arXiv subjects

Haining Wang

Publications and source records attributed to Haining Wang.

At least 19 recordsLinked to original sources

arXiv2026

On optimal $p$-adic uniformization of unitary Shimura curves

The paper is a continuation of the paper of Kudla-Rapoport-Zink on $p$-adic uniformization of Shimura curves associated to a group of binary unitary similitudes. Here we consider two variants: first, the RSZ variant, for which we can allow any level which is maximal at the chosen special $p$-adic place where the group is anisotropic; second, the unitary group variant. The latter is based on an explicit determination of the integral local Shimura variety associated to an anisotropic unitary group over a $p$-adic local field.

math.NT↗

arXiv2026

Feedback-Driven Execution for LLM-Based Binary Analysis

Binary analysis increasingly relies on large language models (LLMs) to perform semantic reasoning over complex program behaviors. However, existing approaches largely adopt a one-pass execution paradigm, where reasoning operates over a fixed program representation constructed by static analysis tools. This formulation limits the ability to adapt exploration based on intermediate results and makes it difficult to sustain long-horizon, multi-path analysis under constrained context. We present FORGE, a system that rethinks LLM-based analysis as a feedback-driven execution process. FORGE interleaves reasoning and tool interaction through a reasoning-action-observation loop, enabling incremental exploration and evidence construction. To address the instability of long-horizon reasoning, we introduce a Dynamic Forest of Agents (FoA), a decomposed execution model that dynamically coordinates parallel exploration while bounding per-agent context. We evaluate FORGE on 3,457 real-world firmware binaries. FORGE identifies 1,274 vulnerabilities across 591 unique binaries, achieving 72.3% precision while covering a broader range of vulnerability types than prior approaches. These results demonstrate that structuring LLM-based analysis as a decomposed, feedback-driven execution system enables both scalable reasoning and high-quality outcomes in long-horizon tasks.

cs.CR↗

arXiv2026

Learning Low-Dimensional Representation for O-RAN Testing via Transformer-ESN

Open Radio Access Network (O-RAN) architectures enhance flexibility for 6G and NextG networks. However, it also brings significant challenges in O-RAN testing with evaluating abundant, high-dimensional key performance indicators (KPIs). In this paper, we introduce a novel two-stage framework to learn temporally-aware low-dimensional representations of O-RAN testing KPIs. To be specific, stage one employs an information-theoretic H-score to train a hybrid self-attentive transformer and echo state network (ESN) reservoir, called Transformer-ESN, capturing temporal dynamics and producing task-aligned $8$-dimensional embeddings. Stage two evaluates these embeddings by training a lightweight multilayer perceptron (MLP) predictor exclusively on them for key target KPIs such as reference signal received quality (RSRQ) and spectral efficiency. Using real-world O-RAN testbed data (video streaming with interference), our approach demonstrates a significant advantage specifically when training samples are very limited. In this scenario, the low-dimensional representations learned from the Transformer-ESN yield mean square error (MSE) reductions of up to 41.9\% for RSRQ and 29.9\% for spectral efficiency compared to predictions from the original high-dimensional data. The framework exhibits high efficiency for O-RAN testing, significantly reducing testing complexities for O-RAN systems.

eess.SP↗

arXiv2026

Implicit Patterns in LLM-Based Binary Analysis

Binary vulnerability analysis is increasingly performed by LLM-based agents in an iterative, multi-pass manner, with the model as the core decision-maker. However, how such systems organize exploration over hundreds of reasoning steps remains poorly understood, due to limited context windows and implicit token-level behaviors. We present the first large-scale, trace-level study showing that multi-pass LLM reasoning gives rise to structured, token-level implicit patterns. Analyzing 521 binaries with 99,563 reasoning steps, we identify four dominant patterns: early pruning, path-dependent lock-in, targeted backtracking, and knowledge-guided prioritization that emerge implicitly from reasoning traces. These token-level implicit patterns serve as an abstraction of LLM reasoning: instead of explicit control-flow or predefined heuristics, exploration is organized through implicit decisions regulating path selection, commitment, and revision. Our analysis shows these patterns form a stable, structured system with distinct temporal roles and measurable characteristics. Our results provide the first systematic characterization of LLM-driven binary analysis and a foundation for more reliable analysis systems.

cs.AI↗

arXiv2026

Responsible Intelligence in Practice: A Fairness Audit of Open Large Language Models for Library Reference Services

As libraries explore large language models (LLMs) as a scalable layer for reference services, a core fairness question follows: can LLM-based services support all patrons fairly, regardless of demographic identity? While LLMs offer great potential for broadening access to information assistance, they may also reproduce societal biases embedded in their training data, potentially undermining libraries' commitments to impartial service. In this chapter, we apply a systematic evaluation approach that combines diagnostic classification to detect systematic differences with linguistic analysis to interpret their sources. Across three widely used open models (Llama-3.1 8B, Gemma-2 9B, and Ministral 8B), we find no compelling evidence of systematic differentiation by race/ethnicity, and only minor evidence of sex-linked differentiation in one model. We discuss implications for responsible AI adoption in libraries and the importance of ongoing monitoring in aligning LLM-based services with core professional values.

cs.DL↗

arXiv2025

Demystifying Feature Engineering in Malware Analysis of API Call Sequences

Machine learning (ML) has been widely used to analyze API call sequences in malware analysis, which typically requires the expertise of domain specialists to extract relevant features from raw data. The extracted features play a critical role in malware analysis. Traditional feature extraction is based on human domain knowledge, while there is a trend of using natural language processing (NLP) for automatic feature extraction. This raises a question: how do we effectively select features for malware analysis based on API call sequences? To answer it, this paper presents a comprehensive study of investigating the impact of feature engineering upon malware classification.We first conducted a comparative performance evaluation under three models, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Transformer, with respect to knowledge-based and NLP-based feature engineering methods. We observed that models with knowledge-based feature engineering inputs generally outperform those using NLP-based across all metrics, especially under smaller sample sizes. Then we analyzed a complete set of data features from API call sequences, our analysis reveals that models often focus on features such as handles and virtual addresses, which vary across executions and are difficult for human analysts to interpret.

cs.CR↗

arXiv2025

LLMs as Firmware Experts: A Runtime-Grown Tree-of-Agents Framework

Large Language Models (LLMs) and their agent systems have recently demonstrated strong potential in automating code reasoning and vulnerability detection. However, when applied to large-scale firmware, their performance degrades due to the binary nature of firmware, complex dependency structures, and heterogeneous components. To address this challenge, this paper presents FIRMHIVE, a recursive agent hive that enables LLMs to act as autonomous firmware security analysts. FIRMHIVE introduces two key mechanisms: (1) transforming delegation into a per-agent, executable primitive and (2) constructing a runtime Tree of Agents (ToA) for decentralized coordination. We evaluate FIRMHIVE using real-world firmware images obtained from publicly available datasets, covering five representative security analysis tasks. Compared with existing LLM-agent baselines, FIRMHIVE performs deeper (about 16x more reasoning steps) and broader (about 2.3x more files inspected) cross-file exploration, resulting in about 5.6x more alerts per firmware. Compared to state-of-the-art (SOTA) security tools, FIRMHIVE identifies about 1.5x more vulnerabilities (1,802 total) and achieves 71% precision, representing significant improvements in both yield and fidelity.

cs.CR↗

arXiv2025

CRSF: Enabling QoS-Aware Beyond-Connectivity Service Sharing in 6G Local Networks

Sixth-generation (6G) networks are envisioned to support interconnected local subnetworks that can share specialized, beyond-connectivity services. However, a standardized architecture for discovering and selecting these services across network boundaries has not existed yet. To address this gap, this paper introduces the Central Repository and Selection Function (CRSF), a novel network function for the 6G core that facilitates efficient inter-subnetwork service discovery and selection. We formulate the selection process as a QoS-aware optimization problem designed to balance service quality metrics with user-defined priorities. We evaluate our system model through simulations for a sensing service scenario and observe a consistently higher aggregate Quality of Service (QoS) compared to the baseline selection strategy. The proposed CRSF provides a foundational and extensible mechanism for building standardized, collaborative, and service-centric interconnected networks essential for the 6G era.

cs.NI↗

arXiv2025

Towards xApp Conflict Evaluation with Explainable Machine Learning and Causal Inference in O-RAN

The Open Radio Access Network (O-RAN) architecture enables a flexible, vendor-neutral deployment of 5G networks by disaggregating base station components and supporting third-party xApps for near real-time RAN control. However, the concurrent operation of multiple xApps can lead to conflicting control actions, which may cause network performance degradation. In this work, we propose a framework for xApp conflict management that combines explainable machine learning and causal inference to evaluate the causal relationships between RAN Control Parameters (RCPs) and Key Performance Indicators (KPIs). We use model explainability tools such as SHAP to identify RCPs that jointly affect the same KPI, signaling potential conflicts, and represent these interactions as a causal Directed Acyclic Graph (DAG). We then estimate the causal impact of each of these RCPs on their associated KPIs using metrics such as Average Treatment Effect (ATE) and Conditional Average Treatment Effect (CATE). This approach offers network operators guided insights into identifying conflicts and quantifying their impacts, enabling more informed and effective conflict resolution strategies across diverse xApp deployments.

cs.NI↗

arXiv2025

Dynamic Vulnerability Patching for Heterogeneous Embedded Systems Using Stack Frame Reconstruction

Existing dynamic vulnerability patching techniques are not well-suited for embedded devices, especially mission-critical ones such as medical equipment, as they have limited computational power and memory but uninterrupted service requirements. Those devices often lack sufficient idle memory for dynamic patching, and the diverse architectures of embedded systems further complicate the creation of patch triggers that are compatible across various system kernels and hardware platforms. To address these challenges, we propose a hot patching framework called StackPatch that facilitates patch development based on stack frame reconstruction. StackPatch introduces different triggering strategies to update programs stored in memory units. We leverage the exception-handling mechanisms commonly available in embedded processors to enhance StackPatch's adaptability across different processor architectures for control flow redirection. We evaluated StackPatch on embedded devices featuring three major microcontroller (MCU) architectures: ARM, RISC-V, and Xtensa. In the experiments, we used StackPatch to successfully fix 102 publicly disclosed vulnerabilities in real-time operating systems (RTOS). We applied patching to medical devices, soft programmable logic controllers (PLCs), and network services, with StackPatch consistently completing each vulnerability remediation in less than 260 MCU clock cycles.

cs.CR↗

arXiv2025

HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment

Despite significant progress in no-reference image quality assessment (NR-IQA), dataset biases and reliance on subjective labels continue to hinder their generalization performance. We propose HiRQA (Hierarchical Ranking and Quality Alignment), a self-supervised, opinion-unaware framework that offers a hierarchical, quality-aware embedding through a combination of ranking and contrastive learning. Unlike prior approaches that depend on pristine references or auxiliary modalities at inference time, HiRQA predicts quality scores using only the input image. We introduce a novel higher-order ranking loss that supervises quality predictions through relational ordering across distortion pairs, along with an embedding distance loss that enforces consistency between feature distances and perceptual differences. A training-time contrastive alignment loss, guided by structured textual prompts, further enhances the learned representation. Trained only on synthetic image distortions, HiRQA generalizes to authentic degradations, as demonstrated through comprehensive evaluations on various unseen distortions such as lens flare, haze, motion blur, and low-light conditions. For real-time deployment, we introduce HiRQA-S, a lightweight variant with an inference time of only 3.5 ms per image. Extensive experiments across synthetic and authentic benchmarks validate HiRQA's competitive performance, strong generalization ability, and scalability. The HiRQA model and inference pipeline are available at: https://github.com/uf-robopi/HiRQA.

cs.CV↗

arXiv2025

Fairness Evaluation of Large Language Models in Academic Library Reference Services

As libraries explore large language models (LLMs) for use in virtual reference services, a key question arises: Can LLMs serve all users equitably, regardless of demographics or social status? While they offer great potential for scalable support, LLMs may also reproduce societal biases embedded in their training data, risking the integrity of libraries' commitment to equitable service. To address this concern, we evaluate whether LLMs differentiate responses across user identities by prompting six state-of-the-art LLMs to assist patrons differing in sex, race/ethnicity, and institutional role. We find no evidence of differentiation by race or ethnicity, and only minor evidence of stereotypical bias against women in one model. LLMs demonstrate nuanced accommodation of institutional roles through the use of linguistic choices related to formality, politeness, and domain-specific vocabularies, reflecting professional norms rather than discriminatory treatment. These findings suggest that current LLMs show a promising degree of readiness to support equitable and contextually appropriate communication in academic library reference services.

cs.CL↗

arXiv2025

DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning

Previous multimodal sentence representation learning methods have achieved impressive performance. However, most approaches focus on aligning images and text at a coarse level, facing two critical challenges:cross-modal misalignment bias and intra-modal semantic divergence, which significantly degrade sentence representation quality. To address these challenges, we propose DALR (Dual-level Alignment Learning for Multimodal Sentence Representation). For cross-modal alignment, we propose a consistency learning module that softens negative samples and utilizes semantic similarity from an auxiliary task to achieve fine-grained cross-modal alignment. Additionally, we contend that sentence relationships go beyond binary positive-negative labels, exhibiting a more intricate ranking structure. To better capture these relationships and enhance representation quality, we integrate ranking distillation with global intra-modal alignment learning. Comprehensive experiments on semantic textual similarity (STS) and transfer (TR) tasks validate the effectiveness of our approach, consistently demonstrating its superiority over state-of-the-art baselines.

cs.CL↗

arXiv2025

Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of Flows

Simulation of fluid flows is crucial for modeling physical phenomena like meteorology, aerodynamics, and biomedicine. Classical numerical solvers often require fine spatiotemporal grids to satisfy stability, consistency, and convergence conditions, leading to substantial computational costs. Although machine learning has demonstrated better efficiency, they typically suffer from issues of interpretability, generalizability, and data dependency. Hence, we propose a learnable and differentiable finite volume solver, called LDSolver, designed for efficient and accurate simulation of fluid flows on spatiotemporal coarse grids. LDSolver comprises two key components: (1) a differentiable finite volume solver, and (2) an learnable module providing equivalent approximation for fluxes (derivatives and interpolations), and temporal error correction on coarse grids. Even with limited training data (e.g., only a few trajectories), our model could accelerate the simulation while maintaining a high accuracy with superior generalizability. Experiments on different flow systems (e.g., Burgers, decaying, forced and shear flows) show that LDSolver achieves state-of-the-art performance, surpassing baseline models with notable margins.

cs.LG↗

arXiv2025

SlotPi: Physics-informed Object-centric Reasoning Models

Understanding and reasoning about dynamics governed by physical laws through visual observation, akin to human capabilities in the real world, poses significant challenges. Currently, object-centric dynamic simulation methods, which emulate human behavior, have achieved notable progress but overlook two critical aspects: 1) the integration of physical knowledge into models. Humans gain physical insights by observing the world and apply this knowledge to accurately reason about various dynamic scenarios; 2) the validation of model adaptability across diverse scenarios. Real-world dynamics, especially those involving fluids and objects, demand models that not only capture object interactions but also simulate fluid flow characteristics. To address these gaps, we introduce SlotPi, a slot-based physics-informed object-centric reasoning model. SlotPi integrates a physical module based on Hamiltonian principles with a spatio-temporal prediction module for dynamic forecasting. Our experiments highlight the model's strengths in tasks such as prediction and Visual Question Answering (VQA) on benchmark and fluid datasets. Furthermore, we have created a real-world dataset encompassing object interactions, fluid dynamics, and fluid-object interactions, on which we validated our model's capabilities. The model's robust performance across all datasets underscores its strong adaptability, laying a foundation for developing more advanced world models.

cs.CV↗

arXiv2025

DGIQA: Depth-guided Feature Attention and Refinement for Generalizable Image Quality Assessment

A long-held challenge in no-reference image quality assessment (NR-IQA) learning from human subjective perception is the lack of objective generalization to unseen natural distortions. To address this, we integrate a novel Depth-Guided cross-attention and refinement (Depth-CAR) mechanism, which distills scene depth and spatial features into a structure-aware representation for improved NR-IQA. This brings in the knowledge of object saliency and relative contrast of the scene for more discriminative feature learning. Additionally, we introduce the idea of TCB (Transformer-CNN Bridge) to fuse high-level global contextual dependencies from a transformer backbone with local spatial features captured by a set of hierarchical CNN (convolutional neural network) layers. We implement TCB and Depth-CAR as multimodal attention-based projection functions to select the most informative features, which also improve training time and inference efficiency. Experimental results demonstrate that our proposed DGIQA model achieves state-of-the-art (SOTA) performance on both synthetic and authentic benchmark datasets. More importantly, DGIQA outperforms SOTA models on cross-dataset evaluations as well as in assessing natural image distortions such as low-light effects, hazy conditions, and lens flares.

cs.CV↗

arXiv2024

Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning

A vast amount of scholarly work is published daily, yet much of it remains inaccessible to the general public due to dense jargon and complex language. To address this challenge in science communication, we introduce a reinforcement learning framework that fine-tunes a language model to rewrite scholarly abstracts into more comprehensible versions. Guided by a carefully balanced combination of word- and sentence-level accessibility rewards, our language model effectively substitutes technical terms with more accessible alternatives, a task which models supervised fine-tuned or guided by conventional readability measures struggle to accomplish. Our best model adjusts the readability level of scholarly abstracts by approximately six U.S. grade levels -- in other words, from a postgraduate to a high school level. This translates to roughly a 90% relative boost over the supervised fine-tuning baseline, all while maintaining factual accuracy and high-quality language. An in-depth analysis of our approach shows that balanced rewards lead to systematic modifications in the base model, likely contributing to smoother optimization and superior performance. We envision this work as a step toward bridging the gap between scholarly research and the general public, particularly younger readers and those without a college degree.

cs.CL↗

arXiv2024

Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistance

As large language models (LLMs) become increasingly integral to the hospitality and tourism industry, concerns about their fairness in serving diverse identity groups persist. Grounded in social identity theory and sociotechnical systems theory, this study examines ethnic and gender biases in travel recommendations generated by LLMs. Using fairness probing, we analyze outputs from three leading open-source LLMs. The results show that test accuracy for both ethnicity and gender classifiers exceed random chance. Analysis of the most influential features reveals the presence of stereotype bias in LLM-generated recommendations. We also found hallucinations among these features, occurring more frequently in recommendations for minority groups. These findings indicate that LLMs exhibit ethnic and gender bias when functioning as travel planning assistants. This study underscores the need for bias mitigation strategies to improve the inclusivity and reliability of generative AI-driven travel planning assistance.

cs.AI↗