arXiv subjects

Minghui Xu

Publications and source records attributed to Minghui Xu.

At least 19 recordsLinked to original sources

arXiv2026

Geometry-aware Latent Autoregressive Generative Model for PDEs in Complex Domains

Solving multiphysics partial differential equations (PDEs) remains a major challenge in scientific computing, especially for highly complex $\mu$m-scale tortuous geometries critical to energy and chemical engineering. We address this challenge by proposing a Geometry-aware Latent Autoregressive generative Model for PDEs (GeoLAMP) for solving physics within highly irregular and tortuous structures. GeoLAMP introduces a dual-encoder architecture on graph representations to jointly capture global topology and fine-scale geometric features, enabling an effective transition from real-space fields to compact latent representations. In the latent space, we propose a causal self-attention transformer with flow matching to model temporal dynamics, allowing stable and scalable block-wise autoregressive prediction. A flexible decoder reconstructs high-resolution physical fields on arbitrary points. We establish three multiphysics benchmark datasets in complex geometries, covering reactive flow, heat convection, and elasticity. GeoLAMP consistently achieves the most stable autoregression performance on these datasets, maintaining low errors throughout the entire rollout horizon. Our results provide a systematic study of geometry-aware learning for PDEs in $\mu$m-scale complex geometries and offer new insights into block-wise time marching of latent autoregressive PDE modeling via a flow matching framework.

cs.LG↗

arXiv2026

Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning

Current large language models (LLMs) increasingly benefit from external tool integration, especially for tasks requiring reliable computation and verification. Motivated by this, we study calculator tool calling for improving mathematical reasoning on the Countdown task. We first analyze reasoning failures and find that calculation errors account for a substantial portion of incorrect responses. We then construct supervised fine-tuning datasets to teach the model useful tool-use patterns and how to interpret returned outputs. Building on this tool-formatted policy, we apply several on-policy reinforcement learning methods, including RLOO, RLOO++, GRPO, and DAPO, using automatically verifiable final-answer rewards. To enable a more reliable evaluation, we construct a fresh 1,024-problem held-out Countdown benchmark with no exact overlap with the training data. Our results show that calculator tool integration consistently improves both SFT and RL baselines, yielding roughly 10 percentage-point gains across pass@k. Among the RL methods, Tool-DAPO achieves the strongest performance, improving pass@1 from 35.8% for Tool-SFT to 66.0%. Further analysis shows that RL encourages more effective tool use even when only final-answer rewards are provided. These findings suggest that tool integration reduces arithmetic and verification errors, while RL increases the probability of correct reasoning traces.

cs.AI↗

arXiv2026

CIDER: Continual Interactive Distillation for Embodied Reinforcement Learning

Human-in-the-loop real-world reinforcement learning enables rapid acquisition of effective robotic manipulation policies for individual tasks, often within tens of minutes. Yet it remains unclear how to extend this paradigm to continual learning, where a single policy must acquire new skills without losing previously learned behaviors. Existing real-world continual learning methods do not explicitly constrain prior behaviors, leading to severe catastrophic forgetting. We introduce Continual Interactive Distillation for Embodied Reinforcement Learning (CIDER), a continual reinforcement learning framework that freezes the accumulated historical policy as a teacher before learning each new task and interleaves task learning with distillation-based retention. We further introduce gradient routing to separate the gradients used for acquiring new tasks from those used for preserving prior behaviors. We evaluate our method with a single shared actor on six real-world household and industrial manipulation tasks. Interactive Distillation maintains high measured success on previously learned tasks across our six-task real-robot sequence while acquiring each new task in 10 to 20 minutes, whereas every baseline forgets at least one previous task. Additional ablations reveal the key design choices that govern the tradeoff between stability and plasticity in real-world continual reinforcement learning.

cs.RO↗

arXiv2026

OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents

Large language model agents are becoming operational interfaces to files, memories, registries, and external tools. This deployment shift creates a new skill revocation problem: after a skill is removed from an explicit registry, an agent may still reconstruct it from residual carriers such as archives, transcripts, schemas, or memory entries. We study this problem as operational skill unlearning, where the goal is not parameter-level forgetting, but preventing a deployed agent from rebuilding a revoked skill through primitive tools. We introduce OBLIVION, a controlled benchmark and defense harness for revoked-skill resurrection. OBLIVION models each episode as a source-to-sink workflow, applies Cross-Surface Coherent Erasure to reduce residual carriers, and uses frozen workflow remediation near dangerous sinks. On the locked 88 attack episodes, the no-defense arm reaches formal attack success rate 1.0. OBLIVION reduces the rate to 0.114 and impact-weighted exposure to 0.115 while keeping locked utility at 1.0 and benign block rate at 0. In a separate skill-attack-derived sandbox, OBLIVION reduces attack success from 1.0 to 0.2 and impact-weighted exposure from 1.0 to 0.213 while preserving all utility controls. These results support workflow-level evaluation beyond checking explicit skill entries.

cs.AI↗

arXiv2026

Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks

Large language models (LLMs) are safety-aligned before deployment to reduce harmful content generation. Yet neuron-level pruning attacks show that refusal can depend on a small set of removable units: disabling them can remove safety behavior while leaving much of the model usable. To address this problem, we introduce Mask2Shield (M2S), a masked-forward alignment method that trains a model under this functional pruning. The masked student must recover a safe refusal through the remaining computation, while a frozen, unmasked teacher supplies complete benign answers to limit capability drift. Across ten model configurations, M2S reduces successful recomputed pruning attacks from 80--279 to 1--44 out of 313 prompts while generally preserving four capability benchmarks. We also evaluate M2S with TwinBreak, which uses a different neuron-selection rule and iterative pruning procedure. Together, these results show that M2S makes targeted pruning less effective by reducing reliance on a small, removable safety-neuron set.

cs.CR↗

arXiv2026

Digital measurement of droplet flame diameter in microgravity combustion images using Segment Anything Model 2 with automatic prompt selection

Flame diameter is a key measurable parameter in microgravity droplet combustion, but its extraction from self-illuminated frames remains difficult because soot tails, blurred luminous boundaries, chamber reflections, and droplet drift introduce substantial measurement bias and operator dependence. This work presents an AI-enabled digital measurement workflow for automated flame diameter from combustion images. The workflow integrates automatic prompt-point generation into Segment Anything Model 2, employing Random Sample Consensus (RANSAC)-based circle fitting. The automatic prompt strategy removes subjective manual point selection, while the video memory mechanism maintains temporal consistency for drifting droplets, and the RANSAC fitting rejects soot-tail pixels as geometric outliers. The method is validated by 19,537 flame images of n-heptane, n-decane, and n-octane droplets with varying initial diameters. Compared with manual-reference measurements, the proposed workflow achieves a mean relative agreement of 96.9%, a mean absolute percentage error of 3.1%, and substantially outperforms conventional Hough circle detection, which performed worse under the same evaluation conditions. The results also show that the measurement accuracy improves with increasing droplet size. The proposed workflow has a combined standard uncertainty of 8.54% and achieves approximately a 229-fold improvement in efficiency over manual measurement. These results demonstrate that the proposed SAM2-based workflow provides a reproducible, fully automated, and metrologically characterized digital measurement system for extracting flame diameter from challenging combustion images. The approach supports high-throughput combustion diagnostics and illustrates that AI-based segmentation can be integrated into quantitative measurement workflows for digitalized image-based metrology.

cs.CV↗

arXiv2026

Experimental and model-assisted analysis of lamella thinning and breakup in diesel-surrogate fuel-droplet wall impingement under Leidenfrost conditions

Hot-wall fuel-droplet impingement affects liquid redistribution, secondary droplet formation, and droplet evaporation in diesel-relevant spray-wall systems. This study investigates the spreading and breakup of single n-hexadecane droplets, used as a single-component diesel surrogate, on a heated stainless-steel wall at 300-500 {\deg}C over a Weber number (We) range of 5.77-208.61. High-speed backlit images were recorded during experiments and used to classify deposition, rebound, ejection, fragmentation, and splashing regimes, and to measure spreading-factor histories. The measured spreading histories were compared with a lamella-rim model to evaluate its predictive capability before droplet breakup and to infer the lamella state at experimentally observed breakup instants. The 300 {\deg}C cases did not enter the Leidenfrost regime under the present impact conditions and therefore serve as a non-Leidenfrost reference, deviating from the model predictions. For Leidenfrost cases at 350-500 {\deg}C, the model captures the pre-breakup spreading trajectory, including higher-We cases that later undergo breakup. Wall temperature has a limited influence on the early spreading stage but more strongly affects later breakup timing after lamella thinning, especially in the intermediate-We regime. At high We, breakup becomes increasingly inertia-dominated. Model-inferred lamella thicknesses evaluated at experimentally observed breakup instants are mainly concentrated between 0.010 and 0.017 of the initial droplet diameter. These results suggest that model-inferred lamella thickness can complement conventional Weber-number and temperature-based regime maps by providing local-state information for breakup timing in hot-wall fuel-droplet impingement models.

physics.flu-dyn↗

arXiv2026

Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair

Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipelines usually attack these costs separately. Pruning reduces the network, but most pruning methods still rely on a long post-pruning retraining stage to recover a many-step sampler. Step distillation reduces the number of denoising steps, but it usually assumes a student that can already follow the teacher well enough to receive useful distillation gradients. This paper asks whether post-pruning retraining can be replaced by step distillation. We find that the direct replacement fails: after pruning an EDM2-XS teacher, starting SiDA from the pruned checkpoint produces unusable samples. We introduce a short teacher-alignment repair stage as a bridge between pruning and step distillation. The bridge matches the pruned generator to the teacher on noisy real-image latents, then hands the repaired checkpoint to one-step distillation. On ImageNet-512, the original EDM2-XS baseline uses 124.713M parameters and 63 network evaluations, reaching an FID of 3.53. With a suitable distillation objective, our 20% pruned one-step generator uses 98.826M parameters and one network evaluation, reaching an FID of 3.12. With 30% pruning, the model uses 88.029M parameters and one network evaluation, with an FID of 4.26.

cs.CV↗

arXiv2026

Bad company corrupts good morals: Understanding and Measuring Narrative-Induced Moral Reasoning Degradation in LLMs

Large language models are deployed in long-context, emotionally interactive environments like digital humans, AI companions, educational assistants, and counseling systems. Unlike jailbreak attacks with explicit adversarial prompts, these systems interact with emotionally charged narratives involving bullying, betrayal, loneliness, social hostility, and institutional unfairness. This raises an important question: can prolonged narrative exposure reshape the reasoning and alignment stability of LLMs? We present the first systematic study of narrative-induced alignment degradation in LLMs. We design BreakingBad, a three-stage framework that measures how negative narrative immersion affects moral reasoning, behaviors, and deployment risks. It combines ethical decision evaluation, behavioral probing, and digital-human interaction analysis. Our experiments reveal three findings. First, negative narrative exposure degrades moral accuracy across multiple LLMs, with average drops of 12%-31%, especially in ambiguous scenarios and those involving vulnerable individuals. Second, the degradation is structured: different narratives induce distinct shifts, and first-person narratives produce stronger effects than third-person. Third, these shifts propagate into real deployments. Across counseling, education, medical, and financial/legal scenarios, narrative-conditioned models increasingly normalize hopelessness, cynicism, emotional detachment, and ethically questionable reasoning while remaining superficially policy-compliant. More broadly, our findings suggest alignment robustness is not static but a dynamically conditioned state shaped by long-term semantic environments and interaction history. These results reveal a new class of alignment risk that existing safety defenses largely fail to capture.

cs.CY↗

arXiv2026

"What Happens Locally, Leaks Globally": Detecting Privacy Leakage Risks in MCP Servers

The Model Context Protocol (MCP) has rapidly become the de facto standard for connecting large language models (LLMs) to external resources, but it also introduces a class of privacy risks that existing tools are ill-equipped to detect. Unlike conventional exfiltration bugs, leakage in MCP servers is largely protocol-induced: credentials, API keys, and Personally Identifiable Information (PII) cross the local/LLM boundary simply by being returned, logged, or raised inside a tool handler, with no explicit outbound request in the source code. We present MCPPrivacyDetector, a context-aware cross-language static analysis framework that detects such leakage in multilingual MCP servers. MCPPrivacyDetector lifts heterogeneous code implemented across different programming language (e.g., Python) into a unified program representation, applies context-aware semantic filtering to isolate genuinely sensitive values and protocol-specific implicit sinks (e.g., @mcp.tool handlers), and performs taint analysis to enumerate feasible flows. Applied to 10,655 real-world MCP servers, MCPPrivacyDetector finds leakage rates above 10%. Case studies confirm concrete exposures including leaked Bearer tokens, propagated API keys, and plaintext authentication credentials, arguing for systematic, protocol-aware safeguards in the emerging LLM agent toolchain.

cs.CR↗

arXiv2026

A Measurement Study of Cryptographic Misuse in Embodied AI Mobile Applications

Embodied AI (EAI) mobile applications are evolving from auxiliary user interfaces into active control-path components, directly linking mobile-side cryptographic security to cyber-physical trust. Despite this shift, existing security research predominantly focuses on embodied AI devices and cloud infrastructures, leaving the mobile control layer largely unexplored as a critical attack surface. To bridge this gap, we present the first large-scale measurement study of cryptographic misuse within the EAI mobile ecosystem. We construct EAIAppZoo, a benchmark of 507 real-world applications across six EAI domains, and employ an automated semantic-aware analysis pipeline to measure the prevalence and characteristics of five major cryptographic failure modes. Our measurement yields 12,975 misuse findings (with an evaluated precision of 80.74\%), revealing that these cryptographic failures are driven by EAI-specific engineering constraints rather than random developer errors. We uncover structural security trade-offs: latency-sensitive control paths systematically weaken transport protection, while the heavy reliance on offline device provisioning and legacy IoT SDKs exacerbates the local hardcoding of authentication credentials. Through real-world case studies, we demonstrate how these mobile-side cryptographic flaws bypass nominal network protections, enabling adversaries to intercept command channels and hijack the physical control of EAI entities. Ultimately, our findings highlight that mobile applications have become a fragile, yet overlooked, cryptographic trust boundary in cyber-physical systems.

cs.CR↗

arXiv2026

Reverse Iterated Function Systems: Density, Dimensions, and $p$-adic Extension

Strichartz initiated the study of reverse iterated function systems (RIFSs) on integer lattices and the dimensions of their invariant sets. We develop a dimension theory for RIFSs through forward orbits, first on locally compact complete metric spaces and then for one-dimensional affine systems. For an affine RIFS $\mathcal F=\{f_i(x)=r_i x+b_i\}_{i=1}^m$ on $\mathbb R$, we introduce the semigroup-growth exponent\[ d_{\mathcal F}=\lim_{R\to\infty}\frac{\log\#\{g\in G^*(\mathcal F):|g'|\le R\}}{\log R}, \] where $G^*(\mathcal F)$ is the semigroup of distinct maps generated by $\mathcal F$. We prove that this limit exists and that $\dim_{\mathrm B}K(\mathcal F^{-1})\le d_{\mathcal F}\le s$. Every forward orbit has mass dimension $d_{\mathcal F}$ if it is locally finite and infinity otherwise; its Beurling dimension is $d_{\mathcal F}$ if it is uniformly locally finite and infinity otherwise. These formulas extend to suitably discrete invariant sets. Moreover, $d_{\mathcal F}=s$ if and only if the dual IFS has no exact overlaps, while $d_{\mathcal F}=0$ if and only if $\mathcal F$ is degenerate. Under finite overlaps, we obtain two-sided polynomial orbit-counting estimates. For non-overlapping uniformly locally finite orbits, renewal theory gives a limiting central density in the non-arithmetic case and a multiplicatively periodic asymptotic profile in the arithmetic case. We also determine the lower and discrete Hausdorff dimensions of rational lattice orbits with finite overlaps. Finally, for expansion ratios that are signed powers of a fixed prime $p$, we identify the Euclidean mass and Beurling dimensions of every rational orbit with the $p$-adic box-counting dimensions of the orbit and its attractor, without any separation assumption.

math.DS↗

arXiv2026

Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning

Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and large-scale geographic mapping. Existing approaches face a fundamental trade-off: optimization-based methods achieve strong accuracy but require hours of per-scene computation, while generalizable geometry foundation models offer near-instant inference but fail to generalize to satellite imagery due to the domain gap introduced by the Rational Polynomial Camera (RPC) model and mismatched depth scale distributions. We present Sat3R, a feed-forward framework that bridges this gap via RPC-aware metric depth fine-tuning of Depth Anything V2 using the Scale-Invariant Logarithmic (SiLog) loss. By constructing physically consistent pseudo depth supervision from RPC geometry, Sat3R adapts a monocular depth foundation model to the satellite domain without per-scene optimization. Experiments on the DFC2019 benchmark demonstrate that Sat3R reduces MAE by 38% over zero-shot feed-forward baselines and achieves competitive accuracy against optimization-based methods, while delivering over 300x speedup. Sat3R demonstrates that feed-forward models, when properly adapted to the satellite domain, can match optimization-based accuracy at a fraction of the computational cost, paving the way for practical large-scale satellite DSM reconstruction.

cs.CV↗

arXiv2026

OrbitBFT: Enabling Scalable and Robust BFT Consensus in LEO Constellations

Low Earth Orbit (LEO) satellite constellations are evolving from communication relays into autonomous platforms operating in increasingly congested and contested environments. Since uplinks to ground stations can be severed or jammed, ensuring reliable coordination among satellites requires autonomous Byzantine Fault-Tolerant (BFT) consensus. However, applying conventional BFT protocols to LEO constellations is challenging due to their dynamic topology, sparse connectivity, and limited communication bandwidth. In this paper, we present OrbitBFT, a novel two-stage hierarchical BFT consensus protocol tailored to the unique characteristics of LEO constellations. First, OrbitBFT exploits the topological stability within orbital planes to partition the constellation and perform localized intra-plane consensus, which reduces communication overhead. Second, we design a Byzantine-resilient bypass mechanism and a hop-by-hop transmission protocol to ensure reliable message delivery and mitigate congestion, even in the presence of adversarial behavior. Third, we adapt and optimize PBFT and HotStuff to the LEO context, achieving linear message complexity while preserving safety and liveness. Extensive evaluations in a realistic Starlink-based simulation demonstrate that OrbitBFT significantly improves scalability, throughput, and latency compared to its original designs, making it a practical and efficient BFT solution for large-scale satellite networks.

cs.DC↗

arXiv2026

PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) is essential for enhancing Large Language Models (LLMs) with external knowledge, but its reliance on cloud environments exposes sensitive data to privacy risks. Existing privacy-preserving solutions often sacrifice retrieval quality due to noise injection or only provide partial encryption. We propose PRAG, an end-to-end privacy-preserving RAG system that achieves end-to-end confidentiality for both documents and queries without sacrificing the scalability of cloud-hosted RAG. PRAG features a dual-mode architecture: a non-interactive PRAG-I utilizes homomorphic-friendly approximations for low-latency retrieval, while an interactive PRAG-II leverages client assistance to match the accuracy of non-private RAG. To ensure robust semantic ordering, we introduce Operation-Error Estimation (OEE), a mechanism that stabilizes ranking against homomorphic noise. Experiments on large-scale datasets demonstrate that PRAG achieves competitive recall (72.45%-74.45%), practical retrieval latency, and strong resilience against graph reconstruction attacks while maintaining end-to-end confidentiality. This work confirms the feasibility of secure, high-performance RAG at scale.

cs.CR↗

arXiv2026

AgentDID: Trustless Identity Authentication for AI Agents

AI agents are autonomous entities that can be instantiated on demand, migrate across platforms, and interact with other agents or services without continuous human supervision. In such environments, identity is critical for establishing reliable interaction semantics among agents that may lack prior trust relationships. However, existing identity and access management mechanisms are designed for human users or static machines, assuming centralized enrollment, persistent identifiers, and stable execution contexts. These assumptions do not hold for AI agents, whose identities are self-managed, short-lived, and tightly coupled with their execution state and capabilities. We study the problem of identity authentication and state verification for AI agents and identify three challenges: (1) supporting self-managed identities for autonomously created agents, (2) enabling authentication under large-scale, concurrent interactions, and (3) verifying agents' dynamic execution state, such as whether their context and capabilities remain valid at interaction time. To address these challenges, we present AgentDID, a decentralized framework for identity authentication and state verification. AgentDID leverages decentralized identifiers (DIDs) and verifiable credentials (VCs), enabling agents to manage their own identities and authenticate across systems without centralized control. To address the limitations of static credential-based approaches, AgentDID introduces a challenge-response mechanism that allows verifiers to validate an agent's execution conditions at interaction time. We implement AgentDID in compliance with W3C standards and evaluate it through throughput experiments with multiple concurrent agents. Results show that the system achieves scalable identity authentication and state verification, demonstrating its potential to support large populations of AI agents.

cs.CR↗

arXiv2026

Efficient Diffusion Distillation via Embedding Loss

Recent advances in distilling expensive diffusion models into efficient few-step generators show significant promise. However, these methods typically demand substantial computational resources and extended training periods, limiting accessibility for resource-constrained researchers, and existing supplementary loss functions have notable limitations. Regression loss requires pre-generating large datasets before training and limits the student model to the teacher's performance, while GAN-based losses suffer from training instability and require careful tuning. In this paper, we propose Embedding Loss (EL), a novel supplementary loss function that complements existing diffusion distillation methods to enhance generation quality and accelerate training with smaller batch sizes. Leveraging feature embeddings from a diverse set of randomly initialized networks, EL effectively aligns the feature distributions between the distilled few-step generator and the original data. By computing Maximum Mean Discrepancy (MMD) in the embedded feature space, EL ensures robust distribution matching, thereby preserving sample fidelity and diversity during distillation. Within distribution matching distillation frameworks, EL demonstrates strong empirical performance for one-step generators. On the CIFAR-10 dataset, our approach achieves state-of-the-art FID values of 1.475 for unconditional generation and 1.380 for conditional generation. Beyond CIFAR-10, we further validate EL across multiple benchmarks and distillation methods, including ImageNet, AFHQ-v2, and FFHQ datasets, using DMD, DI, and CM distillation frameworks, demonstrating consistent improvements over existing one-step distillation methods. Our method also reduces training iterations by up to 80%, offering a more practical and scalable solution for deploying diffusion-based generative models in resource-constrained environments.

cs.CV↗

arXiv2026

Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs

Traditional data valuation methods based on ``row-count $\times$ quality coefficient'' paradigms fail to capture the nuanced, nonlinear contributions that data makes to Large Language Model (LLM) capabilities. This paper presents a dynamic data valuation framework that transitions from static accounting to utility-based pricing. Our approach operates on three layers: (1) token-level information density metrics using Shannon entropy and Data Quality Scores; (2) empirical training gain measurement through influence functions, proxy model strategies, and Data Shapley values; and (3) cryptographic verifiability through hash-based commitments, Merkle trees, and a tamper-evident training ledger. We provide comprehensive experimental validation on three real domains (instruction following, mathematical reasoning, and code summarization), demonstrating that proxy-based empirical gain achieves near-perfect ranking alignment with realized utility, substantially outperforming row-count and token-count baselines. This framework enables a fair Data-as-a-Service economy where high-reasoning data is priced according to its actual contribution to model intelligence, while providing the transparency and auditability necessary for trustworthy data markets.

cs.LG↗