arXiv subjects

Zhirong Huang

Publications and source records attributed to Zhirong Huang.

At least 19 recordsLinked to original sources

arXiv2026

HonestAffinity: Leak-Aware Evaluation of Protein and Pocket Priors for Binding Affinity Prediction

Sequence-based deep learning offers a scalable alternative to structure-based scoring for protein-ligand binding affinity prediction. However, progress is hard to interpret when architectural priors are evaluated on canonical PDBbind-style splits that leak similarity classes across folds. We present HonestAffinity, a compact 1D-input predictor to isolate two priors under a leak-aware protocol: frozen ESM-2 (650M) protein embeddings and a learned binary pocket-position marker. We evaluate a multi-scale convolutional/Transformer template in three variants: HonestAffinity-Pocket, HonestAffinity-NoPocket, and HonestAffinity-Pocket-NoESM. All three train on 11,513 LP-PDBBind complexes in ~3 GPU-hours. We benchmark against five baselines on the LP-PDBBind 3-tier no-leak hold-out, CASF-2016, and a CASF-2016 non-train subset. Our central finding is a split-conditioned reversal rather than a uniformly best prior: HonestAffinity-Pocket achieves the best mean Pearson R on validation and CASF-2016 splits, whereas HonestAffinity-Pocket-NoESM achieves the best mean Pearson R on every strict LP no-leak tier (test_cl1-cl3). Both the pocket marker and ESM-2 input improve performance on familiar splits but reduce Pearson R on strict no-leak tiers. We argue models should report paired canonical and leak-proof ablations, and that deployment-regime-matched variants better describe these reversals than a single default. Code and scripts are linked in the footnote; checkpoints will be released upon acceptance.

cs.CE↗

arXiv2026

Disentangled Instrumental Variables for Causal Inference with Networked Observational Data

Instrumental variables (IVs) are crucial for addressing unobservable confounders, yet their stringent exogeneity assumptions pose significant challenges in networked data. Existing methods typically rely on modelling neighbour information when recovering IVs, thereby inevitably mixing shared environment-induced endogenous correlations and individual-specific exogenous variation, leading the resulting IVs to inherit dependence on unobserved confounders and to violate exogeneity. To overcome this challenge, we propose $\underline{Dis}$entangled $\underline{I}$nstrumental $\underline{V}$ariables (DisIV) framework, a novel method for causal inference based on networked observational data with latent confounders. DisIV exploits network homogeneity as an inductive bias and employs a structural disentanglement mechanism to extract individual-specific components that serve as latent IVs. The causal validity of the extracted IVs is constrained through explicit orthogonality and exclusion conditions. Extensive semi-synthetic experiments on real-world datasets demonstrate that DisIV consistently outperforms state-of-the-art baselines in causal effect estimation under network-induced confounding.

cs.AI↗

arXiv2025

Beam Halo Formation via Longitudinal-Transverse Coupling in Continuous-Wave Photoinjectors

Beam halo formation poses a critical challenge for high-repetition-rate continuous-wave (CW) free-electron lasers (FELs), directly affecting beam quality and machine protection, as observed during the LCLS-II commissioning. We identify and experimentally validate a previously unrecognized three-step mechanism for halo generation in the photoinjector, arising from coupled longitudinal-transverse dynamics in the low-energy beam. Theoretical analysis reveals that (i) the RF buncher induces an energy-radius correlation, (ii) velocity bunching transforms this correlation into hollowed density structures in the bunch head and tail, and (iii) differential overfocusing of these hollowed regions by downstream focusing forms the observed halo. This mechanism is confirmed by particle-in-cell simulations and direct experimental measurements, including controlled formation of a core-ring profile via solenoid tuning. The results establish the physical origin of the halo and demonstrate a mitigation via buncher compression tuning that reduces halo and downstream loss, supporting sustained high-repetition-rate FEL operation.

physics.acc-ph↗

arXiv2025

Three Dimensional Theory of the Ion Channel Laser

The ion channel laser (ICL) is a plasma-based alternative to the free electron laser (FEL) that uses the electric field of a uniform-density ion channel rather than the magnetic field of an undulator to induce transverse oscillations of electrons in an ultrarelativistic bunch and thereby produce coherent radiation via a collective electromagnetic instability. The powerful focusing of the ion channel generally yields significantly higher gain parameters in the ICL as compared to the FEL. This permits lasing in extremely short distances using electron bunches with an energy spread as large as a few percent; a value readily achievable with current plasma-based accelerators. ICLs, however, impose stringent transverse phase space requirements on the electron bunch beyond what is required in FELs. In this work, we present a novel 3D theory of the planar off-axis configuration of the ICL that accounts for a number of effects including diffraction, transverse radiation profile, frequency and betatron phase detuning, and nonzero spread in energy and undulator parameter. We derive the ICL pendulum and field equations, which we use to write down the 3D Maxwell-Klimontovich equations. After linearizing, we obtain an integro-differential equation describing the $z$-evolution of the radiation field. The 3D ICL dispersion relation is obtained using a Van Kampen normal mode expansion. We numerically solve the $z$-evolution equation to compute radiation power growth rates and transverse radiation profiles over a range of different ICL parameters. We examine the gain reduction due to 3D effects, energy spread, and emittance. Electron bunch phase space and emittance requirements for lasing are derived. Finally, we make general observations about the performance and feasibility of the ICL and discuss future prospects.

physics.acc-ph↗

arXiv2025

Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems

It is often challenging to identify a valid instrumental variable (IV), although the IV methods have been regarded as effective tools of addressing the confounding bias introduced by latent variables. To deal with this issue, an Interaction-Data-guided Conditional IV (IDCIV) debiasing method is proposed for Recommender Systems, called IDCIV-RS. The IDCIV-RS automatically generates the representations of valid CIVs and their corresponding conditioning sets directly from interaction data, significantly reducing the complexity of IV selection while effectively mitigating the confounding bias caused by latent variables in recommender systems. Specifically, the IDCIV-RS leverages a variational autoencoder (VAE) to learn both the CIV representations and their conditioning sets from interaction data, followed by the application of least squares to derive causal representations for click prediction. Extensive experiments on two real-world datasets, Movielens-10M and Douban-Movie, demonstrate that IDCIV-RS successfully learns the representations of valid CIVs, effectively reduces bias, and consequently improves recommendation accuracy.

cs.IR↗

arXiv2025

SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection

With the increasing security issues in blockchain, smart contract vulnerability detection has become a research focus. Existing vulnerability detection methods have their limitations: 1) Static analysis methods struggle with complex scenarios. 2) Methods based on specialized pre-trained models perform well on specific datasets but have limited generalization capabilities. In contrast, general-purpose Large Language Models (LLMs) demonstrate impressive ability in adapting to new vulnerability patterns. However, they often underperform on specific vulnerability types compared to methods based on specialized pre-trained models. We also observe that explanations generated by general-purpose LLMs can provide fine-grained code understanding information, contributing to improved detection performance. Inspired by these observations, we propose SAEL, an LLM-based framework for smart contract vulnerability detection. We first design targeted prompts to guide LLMs in identifying vulnerabilities and generating explanations, which serve as prediction features. Next, we apply prompt-tuning on CodeT5 and T5 to process contract code and explanations, enhancing task-specific performance. To combine the strengths of each approach, we introduce an Adaptive Mixture-of-Experts architecture. This dynamically adjusts feature weights via a Gating Network, which selects relevant features using TopK filtering and Softmax normalization, and incorporates a Multi-Head Self-Attention mechanism to enhance cross-feature relationships. This design enables effective integration of LLM predictions, explanation features, and code features through gradient optimization. The loss function jointly considers both independent feature performance and overall weighted predictions. Experiments show that SAEL outperforms existing methods across various vulnerabilities.

cs.CR↗

arXiv2025

Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection

Smart contract vulnerability detection remains a major challenge in blockchain security. Existing vulnerability detection methods face two main issues: (1) Existing datasets lack comprehensive coverage and high-quality explanations for preference learning. (2) Large language models (LLMs) often struggle with accurately interpreting specific concepts in smart contract security. Empirical analysis shows that even after continual pre-training (CPT) and supervised fine-tuning (SFT), LLMs may misinterpret the execution order of state changes, resulting in incorrect explanations despite making correct detection decisions. To address these challenges, we propose Smart-LLaMA-DPO based on LLaMA-3.1-8B. We construct a comprehensive dataset covering four major vulnerability types and machine-unauditable vulnerabilities, including precise labels, explanations, and locations for SFT, as well as high-quality and low-quality output pairs for Direct Preference Optimization (DPO). Second, we perform CPT using large-scale smart contract to enhance the LLM's understanding of specific security practices in smart contracts. Futhermore, we conduct SFT with our comprehensive dataset. Finally, we apply DPO, leveraging human feedback and a specially designed loss function that increases the probability of preferred explanations while reducing the likelihood of non-preferred outputs. We evaluate Smart-LLaMA-DPO on four major vulnerability types: reentrancy, timestamp dependence, integer overflow/underflow, and delegatecall, as well as machine-unauditable vulnerabilities. Our method significantly outperforms state-of-the-art baselines, with average improvements of 10.43% in F1 score and 7.87% in accuracy. Moreover, both LLM evaluation and human evaluation confirm that our method generates more correct, thorough, and clear explanations.

cs.CR↗

arXiv2025

MOS: Towards Effective Smart Contract Vulnerability Detection through Mixture-of-Experts Tuning of Large Language Models

Smart contract vulnerabilities pose significant security risks to blockchain systems, potentially leading to severe financial losses. Existing methods face several limitations: (1) Program analysis-based approaches rely on predefined patterns, lacking flexibility for new vulnerability types; (2) Deep learning-based methods lack explanations; (3) Large language model-based approaches suffer from high false positives. We propose MOS, a smart contract vulnerability detection framework based on mixture-of-experts tuning (MOE-Tuning) of large language models. First, we conduct continual pre-training on a large-scale smart contract dataset to provide domain-enhanced initialization. Second, we construct a high-quality MOE-Tuning dataset through a multi-stage pipeline combining LLM generation and expert verification for reliable explanations. Third, we design a vulnerability-aware routing mechanism that activates the most relevant expert networks by analyzing code features and their matching degree with experts. Finally, we extend the feed-forward layers into multiple parallel expert networks, each specializing in specific vulnerability patterns. We employ a dual-objective loss function: one for optimizing detection and explanation performance, and another for ensuring reasonable distribution of vulnerability types to experts through entropy calculation. Experiments show that MOS significantly outperforms existing methods with average improvements of 6.32% in F1 score and 4.80% in accuracy. The vulnerability explanations achieve positive ratings (scores of 3-4 on a 4-point scale) of 82.96%, 85.21% and 94.58% for correctness, completeness, and conciseness through human and LLM evaluation.

cs.SE↗

arXiv2025

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

The task of issue resolving is to modify a codebase to generate a patch that addresses a given issue. However, existing benchmarks, such as SWE-bench, focus almost exclusively on Python, making them insufficient for evaluating Large Language Models (LLMs) across diverse software ecosystems. To address this, we introduce a multilingual issue-resolving benchmark, called Multi-SWE-bench, covering Java, TypeScript, JavaScript, Go, Rust, C, and C++. It includes a total of 1,632 high-quality instances, which were carefully annotated from 2,456 candidates by 68 expert annotators, ensuring that the benchmark can provide an accurate and reliable evaluation. Based on Multi-SWE-bench, we evaluate a series of state-of-the-art models using three representative methods (Agentless, SWE-agent, and OpenHands) and present a comprehensive analysis with key empirical insights. In addition, we launch a Multi-SWE-RL open-source community, aimed at building large-scale reinforcement learning (RL) training datasets for issue-resolving tasks. As an initial contribution, we release a set of 4,723 well-structured instances spanning seven programming languages, laying a solid foundation for RL research in this domain. More importantly, we open-source our entire data production pipeline, along with detailed tutorials, encouraging the open-source community to continuously contribute and expand the dataset. We envision our Multi-SWE-bench and the ever-growing Multi-SWE-RL community as catalysts for advancing RL toward its full potential, bringing us one step closer to the dawn of AGI.

cs.SE↗

arXiv2025

Near-Infrared noise in intense electron bunches

This article investigates electron bunch density fluctuations in the 1 - 10 $μm$ wavelength range, focusing on their impact on coherent electron cooling (CEC) in hadron storage rings. In this study, we thoroughly compare the shot-noise model with experimental observations of optical transition radiation (OTR) generated by a relativistic electron bunch ($γ\approx$ 50), transiting an Aluminium metal surface. The bunch parameters are close to those proposed for a stage in an Electron-Ion Collider (EIC), where the bunch size is much larger than the OTR wavelength being measured. Here we present measurements and particle tracking results of both the low-level noise for the EIC bunch parameters and longitudinal space-charge-induced microbunching for the chicane-compressed bunch with coherent OTR enhancements up to 100 times in the various bandwidth-filtered near-infrared (NIR) OTR photodiode signals. We also discuss the corresponding limitations of the OTR method.

physics.acc-ph↗

arXiv2024

CodeV: Issue Resolving with Visual Data

Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks. GitHub issue resolving is a key challenge among these tasks. While recent approaches have made progress on this task, they focus on textual data within issues, neglecting visual data. However, this visual data is crucial for resolving issues as it conveys additional knowledge that text alone cannot. We propose CodeV, the first approach to leveraging visual data to enhance the issue-resolving capabilities of LLMs. CodeV resolves each issue by following a two-phase process: data processing and patch generation. To evaluate CodeV, we construct a benchmark for visual issue resolving, namely Visual SWE-bench. Through extensive experiments, we demonstrate the effectiveness of CodeV, as well as provide valuable insights into leveraging visual data to resolve GitHub issues.

cs.SE↗

arXiv2024

Smart-LLaMA: Two-Stage Post-Training of Large Language Models for Smart Contract Vulnerability Detection and Explanation

With the rapid development of blockchain technology, smart contract security has become a critical challenge. Existing smart contract vulnerability detection methods face three main issues: (1) Insufficient quality of datasets, lacking detailed explanations and precise vulnerability locations. (2) Limited adaptability of large language models (LLMs) to the smart contract domain, as most LLMs are pre-trained on general text data but minimal smart contract-specific data. (3) Lack of high-quality explanations for detected vulnerabilities, as existing methods focus solely on detection without clear explanations. These limitations hinder detection performance and make it harder for developers to understand and fix vulnerabilities quickly, potentially leading to severe financial losses. To address these problems, we propose Smart-LLaMA, an advanced detection method based on the LLaMA language model. First, we construct a comprehensive dataset covering four vulnerability types with labels, detailed explanations, and precise vulnerability locations. Second, we introduce Smart Contract-Specific Continual Pre-Training, using raw smart contract data to enable the LLM to learn smart contract syntax and semantics, enhancing their domain adaptability. Furthermore, we propose Explanation-Guided Fine-Tuning, which fine-tunes the LLM using paired vulnerable code and explanations, enabling both vulnerability detection and reasoned explanations. We evaluate explanation quality through LLM and human evaluation, focusing on Correctness, Completeness, and Conciseness. Experimental results show that Smart-LLaMA outperforms state-of-the-art baselines, with average improvements of 6.49% in F1 score and 3.78% in accuracy, while providing reliable explanations.

cs.CR↗

arXiv2024

Multi-Cause Deconfounding for Recommender Systems with Latent Confounders

In recommender systems, various latent confounding factors (e.g., user social environment and item public attractiveness) can affect user behavior, item exposure, and feedback in distinct ways. These factors may directly or indirectly impact user feedback and are often shared across items or users, making them multi-cause latent confounders. However, existing methods typically fail to account for latent confounders between users and their feedback, as well as those between items and user feedback simultaneously. To address the problem of multi-cause latent confounders, we propose a multi-cause deconfounding method for recommender systems with latent confounders (MCDCF). MCDCF leverages multi-cause causal effect estimation to learn substitutes for latent confounders associated with both users and items, using user behaviour data. Specifically, MCDCF treats the multiple items that users interact with and the multiple users that interact with items as treatment variables, enabling it to learn substitutes for the latent confounders that influence the estimation of causality between users and their feedback, as well as between items and user feedback. Additionally, we theoretically demonstrate the soundness of our MCDCF method. Extensive experiments on three real-world datasets demonstrate that our MCDCF method effectively recovers latent confounders related to users and items, reducing bias and thereby improving recommendation accuracy.

cs.IR↗

arXiv2024

SWE-bench-java: A GitHub Issue Resolving Benchmark for Java

GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia. Within this task, SWE-bench has been released to evaluate issue resolving capabilities of large language models (LLMs), but has so far only focused on Python version. However, supporting more programming languages is also important, as there is a strong demand in industry. As a first step toward multilingual support, we have developed a Java version of SWE-bench, called SWE-bench-java. We have publicly released the dataset, along with the corresponding Docker-based evaluation environment and leaderboard, which will be continuously maintained and updated in the coming months. To verify the reliability of SWE-bench-java, we implement a classic method SWE-agent and test several powerful LLMs on it. As is well known, developing a high-quality multi-lingual benchmark is time-consuming and labor-intensive, so we welcome contributions through pull requests or collaboration to accelerate its iteration and refinement, paving the way for fully automated programming.

cs.SE↗

arXiv2024

Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems

In recommender systems, popularity and conformity biases undermine recommender effectiveness by disproportionately favouring popular items, leading to their over-representation in recommendation lists and causing an unbalanced distribution of user-item historical data. We construct a causal graph to address both biases and describe the abstract data generation mechanism. Then, we use it as a guide to develop a novel Debiased Contrastive Learning framework for Mitigating Dual Biases, called DCLMDB. In DCLMDB, both popularity bias and conformity bias are handled in the model training process by contrastive learning to ensure that user choices and recommended items are not unduly influenced by conformity and popularity. Extensive experiments on two real-world datasets, Movielens-10M and Netflix, show that DCLMDB can effectively reduce the dual biases, as well as significantly enhance the accuracy and diversity of recommendations.

cs.IR↗

arXiv2024

Dynamic motion trajectory control with nanoradian accuracy for multi-element X-ray optical systems via laser interferometry

The past decades have witnessed the development of new X-ray beam sources with brightness growing at a rate surpassing Moore's law. Current and upcoming diffraction limited and fully coherent X-ray beam sources, including multi-bend achromat based synchrotron sources and high repetition rate X-ray free electron lasers, puts increasingly stringent requirements on stability and accuracy of X-ray optics systems. Parasitic motion errors at sub-micro radian scale in beam transport and beam conditioning optics can lead to significant loss of coherence and brightness delivered from source to experiment. To address this challenge, we incorporated optical metrology based on interferometry and differential wavefront sensing as part of the X-ray optics motion control system. A prototype X-ray optics system was constructed following the optical layout of a tunable X-ray cavity. On-line interferometric metrology enabled dynamical feedback to a motion control system to track and compensate for motion errors. The system achieved sub-microradian scale performance, as multiple optical elements are synchronously and continuously adjusted. This first proof of principle measurement demonstrated both the potential and necessity of incorporating optical metrology as part of the motion control architecture for large scale X-ray optical systems such as monochromators, delay lines, and in particular, X-ray cavity systems to enable the next generation cavity-based X-ray free electron lasers.

physics.optics↗

arXiv2024

Experimental Demonstration of Attosecond Pump-Probe Spectroscopy with an X-ray Free-Electron Laser

Pump-probe experiments with sub-femtosecond resolution are the key to understanding electronic dynamics in quantum systems. Here we demonstrate the generation and control of sub-femtosecond pulse pairs from a two-colour X-ray free-electron laser (XFEL). By measuring the delay between the two pulses with an angular streaking diagnostic, we characterise the group velocity of the XFEL and demonstrate control of the pulse delay down to 270 as. We demonstrate the application of this technique to a pump-probe measurement in core-excited para-aminophenol. These results demonstrate the ability to perform pump-probe experiments with sub-femtosecond resolution and atomic site specificity.

physics.acc-ph↗

arXiv2023

Fast modeling of regenerative amplifier free-electron lasers

High-gain free-electron lasers (FELs) are becoming important light sources at short wavelengths such as the EUV and X-ray regimes. A particularly promising concept is the regenerative amplifier FEL (RAFEL), which can greatly increase the brightness and stability of a single pass device. One of the critical challenges of the x-ray RAFEL is maintaining electron-optical overlap over the relatively large (hundreds of meters) footprint of the system. Numerical modeling of x-ray RAFELs with angular and positional errors is critical for designing stable cavities, as well as to predict signatures of specific misalignment effects. Full-scale simulations of x-ray FELs are incredibly time-consuming, making large-scale parameter searches intractable on reasonable timescales. In this paper, we present a semi-analytical model that allows to investigate realistic scenarios - x-ray cavity without gain ("cold cavity" or x-ray FEL oscillator) and x-ray RAFEL - in the presence of angular/positional errors and electron trajectory oscillation. We especially focus on fast modeling of the FEL process and x-ray optics, while capturing effects pertaining to actual experimental setups at the Linac Coherent Light Source (LCLS) at SLAC. Such a method can be used to explore RAFEL at other wavelengths by suitable replacement of the optics modeling.

physics.acc-ph↗