Searcharxiv⌕ Search

arXiv subjects

Cheng Huang

Publications and source records attributed to Cheng Huang.

At least 37 records · Page 2Linked to original sources
arXiv2026

PipeWeave: Synergizing Analytical and Learning Models for Unified GPU Performance Prediction

The rapid expansion of Transformer-based large language models has dramatically increased the need for high-performance GPUs. As a result, there is growing demand for fast, accurate, and widely generalizable GPU performance models to support next-generation hardware selection and system-level exploration. However, current data-driven methods are limited, exhibiting poor generalization across hardware and inadequate modeling of complex production-level kernels common in modern inference stacks. To address these issues, we present PipeWeave, a unified GPU modeling framework. This approach first employs an analytical model to quantify a given kernel's demands on the GPU's heterogeneous instruction pipelines. These analytical features are then fed into a machine learning (ML) model to capture complex cross-pipeline interactions and resource dependencies, enabling high-fidelity performance prediction. Our evaluation across 11 GPU types from four generations of major architectures on two widely-used serving systems demonstrates that PipeWeave delivers high fidelity and strong generalizability. It achieves accurate predictions, with only 6.1% average error at the kernel level and 8.5% for end-to-end inference -- reducing the error of state-of-the-art methods by 6.7x and 4.4x, respectively. We also demonstrate PipeWeave's value "beyond simulation" by utilizing its performance ceiling to diagnose implementation shortcomings and guide the optimization of a production fused MoE Triton kernel, achieving up to 1.7x speedup. Code is available https://github.com/zksainx/pipeweave.

cs.PF↗
arXiv2026

FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for Ü-Tsang, Amdo and Kham Speech Dataset Generation

Tibetan is a low-resource language with minimal parallel speech corpora spanning its three major dialects-Ü-Tsang, Amdo, and Kham-limiting progress in speech modeling. To address this issue, we propose FMSD-TTS, a few-shot, multi-speaker, multi-dialect text-to-speech framework that synthesizes parallel dialectal speech from limited reference audio and explicit dialect labels. Our method features a novel speaker-dialect fusion module and a Dialect-Specialized Dynamic Routing Network (DSDR-Net) to capture fine-grained acoustic and linguistic variations across dialects while preserving speaker identity. Extensive objective and subjective evaluations demonstrate that FMSD-TTS significantly outperforms baselines in both dialectal expressiveness and speaker similarity. We further validate the quality and utility of the synthesized speech through a challenging speech-to-speech dialect conversion task. Our contributions include: (1) a novel few-shot TTS system tailored for Tibetan multi-dialect speech synthesis, (2) the public release of a large-scale synthetic Tibetan speech corpus generated by FMSD-TTS, and (3) an open-source evaluation toolkit for standardized assessment of speaker similarity, dialect consistency, and audio quality.

cs.SD↗
arXiv2026

TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Framework for Ü-Tsang, Amdo and Kham Speech Dataset Generation

Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (Ü-Tsang, Amdo, and Kham), limiting progress in speech modeling. To address this issue, we propose TMD-TTS, a unified Tibetan multi-dialect text-to-speech (TTS) framework that synthesizes parallel dialectal speech from explicit dialect labels. Our method features a dialect fusion module and a Dialect-Specialized Dynamic Routing Network (DSDR-Net) to capture fine-grained acoustic and linguistic variations across dialects. Extensive objective and subjective evaluations demonstrate that TMD-TTS significantly outperforms baselines in dialectal expressiveness. We further validate the quality and utility of the synthesized speech through a challenging Speech-to-Speech Dialect Conversion (S2SDC) task.

cs.CL↗
arXiv2026

Component-Based Reduced-Order Modeling Framework for Rocket Combustion Dynamics in Multi-Injector Configurations

Even with the most advanced computational capabilities, high-fidelity (e.g., large-eddy) simulations of large-scale rocket engines remain far out of reach. In the current work, we develop and establish a component-based reduced-order modeling (CBROM) framework to enable accurate and efficient parametric modeling of large-scale rocket engines by geometrically decomposing a single domain into a combination of several representative components, including injectors, combustor and nozzle. Individual component-based reduced-order models (ROMs) are trained for each component with fabricated system-level responses enforced through carefully formulated boundary conditions during the training, which only require high-fidelity simulations of a much smaller computational domain, thereby significantly reducing the costs of ROM training. The trained component-based ROMs are then coupled together to enable full-system simulations. Specifically, we pursue an advanced adaptive ROM formulation leveraging a model-form preserving least-squares with variable transformation (MP-LSVT) projection to construct the component-based ROMs. The CBROM framework is evaluated using a seven-injector model rocket combustor configuration that exhibits self-excited combustion dynamics with distinct characteristics that vary with flow condition and geometric variations. The framework is demonstrated to provide accurate parametric predictions of the changes in dynamic behaviors, expressed in the spectra from dynamic mode decomposition (DMD) analysis and features in the time-averaged and RMS fields of target state variables.

physics.flu-dyn↗
arXiv2026

WaveTune: Wave-aware Bilinear Modeling for Efficient GPU Kernel Auto-tuning

The rapid adoption of Large Language Models (LLMs) has made GPU inference efficiency an increasingly critical system concern. The runtime of LLM workloads is largely dominated by tile-based kernels, particularly General Matrix Multiplications (GEMMs). Although these kernels are highly optimized, their performance remains sensitive to a large space of runtime parameters, such as tile sizes and pipeline stages. The interaction between these parameters and hardware resources leads to a non-convex optimization landscape. Existing approaches to parameter configuration -- including search-based auto-tuning, heuristic rules, and learned cost models -- face a fundamental trade-off between performance optimality and runtime efficiency. In this paper, we present WaveTune, a wave-aware framework for runtime kernel auto-tuning. First, we introduce a unified mapping method to handle input diversity and decompose the configuration space to manage high dimensionality. Second, we develop an analytical wave-aware bilinear model that accurately predicts kernel latency. Third, we design a sparse sampling scheme based on wave structures and a lightweight dual-table retrieval mechanism to minimize runtime overhead. As a result, WaveTune enables precise and efficient runtime configuration for GPU kernels. Across three representative kernels and five GPU architectures, WaveTune consistently achieves near-optimal kernel performance, delivering up to 1.83x kernel-level speedup and up to 1.33x end-to-end TTFT reduction, while reducing runtime decision overhead by five orders of magnitude compared to exhaustive search. These results demonstrate that WaveTune effectively eliminates the traditional trade-off between configuration latency and execution optimality, providing a practical and robust solution for high-performance LLM inference.

cs.PF↗
arXiv2026

Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing

The rapid advancement of Large Language Models (LLMs) has created new opportunities for Automated Penetration Testing (AutoPT), spawning numerous frameworks aimed at achieving end-to-end autonomous attacks. However, despite the proliferation of related studies, existing research generally lacks systematic architectural analysis and large-scale empirical comparisons under a unified benchmark. Therefore, this paper presents the first Systematization of Knowledge (SoK) focusing on the architectural design and comprehensive empirical evaluation of current LLM-based AutoPT frameworks. At systematization level, we comprehensively review existing framework designs across six dimensions: agent architecture, agent plan, agent memory, agent execution, external knowledge, and benchmarks. At empirical level, we conduct large-scale experiments on 13 representative open-source AutoPT frameworks and 2 baseline frameworks utilizing a unified benchmark. The experiments consumed over 10 billion tokens in total and generated more than 1,500 execution logs, which were manually reviewed and analyzed over four months by a panel of more than 15 researchers with expertise in cybersecurity. By investigating the latest progress in this rapidly developing field, we provide researchers with a structured taxonomy to understand existing LLM-based AutoPT frameworks and a large-scale empirical benchmark, along with promising directions for future research.

cs.CR↗
arXiv2026

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning

Enabling large language models (LLMs) to appropriately abstain from answering questions beyond their knowledge is crucial for mitigating hallucinations. While existing reinforcement learning methods foster autonomous abstention, they often compromise answer accuracy because their static reward mechanisms, agnostic to models' knowledge boundaries, drive models toward excessive caution. In this work, we propose KARL, a novel framework that continuously aligns an LLM's abstention behavior with its evolving knowledge boundary. KARL introduces two core innovations: a Knowledge-Boundary-Aware Reward that performs online knowledge boundary estimation using within-group response statistics, dynamically rewarding correct answers or guided abstention; and a Two-Stage RL Training Strategy that first explores the knowledge boundary and bypasses the "abstention trap", and subsequently converts incorrect answers beyond the knowledge boundary into abstentions without sacrificing accuracy. Extensive experiments on multiple benchmarks demonstrate that KARL achieves a superior accuracy-hallucination trade-off, effectively suppressing hallucinations while maintaining high accuracy across both in-distribution and out-of-distribution scenarios.

cs.LG↗
arXiv2026

AttnBoost: Retail Supply Chain Sales Insights via Gradient Boosting Perspective

Forecasting product demand in retail supply chains presents a complex challenge due to noisy, heterogeneous features and rapidly shifting consumer behavior. While traditional gradient boosting decision trees (GBDT) offer strong predictive performance on structured data, they often lack adaptive mechanisms to identify and emphasize the most relevant features under changing conditions. In this work, we propose AttnBoost, an interpretable learning framework that integrates feature-level attention into the boosting process to enhance both predictive accuracy and explainability. Specifically, the model dynamically adjusts feature importance during each boosting round via a lightweight attention mechanism, allowing it to focus on high-impact variables such as promotions, pricing, and seasonal trends. We evaluate AttnBoost on a large-scale retail sales dataset and demonstrate that it outperforms standard machine learning and deep tabular models, while also providing actionable insights for supply chain managers. An ablation study confirms the utility of the attention module in mitigating overfitting and improving interpretability. Our results suggest that attention-guided boosting represents a promising direction for interpretable and scalable AI in real-world forecasting applications.

cs.LG↗
arXiv2026

Thermodynamics of Shastry-Sutherland Model under Magnetic Field

Motivated by the recent experimental discovery of the $T$-linear specific heat in pressurized and magnetized Shastry-Sutherland Mott insulator SrCu$_2$(BO$_3$)$_2$, we perform the state-of-the-art thermal tensor-network computation on the Shastry-Sutherland model under a magnetic field. Our simulation results suggest the existence of a symmetric intermediate phase with $T$-linear specific heat at low temperature, occupying a large parameter space and between the plaquette-singlet phase and antiferromagnetic phase at low fields and other symmetry-breaking phases at high fields before the system is fully polarized. Such an unexpected novel state bears an astonishing similarity to the experimental findings in the material. It opens the door to further investigations of the possible liberation of deconfined magnetized Dirac spinons by the competing interactions in this highly frustrated quantum magnet model, and by the combined effects of magnetic field and pressure in the associated Shastry-Sutherland Mott insulator SrCu$_2$(BO$_3$)$_2$.

cond-mat.str-el↗
arXiv2026

T-linear specific heat in pressurized and magnetized Shastry-Sutherland Mott insulator SrCu2(BO3)2

The pressurized Shastry-Sutherland Mott insulator SrCu2(BO3)2 has been found to host a plaquette-singlet phase and an antiferromagnetic phase that break different symmetries spontaneously.The recent experiment showed that their transition is of a first order nature, which seems against the pursuit of exotic and deconfined degrees of freedom in this famous frustrated quantum magnet. We found a new direction in this study. By applying a magnetic field to the material, we discover that SrCu2(BO3)2 exhibits a universal and metallic T-linear specific heat behavior in a large magnetitic field range close to the pressure of zero-field first order transition between plaquette-singlet and antiferromagnetic phases. Such an unexpected gapless response from an electronically gapped Mott insulator could be attributed to magnetized Dirac spinons liberated by the combined effect of magnetic field and pressure, consistently seen from our quantum many-body thermal tensor network computation of the Shastry-Sutherland model under magnetic field. Such a robust and universal T-linear specific heat phase points out the richness of the phase diagram of the material expanded by the axes of pressure and magnetic field and is calling for new theoretical frameworks to its full explanation.

cond-mat.str-el↗
arXiv2026

LFQA-E: Carefully Benchmarking Long-form QA Evaluation

Long-Form Question Answering (LFQA) involves generating comprehensive, paragraph-level responses to open-ended questions, which poses a significant challenge for evaluation due to the richness of information and flexible response format. Existing LFQA-evaluation benchmarks often lack reference answers and are limited in size and topic coverage, reducing their reliability. To address this gap, we introduce LFQA-E, a well-constructed, multilingual, and reference-based benchmark designed to rigorously evaluate automatic metrics for LFQA. LFQA-E comprises 1618 questions and 7323 pairwise comparisons across 15 topics, drawn from diverse sources such as online queries and examination questions, thereby enabling a comprehensive assessment of evaluation metrics. We examine five categories of metrics, encompassing 17 specific methods, using LFQA-E. The results demonstrate that none of the existing automatic metrics perform comparably to human judgments, highlighting their inability to capture the dense information in long-form responses. Furthermore, we present a detailed analysis of the failure cases and the generalization capacity of these metrics, offering insights to guide the future development of LFQA evaluation methods. The benchmark and code are available at https://github.com/YuchenFan48/LFQA-E.

cs.CL↗
arXiv2026

Fair-Eye Net: A Fair, Trustworthy, Multimodal Integrated Glaucoma Full Chain AI System

Glaucoma is a top cause of irreversible blindness globally, making early detection and longitudinal follow-up pivotal to preventing permanent vision loss. Current screening and progression assessment, however, rely on single tests or loosely linked examinations, introducing subjectivity and fragmented care. Limited access to high-quality imaging tools and specialist expertise further compromises consistency and equity in real-world use. To address these gaps, we developed Fair-Eye Net, a fair, reliable multimodal AI system closing the clinical loop from glaucoma screening to follow-up and risk alerting. It integrates fundus photos, OCT structural metrics, VF functional indices, and demographic factors via a dual-stream heterogeneous fusion architecture, with an uncertainty-aware hierarchical gating strategy for selective prediction and safe referral. A fairness constraint reduces missed diagnoses in disadvantaged subgroups. Experimental results show it achieved an AUC of 0.912 (96.7% specificity), cut racial false-negativity disparity by 73.4% (12.31% to 3.28%), maintained stable cross-domain performance, and enabled 3-12 months of early risk alerts (92% sensitivity, 88% specificity). Unlike post hoc fairness adjustments, Fair-Eye Net optimizes fairness as a primary goal with clinical reliability via multitask learning, offering a reproducible path for clinical translation and large-scale deployment to advance global eye health equity.

cs.CV↗
arXiv2025

From Retrieval to Reasoning: A Framework for Cyber Threat Intelligence NER with Explicit and Adaptive Instructions

The automation of Cyber Threat Intelligence (CTI) relies heavily on Named Entity Recognition (NER) to extract critical entities from unstructured text. Currently, Large Language Models (LLMs) primarily address this task through retrieval-based In-Context Learning (ICL). This paper analyzes this mainstream paradigm, revealing a fundamental flaw: its success stems not from global semantic similarity but largely from the incidental overlap of entity types within retrieved examples. This exposes the limitations of relying on unreliable implicit induction. To address this, we propose TTPrompt, a framework shifting from implicit induction to explicit instruction. TTPrompt maps the core concepts of CTI's Tactics, Techniques, and Procedures (TTPs) into an instruction hierarchy: formulating task definitions as Tactics, guiding strategies as Techniques, and annotation guidelines as Procedures. Furthermore, to handle the adaptability challenge of static guidelines, we introduce Feedback-driven Instruction Refinement (FIR). FIR enables LLMs to self-refine guidelines by learning from errors on minimal labeled data, adapting to distinct annotation dialects. Experiments on five CTI NER benchmarks demonstrate that TTPrompt consistently surpasses retrieval-based baselines. Notably, with refinement on just 1% of training data, it rivals models fine-tuned on the full dataset. For instance, on LADDER, its Micro F1 of 71.96% approaches the fine-tuned baseline, and on the complex CTINexus, its Macro F1 exceeds the fine-tuned ACLM model by 10.91%.

cs.CR↗
arXiv2025

TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models

To address the severe data scarcity in Tibetan, a low-resource language spoken by over six million people, we introduce TIBSTC-CoT, the large-scale, multi-domain Tibetan dataset automatically constructed via chain-of-thought prompting with large language models (LLMs). TIBSTC-CoT establishes a scalable and reproducible framework for dataset creation in low-resource settings, covering diverse domains and reasoning patterns essential for language understanding and generation. Building on this dataset, we develop the Sunshine-thinking LLM family, a series of Tibetan-centric LLMs equipped with chain-of-thought capabilities. Trained entirely on TIBSTC-CoT, Sunshine-thinking has demonstrated strong reasoning and generation performance, comparable to state-of-the-art (SOTA) multilingual LLMs. Our work marks a significant step toward inclusive AI by enabling high-quality Tibetan language processing through both resource creation and model innovation. All data are available: https://github.com/Vicentvankor/sun-shine.

cs.CL↗
arXiv2025

PrivDFS: Private Inference via Distributed Feature Sharing against Data Reconstruction Attacks

In this paper, we introduce PrivDFS, a distributed feature-sharing framework for input-private inference in image classification. A single holistic intermediate representation in split inference gives diffusion-based Data Reconstruction Attacks (DRAs) sufficient signal to reconstruct the input with high fidelity. PrivDFS restructures this vulnerability by fragmenting the representation and processing the fragments independently across a majority-honest set of servers. As a result, each branch observes only an incomplete and reconstruction-insufficient view of the input. To realize this, PrivDFS employs learnable binary masks that partition the intermediate representation into sparse and largely non-overlapping feature shares, each processed by a separate server, while a lightweight fusion module aggregates their predictions on the client. This design preserves full task accuracy when all branches are combined, yet sharply limits the reconstructive power available to any individual server. PrivDFS applies seamlessly to both ResNet-based CNNs and Vision Transformers. Across CIFAR-10/100, CelebA, and ImageNet-1K, PrivDFS induces a pronounced collapse in DRA performance, e.g., on CIFAR-10, PSNR drops from 23.25 -> 12.72 and SSIM from 0.963 -> 0.260, while maintaining accuracy within 1% of non-private split inference. These results establish structural feature partitioning as a practical and architecture-agnostic approach to reducing reconstructive leakage in cloud-based vision inference.

cs.LG↗
arXiv2025

Tibetan Language and AI: A Comprehensive Survey of Resources, Methods and Challenges

Tibetan, one of the major low-resource languages in Asia, presents unique linguistic and sociocultural characteristics that pose both challenges and opportunities for AI research. Despite increasing interest in developing AI systems for underrepresented languages, Tibetan has received limited attention due to a lack of accessible data resources, standardized benchmarks, and dedicated tools. This paper provides a comprehensive survey of the current state of Tibetan AI in the AI domain, covering textual and speech data resources, NLP tasks, machine translation, speech recognition, and recent developments in LLMs. We systematically categorize existing datasets and tools, evaluate methods used across different tasks, and compare performance where possible. We also identify persistent bottlenecks such as data sparsity, orthographic variation, and the lack of unified evaluation metrics. Additionally, we discuss the potential of cross-lingual transfer, multi-modal learning, and community-driven resource creation. This survey aims to serve as a foundational reference for future work on Tibetan AI research and encourages collaborative efforts to build an inclusive and sustainable AI ecosystem for low-resource languages.

cs.CL↗
arXiv2025

Automated Glaucoma Report Generation via Dual-Attention Semantic Parallel-LSTM and Multimodal Clinical Data Integration

Generative AI for automated glaucoma diagnostic report generation faces two predominant challenges: content redundancy in narrative outputs and inadequate highlighting of pathologically significant features including optic disc cupping, retinal nerve fiber layer defects, and visual field abnormalities. These limitations primarily stem from current multimodal architectures' insufficient capacity to extract discriminative structural-textural patterns from fundus imaging data while maintaining precise semantic alignment with domain-specific terminology in comprehensive clinical reports. To overcome these constraints, we present the Dual-Attention Semantic Parallel-LSTM Network (DA-SPL), an advanced multimodal generation framework that synergistically processes both fundus imaging and supplementary visual inputs. DA-SPL employs an Encoder-Decoder structure augmented with the novel joint dual-attention mechanism in the encoder for cross-modal feature refinement, the parallelized LSTM decoder architecture for enhanced temporal-semantic consistency, and the specialized label enhancement module for accurate disease-relevant term generation. Rigorous evaluation on standard glaucoma datasets demonstrates DA-SPL's consistent superiority over state-of-the-art models across quantitative metrics. DA-SPL exhibits exceptional capability in extracting subtle pathological indicators from multimodal inputs while generating diagnostically precise reports that exhibit strong concordance with clinical expert annotations.

cs.CE↗
arXiv2025

TLUE: A Tibetan Language Understanding Evaluation Benchmark

Large language models have made tremendous progress in recent years, but low-resource languages, like Tibetan, remain significantly underrepresented in their evaluation. Despite Tibetan being spoken by over seven million people, it has largely been neglected in the development and assessment of large language models. To address this gap, we present a \textbf{T}ibetan \textbf{L}anguage \textbf{U}nderstanding \textbf{E}valuation Benchmark, \textbf{TLUE}, the first large-scale benchmark for measuring the proficiency of LLMs in the Tibetan language. \textbf{TLUE} comprises two major components: a comprehensive multi-task understanding benchmark spanning 5 domains and 67 subdomains, and a safety benchmark encompassing 7 subdomains. Then, we evaluate a diverse set of state-of-the-art large language models. Experimental results demonstrate that most large language models perform below the random baseline, highlighting the considerable challenges they face in Tibetan language processing. \textbf{TLUE} provides a crucial foundation for advancing future research in Tibetan language understanding and highlights the importance of promoting greater inclusivity in the development of large language models.

cs.CL↗