Searcharxiv⌕ Search

arXiv subjects

Xin Huang

Publications and source records attributed to Xin Huang.

At least 55 records · Page 3Linked to original sources
arXiv2026

Convergence for adaptive resampling of random Fourier features

The machine learning random Fourier feature method for data in high dimension is computationally and theoretically attractive since the optimization is based on a convex standard least squares problem and independent sampling of Fourier frequencies. The challenge is to sample the Fourier frequencies well. This work proves convergence of a data adaptive method based on resampling the frequencies asymptotically optimally, as the number of nodes and amount of data tend to infinity. Numerical results based on resampling and adaptive random walk steps together with approximations of the least squares problem by conjugate gradient iterations confirm the analysis for regression and classification problems.

math.NA↗
arXiv2026

PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning

Reinforcement learning (RL) has shown strong promise for LLM-based machine translation, with recent methods such as GRPO demonstrating notable gains; nevertheless, translation-oriented RL remains challenged by noisy learning signals arising from Monte Carlo return estimation, as well as a large trajectory space that favors global exploration over fine-grained local optimization. We introduce \textbf{PEGRL}, a \textit{two-stage} RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization. At each iteration, translation outputs are sampled to construct post-editing inputs, allowing return estimation in the post-editing stage to benefit from conditioning on the current translation behavior, while jointly supporting both global exploration and fine-grained local optimization. A task-specific weighting scheme further balances the contributions of translation and post-editing objectives, yielding a biased yet more sample-efficient estimator. Experiments on English$\to$Finnish, English$\to$Turkish, and English$\leftrightarrow$Chinese show consistent gains over RL baselines, and for English$\to$Turkish, performance on COMET-KIWI is comparable to advanced LLM-based systems (DeepSeek-V3.2). Our code and a set of representative pretrained models are publicly available at \url{https://github.com/NJUNLP/peg-rl} and \url{https://huggingface.co/collections/DGME/pegrl}

cs.CL↗
arXiv2026

The Galois Alperin weight conjecture for finite category algebras

Let $p$ be a prime, $k$ an algebraic closure of $\mathbb{F}_p$ and $Γ$ the Galois group ${\rm Gal}(k/\mathbb{F}_p)$. Let $\mathcal{C}$ be a finite category and $\mathcal{O}_{\mathcal{C}}$ the $p$-orbit category of $\mathcal{C}$ defined by Linckelmann. We formulate a version of the Galois Alperin weight conjecture (GAWC) for finite category algebras stating that there exists a $Γ\times {\rm Aut}(\mathcal{C})$-equivariant bijection between the set of isomorphism classes of simple $k\mathcal{C}$-modules and that of the weights of $k\mathcal{O}_{\mathcal{C}}$. We reduce the GAWC for finite categories to finite groups. For $\mathcal{C}$ an EI-category, we give a partition of weights of $k\mathcal{O}_{\mathcal{C}}$ with respect to blocks of $k\mathcal{C}$ and then formulate a blockwise Galois Alperin weight conjecture (BGAWC) for $\mathcal{C}$. Similarly, we reduce the BGAWC for finite EI-categories to finite groups.

math.RT↗
arXiv2026

PhysLayer: Language-Guided Layered Animation with Depth-Aware Physics

Existing image-to-video generation methods often produce physically implausible motions and lack precise control over object dynamics. While prior approaches have incorporated physics simulators, they remain confined to 2D planar motions and fail to capture depth-aware spatial interactions. We introduce PhysLayer, a novel framework enabling language-guided, depth-aware layered animation of static images. PhysLayer consists of three key components: First, a language-guided scene understanding module that utilizes vision foundation models to decompose scenes into depth-based layers by analyzing object composition, material properties, and physical parameters. Second, a depth-aware layered physics simulation that extends 2D rigid-body dynamics with depth motion and perspective-consistent scaling, enabling more realistic object interactions without requiring full 3D reconstruction. Third, a physics-guided video synthesis module that integrates simulated trajectories with scene-aware relighting for temporally coherent results. Experimental results demonstrate improvements in CLIP-Similarity (+2.2\%), FID score (+9.3\%), and Motion-FID (+3\%), with human evaluation showing enhanced physical plausibility (+24\%) and text-video alignment (+35\%). Our approach provides a practical balance between physical realism and computational efficiency for controllable image animation.

cs.CV↗
arXiv2026

CineAGI: Character-Consistent Movie Creation through LLM-Orchestrated Multi-Modal Generation and Cross-Scene Integration

Automated movie creation requires coordinating multiple characters, modalities, and narrative elements across extended sequences -- a challenge that existing end-to-end approaches struggle to address effectively. We present \textbf{CineAGI}, a hierarchical movie generation framework that decomposes this complex task through specialized multi-agent orchestration. Our framework employs three key innovations: (1) a multi-agent narrative synthesis module where specialized LLM agents collaboratively generate comprehensive cinematic blueprints with character profiles, scene descriptions, and cross-modal specifications; (2) a decoupled character-centric pipeline that maintains identity consistency through instance-level tracking and integration while enabling flexible multi-character composition; and (3) a hierarchical audio-visual synchronization mechanism ensuring frame-level alignment of dialogue, expressions, and music. Extensive experiments demonstrate that CineAGI achieves 40\% improvement in overall consistency, 4.4\% gain in subject consistency, 5.4\% enhancement in aesthetic quality, and 28.7\% higher character consistency compared to baselines. Our work establishes a principled foundation for automated multi-scene video generation that preserves narrative coherence and character authenticity.

cs.MM↗
arXiv2026

On stable equivalences of Morita type with twisted diagonal vertices

We give a new proof, by using simplified terminology and notation, to a result of Puig stating that if a bimodule of two block algebras of finite groups over an algebraically closed field induces a stable equivalence of Morita type and has a twisted diagonal vertex, then it has an endopermutation module as a source. We also extend this result to arbitrary fields under a mild assumption.

math.RT↗
arXiv2026

Score-Based Matching with Target Guidance for Cryo-EM Denoising

Cryo-electron microscopy (cryo-EM) enables single-particle analysis of biological macromolecules under strict low-dose imaging conditions, but the resulting micrographs often exhibit extremely low signal-to-noise ratios and weak particle visibility. Image denoising is therefore an important preprocessing step for downstream cryo-EM analysis, including particle picking, 2D classification, and 3D reconstruction. Existing cryo-EM denoising methods are commonly trained with pixel-wise or Noise2Noise-style objectives, which can improve visual quality but do not explicitly account for structural consistency required by downstream analysis. In this work, we propose a score-based denoising framework for cryo-EM that learns the clean-data score to recover particle signals while better preserving structural information. Building on this formulation, we further introduce a target-guided variant that incorporates reference-density guidance to stabilize score learning under weak and ambiguous signal conditions. Rather than simply amplifying particle-like responses, our framework better suppresses structured low-frequency background, which improves particle--background separability for downstream analysis. Experiments on multiple cryo-EM datasets show that our score-based methods consistently improve downstream particle picking and produce more structure-consistent 3D reconstructions. Experiments on multiple cryo-EM datasets show that our methods improve downstream particle picking and produce more structure-consistent reconstructions.

cs.CV↗
arXiv2026

Efficient Community Search on Attributed Public-Private Graphs

Public-private graph, where a public network is visible to everyone and every user is also associated with its own small private graph accessed by itself only, widely exists in real-world applications of social networks and financial networks. Most existing work on community search, finding a query-dependent community containing a given query, only studies on a public graph, neglecting the privacy issues in public-private networks. However, considering both the public and private attributes of users enables community search to be more accurate, comprehensive, and personalized to discover hidden patterns. In this paper, we study a novel problem of attributed community search in public-private graphs (ACS-PP), aiming to find a connected k-core community that shares the most keywords with the query node. This problem uncovers structurally cohesive communities, such as interest-based user groups or core teams in collaborative networks. To optimize search efficiency, we propose an integrated scheme of constructing a public global graph index and a private personalized graph index. For the private index, we developed a compact structure of the PP-FP-tree index. The PP-FP-tree is constructed based on the public and private neighbors of the query node in the public-private graph, serving as an efficient index to mine frequent node sets that share the most common attributes with the query node. Extensive experiments on real public-private graph datasets validate both the efficiency and quality of our proposed PP-FP search algorithm against existing competitors. The case study on public-private collaboration networks provides insights into the discovery of public-private communities.

cs.DB↗
arXiv2026

AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought

Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. Although these models show strong reasoning abilities, their performance varies significantly between languages due to the imbalanced distribution of training data. Existing approaches using sample-level translation for extensive multilingual pretraining and cross-lingual tuning face scalability challenges and often fail to capture nuanced reasoning processes across languages. In this paper, we introduce AdaMCOT (Adaptive Multilingual Chain-of-Thought), a framework that enhances multilingual factual reasoning by dynamically routing thought processes in intermediary "thinking languages" before generating target-language responses. AdaMCOT leverages a language-agnostic core and incorporates an adaptive, reward-based mechanism for selecting optimal reasoning pathways without requiring additional pretraining. Our comprehensive evaluation across multiple benchmarks demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency, with particularly strong performance gains in low-resource language settings. An in-depth analysis of the model's hidden states and semantic space further elucidates the underlying mechanism of our method. The results suggest that adaptive reasoning paths can effectively bridge the performance gap between high and low-resource languages while maintaining cultural and linguistic nuances.

cs.CL↗
arXiv2026

Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance

Multilingual Large Language Models (LLMs) struggle with cross-lingual tasks due to data imbalances between high-resource and low-resource languages, as well as monolingual bias in pre-training. Existing methods, such as bilingual fine-tuning and contrastive alignment, can improve cross-lingual performance, but they often require extensive parallel data or suffer from instability. To address these challenges, we introduce a Cross-Lingual Mapping Task during the pre-training phase, which enhances cross-lingual alignment without compromising monolingual fluency. Our approach bi-directionally maps languages within the LLM embedding space, improving both language generation and comprehension. We further propose a Language Alignment Coefficient to robustly quantify cross-lingual consistency, even in limited-data scenarios. Experimental results on machine translation (MT), cross-lingual natural language understanding (CLNLU), and cross-lingual question answering (CLQA) show that our model achieves gains of up to 11.9 BLEU points in MT, 6.72 points in CLQA BERTScore-Precision, and more than 5% in CLNLU accuracy over strong multilingual baselines. These findings highlight the potential of incorporating cross-lingual objectives into pre-training to improve multilingual LLMs.

cs.CL↗
arXiv2026

Auditing MCP Servers for Over-Privileged Tool Capabilities

The Model Context Protocol (MCP) has emerged as a standard for connecting Large Language Models (LLMs) to external tools and data. However, MCP servers often expose privileged capabilities, such as file system access, network requests, and command execution that can be exploited if not properly secured. We present mcp-sec-audit, an extensible security assessment toolkit designed specifically for MCP servers. It implements static pattern matching for Python-based MCP servers and dynamic sandboxed fuzzing and monitoring via Docker and eBPF. The tool detects risky capabilities through configurable rule-based analysis and provides mitigation recommendations.

cs.CR↗
arXiv2026

Are AI-assisted Development Tools Immune to Prompt Injection?

Prompt injection is listed as the number-one vulnerability class in the OWASP Top 10 for LLM Applications that can subvert LLM guardrails, disclose sensitive data, and trigger unauthorized tool use. Developers are rapidly adopting AI-assisted development tools built on the Model Context Protocol (MCP). However, their convenience comes with security risks, especially prompt-injection attacks delivered via tool-poisoning vectors. While prior research has studied prompt injection in LLMs, the security posture of real-world MCP clients remains underexplored. We present the first empirical analysis of prompt injection with the tool-poisoning vulnerability across seven widely used MCP clients: Claude Desktop, Claude Code, Cursor, Cline, Continue, Gemini CLI, and Langflow. We identify their detection and mitigation mechanisms, as well as the coverage of security features, including static validation, parameter visibility, injection detection, user warnings, execution sandboxing, and audit logging. Our evaluation reveals significant disparities. While some clients, such as Claude Desktop, implement strong guardrails, others, such as Cursor, exhibit high susceptibility to cross-tool poisoning, hidden parameter exploitation, and unauthorized tool invocation. We further provide actionable guidance for MCP implementers and the software engineering community seeking to build secure AI-assisted development workflows.

cs.CR↗
arXiv2026

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

The Model Context Protocol (MCP) has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces significant security vulnerabilities, particularly on the client side. In this work we conduct threat modelings of MCP implementations using STRIDE (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege) and DREAD (Damage, Reproducibility, Exploitability, Affected Users, Discoverability) frameworks across five key components: (1) MCP Host and Client, (2) LLM, (3) MCP Server, (4) External Data Stores, and (5) Authorization Server. This comprehensive analysis reveals tool poisoning-where malicious instructions are embedded in tool metadata-as the most prevalent and impactful client-side vulnerability. We therefore focus our empirical evaluation on this critical attack vector, providing a systematic comparison of how seven major MCP clients validate and defend against tool poisoning attacks. Our analysis reveals significant security issues with most tested clients due to insufficient static validation and parameter visibility. We propose a multi-layered defense strategy encompassing static metadata analysis, model decision path tracking, behavioral anomaly detection, and user transparency mechanisms. This research addresses a critical gap in MCP security, which has primarily focused on server-side vulnerabilities, and provides actionable recommendations and mitigation strategies for securing AI agent ecosystems.

cs.CR↗
arXiv2026

Visually-Guided Controllable Medical Image Generation via Fine-Grained Semantic Disentanglement

Medical image synthesis is crucial for alleviating data scarcity and privacy constraints. However, fine-tuning general text-to-image (T2I) models remains challenging, mainly due to the significant modality gap between complex visual details and abstract clinical text. In addition, semantic entanglement persists, where coarse-grained text embeddings blur the boundary between anatomical structures and imaging styles, thus weakening controllability during generation. To address this, we propose a Visually-Guided Text Disentanglement framework. We introduce a cross-modal latent alignment mechanism that leverages visual priors to explicitly disentangle unstructured text into independent semantic representations. Subsequently, a Hybrid Feature Fusion Module (HFFM) injects these features into a Diffusion Transformer (DiT) through separated channels, enabling fine-grained structural control. Experimental results in three datasets demonstrate that our method outperforms existing approaches in terms of generation quality and significantly improves performance on downstream classification tasks. The source code is available at https://github.com/hx111/VG-MedGen.

cs.CV↗
arXiv2026

BAMG: A Block-Aware Monotonic Graph Index for Disk-Based Approximate Nearest Neighbor Search

Approximate Nearest Neighbor Search (ANNS) over high-dimensional vectors is a foundational problem in databases, where disk I/O often emerges as the dominant performance bottleneck at scale. To accelerate search, graph-based indexes rely on proximity graph, where nodes represent vectors and edges guide the traversal toward the target. However, existing graph indexing solutions for disk-based ANNS typically either optimize the storage layout for a given graph or construct the graph independently of the storage layout, thus overlooking their interaction. In this paper, we bridge this gap by proposing the Block-aware Monotonic Relative Neighborhood Graph (BMRNG), theoretically guaranteeing the existence of I/O monotonic search paths. The core idea is to align the graph topology with the data placement by jointly considering both geometric distance and storage layout for edge selection. To address the scalability challenge of BMRNG construction, we further develop a practical and efficient variant, the Block-Aware Monotonic Graph (BAMG), which can be constructed in linear time from a monotonic graph considering the storage layout. BAMG integrates block-aware edge pruning with a decoupled storage design that separates raw vectors from the graph index, thereby maximizing block utilization and minimizing redundant disk reads. Additionally, we design a multi-layer navigation graph for adaptive and efficient query entry, along with a block-first search algorithm that prioritizes intra-block traversal to fully exploit each disk I/O operation. Extensive experiments on real-world datasets show that BAMG can outperform state-of-the-art methods in search performance.

cs.DB↗
arXiv2026

LLMTailor: A Layer-wise Tailoring Tool for Efficient Checkpointing of Large Language Models

Checkpointing is essential for fault tolerance in training large language models (LLMs). However, existing methods, regardless of their I/O strategies, periodically store the entire model and optimizer states, incurring substantial storage overhead and resource contention. Recent studies reveal that updates across LLM layers are highly non-uniform. Across training steps, some layers may undergo more significant changes, while others remain relatively stable or even unchanged. This suggests that selectively checkpointing only layers with significant updates could reduce overhead without harming training. Implementing such selective strategies requires fine-grained control over both weights and optimizer states, which no current tool provides. To address this gap, we propose \texttt{LLMTailor}, a checkpoint-merging framework that filters and assembles layers from different checkpoints to form a composite checkpoint. Our evaluation indicates that LLMTailor can work with different selective checkpointing strategies and effectively reduce checkpoint size (e.g., 4.3 times smaller for Llama3.1-8B) and checkpoint time (e.g., 2.8 times faster for Qwen2.5-7B) while maintaining model quality.

cs.DC↗
arXiv2026

Scrutinizing Variables for Checkpoint Using Automatic Differentiation

Checkpoint/Restart (C/R) saves the running state of the programs periodically, which consumes considerable system resources. We observe that not every piece of data is involved in the computation in typical HPC applications; such unused data should be excluded from checkpointing for better storage/compute efficiency. To find out, we propose a systematic approach that leverages automatic differentiation (AD) to scrutinize every element within variables (e.g., arrays) for checkpointing allowing us to identify critical/uncritical elements and eliminate uncritical elements from checkpointing. Specifically, we inspect every single element within a variable for checkpointing with an AD tool to determine whether the element has an impact on the application output or not. We empirically validate our approach with eight benchmarks from the NAS Parallel Benchmark (NPB) suite. We successfully visualize critical/uncritical elements/regions within a variable with respect to its impact (yes or no) on the application output. We find patterns/distributions of critical/uncritical elements/regions quite interesting and follow the physical formulation/logic of the algorithm.The evaluation on NPB benchmarks shows that our approach saves storage for checkpointing by up to 20%.

cs.DC↗
arXiv2026

P-EAGLE: Parallel-Drafting EAGLE with Scalable Training

Reasoning LLMs produce longer outputs, requiring speculative decoding drafters trained on extended sequences. Parallel drafting - predicting multiple tokens per forward pass - offers latency benefits over sequential generation, but training complexity scales quadratically with the product of sequence length and parallel positions, rendering long-context training impractical. We present P(arallel)-EAGLE, which transforms EAGLE from autoregressive to parallel multi-token prediction via a learnable shared hidden state. To scale training to long contexts, we develop a framework featuring attention mask pre-computation and sequence partitioning techniques, enabling gradient accumulation within individual sequences for parallel-prediction training. We implement P-EAGLE in vLLM and demonstrate speedups of 1.10-1.36x over autoregressive EAGLE-3 across GPT-OSS 120B, 20B, and Qwen3-Coder 30B.

cs.LG↗