLM Trajectories in Language Processing

Understanding the similarity between large language models (LLMs) and human brain activity is crucial for advancing both AI and cognitive neuroscience. In this study, we provide a multilinguistic, large-scale assessment of this similarity by systematically comparing 16 publicly available pretrained LLMs with human brain responses during natural language processing tasks in both English and Chinese. Specifically, we use ridge regression to assess the representational similarity between LLM embeddings and electroencephalography (EEG) signals, and analyze the similarity between the "neural trajectory" and the "LLM latent trajectory." This method captures key dynamic patterns, such as magnitude, angle, uncertainty, and confidence. Our findings highlight both similarities and crucial differences in processing strategies: (1) We show that middle-to-high layers of LLMs are central to semantic integration and correspond to the N400 component observed in EEG; (2) The brain exhibits continuous and iterative processing during reading, whereas LLMs often show discrete, stage-end bursts of activity, which suggests a stark contrast in their real-time semantic processing dynamics. This study could offer new insights into LLMs and neural processing, and also establish a critical framework for future investigations into the alignment between artificial intelligence and biological intelligence.

cs.HC↗

CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation

Multimodal Retrieval-Augmented Generation (MRAG) enables Multimodal Large Language Models (MLLMs) to generate responses with external multimodal evidence, and numerous video-based MRAG benchmarks have been proposed to evaluate model capabilities across retrieval and generation stages. However, existing benchmarks remain limited in modality coverage and format diversity, often focusing on single- or limited-modality tasks, or coarse-grained scene understanding. To address these gaps, we introduce CFVBench, a large-scale, manually verified benchmark constructed from 599 publicly available videos, yielding 5,360 open-ended QA pairs. CFVBench spans high-density formats and domains such as chart-heavy reports, news broadcasts, and software tutorials, requiring models to retrieve and reason over long temporal video spans while maintaining fine-grained multimodal information. Using CFVBench, we systematically evaluate 7 retrieval methods and 14 widely-used MLLMs, revealing a critical bottleneck: current models (even GPT5 or Gemini) struggle to capture transient yet essential fine-grained multimodal details. To mitigate this, we propose Adaptive Visual Refinement (AVR), a simple yet effective framework that adaptively increases frame sampling density and selectively invokes external tools when necessary. Experiments show that AVR consistently enhances fine-grained multimodal comprehension and improves performance across all evaluated MLLMs

cs.CL↗

Machine Learning Powered Feasible Path Framework with Adaptive Sampling for Black-box Optimization

Black-box optimization (BBO) involves functions that are unknown, inexact and/or expensive-to-evaluate. Existing BBO algorithms face several challenges, including high computational cost from extensive evaluations, difficulty in handling complex constraints, lacking theoretical convergence guarantees and/or instability due to large solution quality variation. In this work, a machine learning-powered feasible path optimization framework (MLFP) is proposed for general BBO problems including complex constraints. An adaptive sampling strategy is first proposed to explore optimal regions and pre-filter potentially infeasible points to reduce evaluations. Machine learning algorithms are leveraged to develop surrogates of black-boxes. The feasible path algorithm is employed to accelerate theoretical convergence by updating independent variables rather than all. Computational studies demonstrate MLFP can rapidly and robustly converge around the KKT point, even training surrogates with small datasets. MLFP is superior to the state-of-the-art BBO algorithms, as it stably obtains the same or better solutions with fewer evaluations for benchmark examples.

math.OC↗

Characterizing Community Formation in Response to Extreme Weather Events through Human Mobility Networks

Community formation in socio-spatial human networks is one of the important mechanisms for mitigating hazard impacts of extreme weather events. Research is scarce regarding latent network characteristics shaping community formation in human mobility networks during natural disasters. Here, we examined human mobility networks in Harris County, Texas, in the context of the managed power outage forced by 2021 Winter Storm Uri to detect communities and to evaluate latent characteristics in those communities. We examined three characteristics in the communities formed within human mobility networks: hazard-exposure heterophily, socio-demographic homophily, and social-connectedness strength. The results show that population movements were shaped by socio-demographic homophily, heterophilic hazard exposure, and social connectedness strength. Our results also indicate that a community encompassing more high-impact areas would motivate population movements to areas with weaker social connectedness. Our findings reveal important characteristics shaping community formation in human mobility networks in hazard response. Specific to managed power outages, formed communities are spatially co-located, underscoring a best management practice to avoid prolonged power outages among areas within communities, thus improving hazard exposure heterophily. The findings have implications for power utility operators to account for the characteristics of socio-spatial human networks when determining the patterns of managed power outages.

cs.SI↗

GR-3 Technical Report

We report our recent progress towards building generalist robot policies, the development of GR-3. GR-3 is a large-scale vision-language-action (VLA) model. It showcases exceptional capabilities in generalizing to novel objects, environments, and instructions involving abstract concepts. Furthermore, it can be efficiently fine-tuned with minimal human trajectory data, enabling rapid and cost-effective adaptation to new settings. GR-3 also excels in handling long-horizon and dexterous tasks, including those requiring bi-manual manipulation and mobile movement, showcasing robust and reliable performance. These capabilities are achieved through a multi-faceted training recipe that includes co-training with web-scale vision-language data, efficient fine-tuning from human trajectory data collected via VR devices, and effective imitation learning with robot trajectory data. In addition, we introduce ByteMini, a versatile bi-manual mobile robot designed with exceptional flexibility and reliability, capable of accomplishing a wide range of tasks when integrated with GR-3. Through extensive real-world experiments, we show GR-3 surpasses the state-of-the-art baseline method, $π_0$, on a wide variety of challenging tasks. We hope GR-3 can serve as a step towards building generalist robots capable of assisting humans in daily life.

cs.RO↗

Coarse-to-fine crack cue for robust crack detection

Crack detection is an important task in computer vision. Despite impressive in-dataset performance, deep learning-based methods still struggle in generalizing to unseen domains. The thin structure property of cracks is usually overlooked by previous methods. In this work, we introduce CrackCue, a novel method for robust crack detection based on coarse-to-fine crack cue generation. The core concept lies on leveraging the thin structure property to generate a robust crack cue, guiding the crack detection. Specifically, we first employ a simple max-pooling and upsampling operation on the crack image. This results in a coarse crack-free background, based on which a fine crack-free background can be obtained via a reconstruction network. The difference between the original image and fine crack-free background provides a fine crack cue. This fine cue embeds robust crack prior information which is unaffected by complex backgrounds, shadow, and varied lighting. As a plug-and-play method, we incorporate the proposed CrackCue into three advanced crack detection networks. Extensive experimental results demonstrate that the proposed CrackCue significantly improves the generalization ability and robustness of the baseline methods. The source code will be publicly available.

cs.CV↗

Feasible Path SQP Algorithm for Simulation-based Optimization Surrogated with Differentiable Machine Learning Models

With the development of artificial intelligence, simulation-based optimization problems, which present a significant challenge in the process systems engineering community, are increasingly being addressed with the surrogate-based framework. In this work, we propose a deterministic algorithm framework based on feasible path sequential quadratic programming for optimizing differentiable machine learning models embedded problems. The proposed framework effectively addresses two key challenges: (i) achieving the computation of first- and second-order derivatives of machine learning models' outputs with respect to inputs; and (ii) by introducing the feasible path method, the massive intermediate variables resulting from the algebraic formulation of machine learning models eliminated. Surrogate models for six test functions and two process simulations were established and optimized. All six test functions were successfully optimized to the global optima, demonstrating the framework's effectiveness. The optimization time for all cases did not exceed 2s, highlighting the efficiency of the algorithm.

math.OC↗

Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment

Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being simple and effective, this method results in sub-optimal cross-modal alignment by over-emphasizing the text tokens that are less correlated with or even contradictory with the input images. In this paper, we advocate for assigning distinct contributions for each text token based on its visual correlation. Specifically, we present by contrasting image inputs, the difference in prediction logits on each text token provides strong guidance of visual correlation. We therefore introduce Contrastive ALignment (CAL), a simple yet effective re-weighting strategy that prioritizes training visually correlated tokens. Our experimental results demonstrate that CAL consistently improves different types of VLMs across different resolutions and model sizes on various benchmark datasets. Importantly, our method incurs minimal additional computational overhead, rendering it highly efficient compared to alternative data scaling strategies. Codes are available at https://github.com/foundation-multimodal-models/CAL.

cs.CV↗