Search

Symbolic Regression (SR) holds great potential for uncovering underlying mathematical and physical relationships from observed data. However, the vast combinatorial space of possible expressions poses significant challenges for both online search methods and pre-trained transformer models. Additionally, current state-of-the-art approaches typically do not consider the integration of domain experts' prior knowledge and do not support iterative interactions with the model during the equation discovery process. To address these challenges, we propose the Symbolic Q-network (Sym-Q), an advanced interactive framework for large-scale symbolic regression. Unlike previous large-scale transformer-based SR approaches, Sym-Q leverages reinforcement learning without relying on a transformer-based decoder. This formulation allows the agent to learn through offline reinforcement learning using any type of tree encoder, enabling more efficient training and inference. Furthermore, we propose a co-design mechanism, where the reinforcement learning-based Sym-Q facilitates effective interaction with domain experts at any stage of the equation discovery process. Users can dynamically modify generated nodes of the expression, collaborating with the agent to tailor the mathematical expression to best fit the problem and align with the assumed physical laws, particularly when there is prior partial knowledge of the expected behavior. Our experiments demonstrate that the pre-trained Sym-Q surpasses existing SR algorithms on the challenging SSDNC benchmark. Moreover, we experimentally show on real-world cases that its performance can be further enhanced by the interactive co-design mechanism, with Sym-Q achieving greater performance gains than other state-of-the-art models. Our reproducible code is available at https://github.com/EPFL-IMOS/Sym-Q., Comment: This work should not be a new submission but instead should be an update to my existing article, arXiv:2402.05306

Creating data reports is time-consuming, as it requires iterative exploration and understanding of data, followed by summarizing the insights. While large language models (LLMs) are powerful tools for data processing and text generation, they often struggle to produce complete data reports that fully meet user expectations. One significant challenge is effectively communicating the entire analysis logic to LLMs. Moreover, determining a comprehensive analysis logic can be mentally taxing for users. To address these challenges, we propose ReSpark, an LLM-based method that leverages existing data reports as references for creating new ones. Given a data table, ReSpark searches for similar-topic reports, parses them into interdependent segments corresponding to analytical objectives, and executes them with new data. It identifies inconsistencies and customizes the objectives, data transformations, and textual descriptions. ReSpark allows users to review real-time outputs, insert new objectives, and modify report content. Its effectiveness was evaluated through comparative and user studies.

Exploratory Data Analysis (EDA) is a routine task for data analysts, often conducted using flexible computational notebooks. During EDA, data workers process, visualize, and interpret data tables, making decisions about subsequent analysis. However, the cell-by-cell programming approach, while flexible, can lead to disorganized code, making it difficult to trace the state of data tables across cells and increasing the cognitive load on data workers. This paper introduces NoteFlow, a notebook library that recommends charts as ``sight glasses'' for data tables, allowing users to monitor their dynamic updates throughout the EDA process. To ensure visual consistency and effectiveness, NoteFlow adapts chart encodings in response to data transformations, maintaining a coherent and insightful representation of the data. The proposed method was evaluated through user studies, demonstrating its ability to provide an overview of the EDA process and convey critical insights in the data tables.

The sustainability of libraries is critical for modern software development, yet many libraries face abandonment, posing significant risks to dependent projects. This study explores the prevalence and patterns of library abandonment in the Maven ecosystem. We investigate abandonment trends over the past decade, revealing that approximately one in four libraries fail to survive beyond their creation year. We also analyze the release activities of libraries, focusing on their lifespan and release speed, and analyze the evolution of these metrics within the lifespan of libraries. We find that while slow release speed and relatively long periods of inactivity are often precursors to abandonment, some abandoned libraries exhibit bursts of high frequent release activity late in their life cycle. Our findings contribute to a new understanding of library abandonment dynamics and offer insights for practitioners to identify and mitigate risks in software ecosystems.

The increasing prevalence of software vulnerabilities necessitates automated vulnerability repair (AVR) techniques. This Systematization of Knowledge (SoK) provides a comprehensive overview of the AVR landscape, encompassing both synthetic and real-world vulnerabilities. Through a systematic literature review and quantitative benchmarking across diverse datasets, methods, and strategies, we establish a taxonomy of existing AVR methodologies, categorizing them into template-guided, search-based, constraint-based, and learning-driven approaches. We evaluate the strengths and limitations of these approaches, highlighting common challenges and practical implications. Our comprehensive analysis of existing AVR methods reveals a diverse landscape with no single ``best'' approach. Learning-based methods excel in specific scenarios but lack complete program understanding, and both learning and non-learning methods face challenges with complex vulnerabilities. Additionally, we identify emerging trends and propose future research directions to advance the field of AVR. This SoK serves as a valuable resource for researchers and practitioners, offering a structured understanding of the current state-of-the-art and guiding future research and development in this critical domain.

Pulmonary nodules are an early sign of lung cancer, and detecting them early is vital for improving patient survival rates. Most current methods use only single Computed Tomography (CT) images to assess nodule malignancy. However, doctors typically make a comprehensive assessment in clinical practice by integrating follow-up CT scans with clinical data. To enhance this process, our study introduces a Cross-Modal Spatiotemporal Fusion Network, named CSF-Net, designed to predict the malignancy of pulmonary nodules using follow-up CT scans. This approach simulates the decision-making process of clinicians who combine follow-up imaging with clinical information. CSF-Net comprises three key components: spatial feature extraction module, temporal residual fusion module, and cross-modal attention fusion module. Together, these modules enable precise predictions of nodule malignancy. Additionally, we utilized the publicly available NLST dataset to screen and annotate the specific locations of pulmonary nodules and created a new dataset named NLST-cmst. Our experimental results on the NLST-cmst dataset demonstrate significant performance improvements, with an accuracy of 0.8974, a precision of 0.8235, an F1 score of 0.8750, an AUC of 0.9389, and a recall of 0.9333. These findings indicate that our multimodal spatiotemporal fusion approach, which combines follow-up data with clinical information, surpasses existing methods, underscoring its effectiveness in predicting nodule malignancy., Comment: This paper has been accepted by the 2025 IEEE International Symposium on Biomedical Imaging

Self-Admitted Technical Debt (SATD), cases where developers intentionally acknowledge suboptimal solutions in code through comments, poses a significant challenge to software maintainability. Left unresolved, SATD can degrade code quality and increase maintenance costs. While Large Language Models (LLMs) have shown promise in tasks like code generation and program repair, their potential in automated SATD repayment remains underexplored. In this paper, we identify three key challenges in training and evaluating LLMs for SATD repayment: (1) dataset representativeness and scalability, (2) removal of irrelevant SATD repayments, and (3) limitations of existing evaluation metrics. To address the first two dataset-related challenges, we adopt a language-independent SATD tracing tool and design a 10-step filtering pipeline to extract SATD repayments from repositories, resulting two large-scale datasets: 58,722 items for Python and 97,347 items for Java. To improve evaluation, we introduce two diff-based metrics, BLEU-diff and CrystalBLEU-diff, which measure code changes rather than whole code. Additionally, we propose another new metric, LEMOD, which is both interpretable and informative. Using our new benchmarks and evaluation metrics, we evaluate two types of automated SATD repayment methods: fine-tuning smaller models, and prompt engineering with five large-scale models. Our results reveal that fine-tuned small models achieve comparable Exact Match (EM) scores to prompt-based approaches but underperform on BLEU-based metrics and LEMOD. Notably, Gemma-2-9B leads in EM, addressing 10.1% of Python and 8.1% of Java SATDs, while Llama-3.1-70B-Instruct and GPT-4o-mini excel on BLEU-diff, CrystalBLEU-diff, and LEMOD metrics. Our work contributes a robust benchmark, improved evaluation metrics, and a comprehensive evaluation of LLMs, advancing research on automated SATD repayment., Comment: This is a preprint submitted to ACM Transactions on Software Engineering and Methodology (TOSEM)

Local chemical ordering plays an important role in the behavior of complex concentrated alloys, yet its characterization remains challenging due to the nanoscale dimensions and scattered spatial distribution of the ordered domains. This study explores the potential of grain boundaries as microstructural anchor points that amplify chemical ordering and enable the formation of compositional nanopatterns in CrCoNi. Using hybrid Monte Carlo/molecular dynamics simulations, we reveal the development of distinct compositional waves with ordering vectors normal to grain boundaries, extending to lengths greater than 6 nm. These waves manifest as periodic enrichment and depletion patterns, with strong Ni depletion near the Ni-segregated grain boundary accompanied by Co and Cr enrichment. Analogous to surface-driven phase separation, the concentration waves emanating from the boundaries gradually attenuate as they propagate into the grain interior. This behavior highlights the interplay between boundary-dictated directional ordering and the isotropic, untemplated domain growth within the grain. This work advances our fundamental understanding of grain boundary-mediated ordering phenomena and offers a pathway for more precise experimental characterization of local chemical ordering in CCAs.

The ability to automatically encircle boundaries with mobile robots is crucial for tasks such as border tracking and object enclosing. Previous research has primarily focused on regular boundaries, often assuming that their geometric equations are known in advance, which is not often the case in practice. In this paper, we investigate a more general case and propose an algorithm that addresses geometric irregularities of boundaries without requiring prior knowledge of their analytical expressions. To achieve this, we develop a Fourier-based curve fitting method for boundary approximation using sampled points, enabling parametric characterization of general 2-D boundaries. This approach allows star-shaped boundaries to be fitted into polar-angle-based parametric curves, while boundaries of other shapes are handled through decomposition. Then, we design a vector field (VF) to achieve the encirclement of the parameterized boundary, wherein a polar radius error is introduced to measure the robot's ``distance'' to the boundary. The controller is finally synthesized using a control barrier function and quadratic programming to mediate some potentially conflicting specifications: boundary encirclement, obstacle avoidance, and limited actuation. In this manner, the VF-guided reference control not only guides the boundary encircling action, but can also be minimally modified to satisfy obstacle avoidance and input saturation constraints. Simulations and experiments are presented to verify the performance of our new method, which can be applied to mobile robots to perform practical tasks such as cleaning chemical spills and environment monitoring., Comment: 11 pages, submitted to IEEE/ASME Transactions on Mechatronics

Face de-identification (DeID) has been widely studied for common scenes, but remains under-researched for medical scenes, mostly due to the lack of large-scale patient face datasets. In this paper, we release MeMa, consisting of over 40,000 photo-realistic patient faces. MeMa is re-generated from massive real patient photos. By carefully modulating the generation and data-filtering procedures, MeMa avoids breaching real patient privacy, while ensuring rich and plausible medical manifestations. We recruit expert clinicians to annotate MeMa with both coarse- and fine-grained labels, building the first medical-scene DeID benchmark. Additionally, we propose a baseline approach for this new medical-aware DeID task, by integrating data-driven medical semantic priors into the DeID procedure. Despite its conciseness and simplicity, our approach substantially outperforms previous ones. Dataset is available at https://github.com/tianyuan168326/MeMa-Pytorch., Comment: Accepted to AAAI 2025

Recent advancements in long-term time series forecasting (LTSF) have primarily focused on capturing cross-time and cross-variate (channel) dependencies within historical data. However, a critical aspect often overlooked by many existing methods is the explicit incorporation of \textbf{time-related features} (e.g., season, month, day of the week, hour, minute), which are essential components of time series data. The absence of this explicit time-related encoding limits the ability of current models to capture cyclical or seasonal trends and long-term dependencies, especially with limited historical input. To address this gap, we introduce a simple yet highly efficient module designed to encode time-related features, Time Stamp Forecaster (TimeSter), thereby enhancing the backbone's forecasting performance. By integrating TimeSter with a linear backbone, our model, TimeLinear, significantly improves the performance of a single linear projector, reducing MSE by an average of 23\% on benchmark datasets such as Electricity and Traffic. Notably, TimeLinear achieves these gains while maintaining exceptional computational efficiency, delivering results that are on par with or exceed state-of-the-art models, despite using a fraction of the parameters.

Deep learning-based segmentation methods are widely utilized for detecting lesions in ultrasound images. Throughout the imaging procedure, the attenuation and scattering of ultrasound waves cause contour blurring and the formation of artifacts, limiting the clarity of the acquired ultrasound images. To overcome this challenge, we propose a contour-based probabilistic segmentation model CP-UNet, which guides the segmentation network to enhance its focus on contour during decoding. We design a novel down-sampling module to enable the contour probability distribution modeling and encoding stages to acquire global-local features. Furthermore, the Gaussian Mixture Model utilizes optimized features to model the contour distribution, capturing the uncertainty of lesion boundaries. Extensive experiments with several state-of-the-art deep learning segmentation methods on three ultrasound image datasets show that our method performs better on breast and thyroid lesions segmentation., Comment: 4 pages, 4 figures, 2 tables;For icassp2025

Multilayer rhombohedral graphene (RG) has recently emerged as a new, structurally simple flat-band system, which facilitates the exploration of interaction-driven correlation states with highly ordered electron arrangements. Despite a variety of many-body order behaviors observed in RG by transport measurements, the direct microscopic visualization of such correlated phases in real space is still lacking. Here, we show the discovery of a robust intervalley coherent order, a long-predicted ground state in RG, at 77 K in tetralayer RG placed on MoS2 via imaging atomic-scale spatial reconstruction of wave functions for correlated states. By using scanning tunnelling microscopy, we observe spectroscopic signatures of electronic correlations at partially filled flat bands, where distinct splitting appears. At ~60% and ~70% fillings of the flat bands, we visualize atomic-scale reconstruction patterns with a 3 x 3 supercell on graphene lattice at liquid nitrogen temperature, which indicates a robust intervalley coherent phase of the interacting electrons. The 3 x 3 pattern is observed in MoS2-supported RG, while it is absent in hBN-based ones under the same experimental conditions, suggesting the significant influence of spin-orbit proximity effect. Our results provide microscopic insights into the correlated phases in tetralayer RG and highlight the significant potential for realizing highly accessible collective phenomena through Van der Waals proximity., Comment: 21 pages, 5 figures

Code translation aims to convert a program from one programming language (PL) to another. This long-standing software engineering task is crucial for modernizing legacy systems, ensuring cross-platform compatibility, enhancing performance, and more. However, automating this process remains challenging due to many syntactic and semantic differences between PLs. Recent studies show that even advanced techniques such as large language models (LLMs), especially open-source LLMs, still struggle with the task. Currently, code LLMs are trained with source code from multiple programming languages, thus presenting multilingual capabilities. In this paper, we investigate whether such multilingual capabilities can be harnessed to enhance code translation. To achieve this goal, we introduce InterTrans, an LLM-based automated code translation approach that, in contrast to existing approaches, leverages intermediate translations across PLs to bridge the syntactic and semantic gaps between source and target PLs. InterTrans contains two stages. It first utilizes a novel Tree of Code Translation (ToCT) algorithm to plan transitive intermediate translation sequences between a given source and target PL, then validates them in a specific order. We evaluate InterTrans with three open LLMs on three benchmarks (i.e., CodeNet, HumanEval-X, and TransCoder) involving six PLs. Results show an absolute improvement between 18.3% to 43.3% in Computation Accuracy (CA) for InterTrans over Direct Translation with 10 attempts. The best-performing variant of InterTrans (with Magicoder LLM) achieved an average CA of 87.3%-95.4% on three benchmarks.

While fuzzing has demonstrated its effectiveness in exposing vulnerabilities within embedded firmware, the discovery of crashing test cases is only the first step in improving the security of these critical systems. The subsequent fault localization process, which aims to precisely identify the root causes of observed crashes, is a crucial yet time-consuming post-fuzzing work. Unfortunately, the automated root cause analysis on embedded firmware crashes remains an underexplored area, which is challenging from several perspectives: (1) the fuzzing campaign towards the embedded firmware lacks adequate debugging mechanisms, making it hard to automatically extract essential runtime information for analysis; (2) the inherent raw binary nature of embedded firmware often leads to over-tainted and noisy suspicious instructions, which provides limited guidance for analysts in manually investigating the root cause and remediating the underlying vulnerability. To address these challenges, we design and implement FirmRCA, a practical fault localization framework tailored specifically for embedded firmware. FirmRCA introduces an event-based footprint collection approach to aid and significantly expedite reverse execution. Next, to solve the complicated memory alias problem, FirmRCA proposes a history-driven method by tracking data propagation through the execution trace, enabling precise identification of deep crash origins. Finally, FirmRCA proposes a novel strategy to highlight key instructions related to the root cause, providing practical guidance in the final investigation. We evaluate FirmRCA with both synthetic and real-world targets, including 41 crashing test cases across 17 firmware images. The results show that FirmRCA can effectively (92.7% success rate) identify the root cause of crashing test cases within the top 10 instructions., Comment: To appear in the IEEE Symposium on Security and Privacy (IEEE S&P) 2025, San Francisco, CA, USA

Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that fine-tuning with this subset achieves results comparable to or even exceeding those obtained using the entire dataset. However, most existing data selection techniques are designed for small-scale data pools, which fail to meet the demands of real-world SFT scenarios. In this paper, we replicated several self-scoring methods those that do not rely on external model assistance on two million scale datasets, and found that nearly all methods struggled to significantly outperform random selection when dealing with such large-scale data pools. Moreover, our comparisons suggest that, during SFT, diversity in data selection is more critical than simply focusing on high quality data. We also analyzed the limitations of several current approaches, explaining why they perform poorly on large-scale datasets and why they are unsuitable for such contexts. Finally, we found that filtering data by token length offers a stable and efficient method for improving results. This approach, particularly when training on long text data, proves highly beneficial for relatively weaker base models, such as Llama3.

The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images will not be as ideal as in simulations, presenting significant challenges for the practical application of LMMs. To address this issue, we introduce R-Bench, a benchmark focused on the **Real-world Robustness of LMMs**. Specifically, we: (a) model the complete link from user capture to LMMs reception, comprising 33 corruption dimensions, including 7 steps according to the corruption sequence, and 7 groups based on low-level attributes; (b) collect reference/distorted image dataset before/after corruption, including 2,970 question-answer pairs with human labeling; (c) propose comprehensive evaluation for absolute/relative robustness and benchmark 20 mainstream LMMs. Results show that while LMMs can correctly handle the original reference images, their performance is not stable when faced with distorted images, and there is a significant gap in robustness compared to the human visual system. We hope that R-Bench will inspire improving the robustness of LMMs, **extending them from experimental simulations to the real-world application**. Check https://q-future.github.io/R-Bench for details.

Large language models (LLMs) like GitHub Copilot and ChatGPT have emerged as powerful tools for code generation, significantly enhancing productivity and accelerating software development. However, existing benchmarks primarily focus on general code generation without considering API-oriented code generation, i.e., generating code that invokes APIs from specific libraries. Given the growing demand for API-oriented code generation, there is a pressing need for a systematic and automated approach to evaluate LLM on API-oriented code generation. To address this gap, we propose AutoAPIEval, a lightweight and automated framework designed to evaluate the capabilities of LLMs in API-oriented code generation. Our framework works with any library that provides API documentation and focuses on two unit tasks: API recommendation and code example generation, along with four metrics to evaluate the generated APIs and code examples, such as the proportion of incorrect API recommendations for Task 1, and the proportion of code examples where no specific API is invoked and uncompilable/unexecutable code examples for Task 2. In addition, we conducted a case study on three LLMs (ChatGPT, MagiCoder, and DeepSeek Coder) and Java Runtime Environment 8 to demonstrate the framework's effectiveness. Our findings reveal substantial variability in LLM performance across tasks, with ChatGPT adhering better to instructions, while sharing similar effectiveness in code example generation with its counterparts (i.e., MagiCoder and DeekSeek Coder). We also identify key factors associated with code quality, such as API popularity and model confidence, and build classifiers that achieve high accuracy in detecting incorrect API recommendations and erroneous code examples. Retrieval-augmented generation enhances the quality of code generated by LLMs, though its effectiveness varies across different LLMs.

Unsupervised video semantic compression (UVSC), i.e., compressing videos to better support various analysis tasks, has recently garnered attention. However, the semantic richness of previous methods remains limited, due to the single semantic learning objective, limited training data, etc. To address this, we propose to boost the UVSC task by absorbing the off-the-shelf rich semantics from VFMs. Specifically, we introduce a VFMs-shared semantic alignment layer, complemented by VFM-specific prompts, to flexibly align semantics between the compressed video and various VFMs. This allows different VFMs to collaboratively build a mutually-enhanced semantic space, guiding the learning of the compression model. Moreover, we introduce a dynamic trajectory-based inter-frame compression scheme, which first estimates the semantic trajectory based on the historical content, and then traverses along the trajectory to predict the future semantics as the coding context. This reduces the overall bitcost of the system, further improving the compression efficiency. Our approach outperforms previous coding methods on three mainstream tasks and six datasets., Comment: ECCV2024

Generalist web agents have demonstrated remarkable potential in autonomously completing a wide range of tasks on real websites, significantly boosting human productivity. However, web tasks, such as booking flights, usually involve users' PII, which may be exposed to potential privacy risks if web agents accidentally interact with compromised websites, a scenario that remains largely unexplored in the literature. In this work, we narrow this gap by conducting the first study on the privacy risks of generalist web agents in adversarial environments. First, we present a realistic threat model for attacks on the website, where we consider two adversarial targets: stealing users' specific PII or the entire user request. Then, we propose a novel attack method, termed Environmental Injection Attack (EIA). EIA injects malicious content designed to adapt well to environments where the agents operate and our work instantiates EIA specifically for privacy scenarios in web environments. We collect 177 action steps that involve diverse PII categories on realistic websites from the Mind2Web, and conduct experiments using one of the most capable generalist web agent frameworks to date. The results demonstrate that EIA achieves up to 70% ASR in stealing specific PII and 16% ASR for full user request. Additionally, by accessing the stealthiness and experimenting with a defensive system prompt, we indicate that EIA is hard to detect and mitigate. Notably, attacks that are not well adapted for a webpage can be detected via human inspection, leading to our discussion about the trade-off between security and autonomy. However, extra attackers' efforts can make EIA seamlessly adapted, rendering such supervision ineffective. Thus, we further discuss the defenses at the pre- and post-deployment stages of the websites without relying on human supervision and call for more advanced defense strategies., Comment: Accepted by ICLR 2025

Though recent advances in machine learning have led to significant improvements in natural language interfaces for databases, the accuracy and reliability of these systems remain limited, especially in high-stakes domains. This paper introduces SQLucid, a novel user interface that bridges the gap between non-expert users and complex database querying processes. SQLucid addresses existing limitations by integrating visual correspondence, intermediate query results, and editable step-by-step SQL explanations in natural language to facilitate user understanding and engagement. This unique blend of features empowers users to understand and refine SQL queries easily and precisely. Two user studies and one quantitative experiment were conducted to validate SQLucid's effectiveness, showing significant improvement in task completion accuracy and user confidence compared to existing interfaces. Our code is available at https://github.com/magic-YuanTian/SQLucid., Comment: Accepted to UIST'24

A Software Bill of Materials (SBoM) is a detailed inventory of all components, libraries, and modules in a software artifact, providing traceability throughout the software supply chain. With the increasing popularity of JavaScript in software engineering due to its dynamic syntax and seamless supply chain integration, the exposure to vulnerabilities and attacks has risen significantly. A JavaScript application bundle, which is a consolidated, symbol-stripped, and optimized assembly of code for deployment purpose. Generating a SBoM from a JavaScript application bundle through a reverse-engineering process ensures the integrity, security, and compliance of the supplier's software release, even without access to the original dependency graphs. This paper presents the first study on SBoM generation for JavaScript application bundles. We identify three key challenges for this task, i.e., nested code scopes, extremely long sequences, and large retrieval spaces. To address these challenges, we introduce Chain-of-Experts (CoE), a multi-task deep learning model designed to generate SBoMs through three tasks: code segmentation, code classification, and code clone retrieval. We evaluate CoE against individual task-specific solutions on 500 web application bundles with over 66,000 dependencies. Our experimental results demonstrate that CoE offers competitive outcomes with less training and inference time when compared with combined individual task-specific solutions. Consequently, CoE provides the first scalable, efficient, and end-to-end solution for the SBoM generation of real-world JavaScript application bundles.

We theoretically investigate the problem of position detection of an optically levitated Mie particle. The information radiation field (IRF) is proposed and defined to characterize the scattered light carrying complete information about the center-of-mass (c.m.) motion of the particle. Based on the IRF, we suggest an optimal detection scheme for the position of arbitrary particles. We calculate both the information losses of objective collection and mode-matching in levitated optomechanical experiments. Our results conclude that the backward detection scheme, using an incident Gaussian beam focused by a high numerical aperture lens, provides sufficient information to achieve the quantum ground state through cooling of the three-dimensional c.m. motion of the Mie particle.

Recent advances in large language models (LLMs) have transformed software development by automatically generating code from natural language. Yet challenges remain in generating fully correct code that aligns with user intent. Our study reveals that LLMs tend to pay less attention to user prompts as more code tokens are generated. We hypothesize that this attention dilution issue is an important reason for code generation errors. To mitigate this issue, we propose Selective Prompt Anchoring (SPA) to guide code LLMs to pay more attention to user intent when generating code. We evaluate SPA using six base LLMs across six benchmarks. Our results demonstrate that SPA enhances Pass@1 by up to 12.9%, consistently outperforming SOTA code generation methods in all settings. Our code is available at https://github.com/magic-YuanTian/Selective-Prompt-Anchoring.

AI-powered coding assistants such as GitHub Copilot and OpenAI ChatGPT have achieved notable success in automating code generation. However, these tools rely on pre-trained Large Language Models (LLMs) that are typically trained on human-written code sourced from open-source project hosting sites like GitHub, which often contains inherent security vulnerabilities. These vulnerabilities may then be mirrored in the code generated by these LLMs, a critical risk revealed and highlighted by recent empirical studies. In this work, we present an exploratory study on whether fine-tuning pre-trained LLMs on datasets of vulnerability-fixing commits can promote secure code generation. We explored two parameter-efficient fine-tuning techniques (LoRa and IA3) on two pre-trained LLMs for code generation. We crawled a fine-tuning dataset (14,622 C and C++ files) for secure code generation by collecting code fixes of confirmed vulnerabilities from open-source repositories. Our evaluation dataset comprises 52 vulnerability scenarios designed to cover the top most dangerous C and C++ Common Weakness Enumerations (CWEs). Each scenario is a prompt that may induce LLMs to generate vulnerable code. Our exploration reveals that fine-tuning LLMs can improve secure code generation by 6.4% in C language and 5.4% in C++ language. We further experimented with fine-tuning LLMs using different versions of the collected secure code dataset (block, function, and line). We found that fine-tuning with function-level and block-level datasets achieves the best secure code generation performance, compared to the alternatives (file-level and line-level)., Comment: 24 pages, 6 figures

Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approach to facilitate knowledge transfer among these independently fine-tuned models. MM directly combines multiple fine-tuned task-specific models into a merged model without additional training, and the resulting model shows enhanced capabilities in multiple tasks. Although MM provides great utility, it may come with security risks because an adversary can exploit MM to affect multiple downstream tasks. However, the security risks of MM have barely been studied. In this paper, we first find that MM, as a new learning paradigm, introduces unique challenges for existing backdoor attacks due to the merging process. To address these challenges, we introduce BadMerging, the first backdoor attack specifically designed for MM. Notably, BadMerging allows an adversary to compromise the entire merged model by contributing as few as one backdoored task-specific model. BadMerging comprises a two-stage attack mechanism and a novel feature-interpolation-based loss to enhance the robustness of embedded backdoors against the changes of different merging parameters. Considering that a merged model may incorporate tasks from different domains, BadMerging can jointly compromise the tasks provided by the adversary (on-task attack) and other contributors (off-task attack) and solve the corresponding unique challenges with novel attack designs. Extensive experiments show that BadMerging achieves remarkable attacks against various MM algorithms. Our ablation study demonstrates that the proposed attack designs can progressively contribute to the attack performance. Finally, we show that prior defense mechanisms fail to defend against our attacks, highlighting the need for more advanced defense., Comment: To appear in ACM Conference on Computer and Communications Security (CCS), 2024

Sparsely-activated Mixture-of-Experts (MoE) architecture has increasingly been adopted to further scale large language models (LLMs) due to its sub-linear scaling for computation costs. However, frequent failures still pose significant challenges as training scales. The cost of even a single failure is significant, as all GPUs need to wait idle until the failure is resolved, potentially losing considerable training progress as training has to restart from checkpoints. Existing solutions for efficient fault-tolerant training either lack elasticity or rely on building resiliency into pipeline parallelism, which cannot be applied to MoE models due to the expert parallelism strategy adopted by the MoE architecture. We present Lazarus, a system for resilient and elastic training of MoE models. Lazarus adaptively allocates expert replicas to address the inherent imbalance in expert workload and speeds-up training, while a provably optimal expert placement algorithm is developed to maximize the probability of recovery upon failures. Through adaptive expert placement and a flexible token dispatcher, Lazarus can also fully utilize all available nodes after failures, leaving no GPU idle. Our evaluation shows that Lazarus outperforms existing MoE training systems by up to 5.7x under frequent node failures and 3.4x on a real spot instance trace.

The exponential progress in generative AI poses serious implications for the credibility of all real images and videos. There will exist a point in the future where 1) digital content produced by generative AI will be indistinguishable from those created by cameras, 2) high-quality generative algorithms will be accessible to anyone, and 3) the ratio of all synthetic to real images will be large. It is imperative to establish methods that can separate real data from synthetic data with high confidence. We define real images as those that were produced by the camera hardware, capturing a real-world scene. Any synthetic generation of an image or alteration of a real image through generative AI or computer graphics techniques is labeled as a synthetic image. To this end, this document aims to: present known strategies in detection and cryptography that can be employed to verify which images are real, weight the strengths and weaknesses of these strategies, and suggest additional improvements to alleviate shortcomings.

Assessing action quality is both imperative and challenging due to its significant impact on the quality of AI-generated videos, further complicated by the inherently ambiguous nature of actions within AI-generated video (AIGV). Current action quality assessment (AQA) algorithms predominantly focus on actions from real specific scenarios and are pre-trained with normative action features, thus rendering them inapplicable in AIGVs. To address these problems, we construct GAIA, a Generic AI-generated Action dataset, by conducting a large-scale subjective evaluation from a novel causal reasoning-based perspective, resulting in 971,244 ratings among 9,180 video-action pairs. Based on GAIA, we evaluate a suite of popular text-to-video (T2V) models on their ability to generate visually rational actions, revealing their pros and cons on different categories of actions. We also extend GAIA as a testbed to benchmark the AQA capacity of existing automatic evaluation methods. Results show that traditional AQA methods, action-related metrics in recent T2V benchmarks, and mainstream video quality methods perform poorly with an average SRCC of 0.454, 0.191, and 0.519, respectively, indicating a sizable gap between current models and human action perception patterns in AIGVs. Our findings underscore the significance of action quality as a unique perspective for studying AIGVs and can catalyze progress towards methods with enhanced capacities for AQA in AIGVs., Comment: Accepted by NeurIPS2024 Dataset and Benchmark Track as Spotlight. 33 pages, 15 figures

Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream video analysis tasks. In this paper, we propose a Masked Video Modeling (MVM)-powered compression framework that particularly preserves video semantics, by jointly mining and compressing the semantics in a self-supervised manner. While MVM is proficient at learning generalizable semantics through the masked patch prediction task, it may also encode non-semantic information like trivial textural details, wasting bitcost and bringing semantic noises. To suppress this, we explicitly regularize the non-semantic entropy of the compressed video in the MVM token space. The proposed framework is instantiated as a simple Semantic-Mining-then-Compression (SMC) model. Furthermore, we extend SMC as an advanced SMC++ model from several aspects. First, we equip it with a masked motion prediction objective, leading to better temporal semantic learning ability. Second, we introduce a Transformer-based compression module, to improve the semantic compression efficacy. Considering that directly mining the complex redundancy among heterogeneous features in different coding stages is non-trivial, we introduce a compact blueprint semantic representation to align these features into a similar form, fully unleashing the power of the Transformer-based compression module. Extensive results demonstrate the proposed SMC and SMC++ models show remarkable superiority over previous traditional, learnable, and perceptual quality-oriented video codecs, on three video analysis tasks and seven datasets. \textit{Codes and model are available at: \url{https://github.com/tianyuan168326/VideoSemanticCompression-Pytorch}.

The Workflows as Code paradigm is becoming increasingly essential to streamline the design and management of complex processes within data-intensive software systems. These systems require robust capabilities to process, analyze, and extract insights from large datasets. Workflow orchestration platforms such as Apache Airflow are pivotal in meeting these needs, as they effectively support the implementation of the Workflows as Code paradigm. Nevertheless, despite its considerable advantages, developers still face challenges due to the specialized demands of workflow orchestration and the complexities of distributed execution environments. In this paper, we manually study 1,000 sampled Stack Overflow posts derived from 9,591 Airflow-related questions to understand developers' challenges and root causes while implementing Workflows as Code. Our analysis results in a hierarchical taxonomy of Airflow-related challenges that contains 7 high-level categories and 14 sub-categories. We find that the most significant obstacles for developers arise when defining and executing their workflow. Our in-depth analysis identifies 10 root causes behind the challenges, including incorrect workflow configuration, complex environmental setup, and a lack of basic knowledge about Airflow and the external systems that it interacts with. Additionally, our analysis of references shared within the collected posts reveals that beyond the frequently cited Airflow documentation, documentation from external systems and third-party providers is also commonly referenced to address Airflow-related challenges., Comment: This is the preprint version of a paper that has been submitted to the Journal of Systems and Software

Finding the root causes of anomalies in cloud computing systems quickly is crucial to ensure availability and efficiency since accurate root causes can guide engineers to take appropriate actions to address the anomalies and maintain customer satisfaction. However, it is difficult to investigate and identify the root causes based on large-scale and high-dimension monitoring data collected from complex cloud computing environments. Due to the inherently dynamic characteristics of cloud computing systems, the existing approaches in practice largely rely on manual analyses for flexibility and reliability, but massive unpredictable factors and high data complexity make the process time-consuming. Despite recent advances in automated detection and investigation approaches, the speed and quality of root cause analyses remain limited by the lack of expert involvement in these approaches. The limitations found in the current solutions motivate us to propose a visual analytics approach that facilitates the interactive investigation of the anomaly root causes in cloud computing systems. We identified three challenges, namely, a) modeling databases for the root cause investigation, b) inferring root causes from large-scale time series, and c) building comprehensible investigation results. In collaboration with domain experts, we addressed these challenges with RCInvestigator, a novel visual analytics system that establishes a tight collaboration between human and machine and assists experts in investigating the root causes of cloud computing system anomalies. We evaluated the effectiveness of RCInvestigator through two use cases based on real-world data and received positive feedback from experts.

As Virtual Reality (VR) applications grow in popularity, they have bridged distances and brought users closer together. However, with this growth, there have been increasing concerns about security and privacy, especially related to the motion data used to create immersive experiences. In this study, we highlight a significant security threat in multi-user VR applications, which are applications that allow multiple users to interact with each other in the same virtual space. Specifically, we propose a remote attack that utilizes the avatar rendering information collected from an adversary's game clients to extract user-typed secrets like credit card information, passwords, or private conversations. We do this by (1) extracting motion data from network packets, and (2) mapping motion data to keystroke entries. We conducted a user study to verify the attack's effectiveness, in which our attack successfully inferred 97.62% of the keystrokes. Besides, we performed an additional experiment to underline that our attack is practical, confirming its effectiveness even when (1) there are multiple users in a room, and (2) the attacker cannot see the victims. Moreover, we replicated our proposed attack on four applications to demonstrate the generalizability of the attack. Lastly, we proposed a defense against the attack, which has been implemented by major players in the VR industry. These results underscore the severity of the vulnerability and its potential impact on millions of VR social platform users., Comment: Accepted for Usenix 2024

Self-Admitted Technical Debt (SATD), a concept highlighting sub-optimal choices in software development documented in code comments or other project resources, poses challenges in the maintainability and evolution of software systems. Large language models (LLMs) have demonstrated significant effectiveness across a broad range of software tasks, especially in software text generation tasks. Nonetheless, their effectiveness in tasks related to SATD is still under-researched. In this paper, we investigate the efficacy of LLMs in both identification and classification of SATD. For both tasks, we investigate the performance gain from using more recent LLMs, specifically the Flan-T5 family, across different common usage settings. Our results demonstrate that for SATD identification, all fine-tuned LLMs outperform the best existing non-LLM baseline, i.e., the CNN model, with a 4.4% to 7.2% improvement in F1 score. In the SATD classification task, while our largest fine-tuned model, Flan-T5-XL, still led in performance, the CNN model exhibited competitive results, even surpassing four of six LLMs. We also found that the largest Flan-T5 model, i.e., Flan-T5-XXL, when used with a zero-shot in-context learning (ICL) approach for SATD identification, provides competitive results with traditional approaches but performs 6.4% to 9.2% worse than fine-tuned LLMs. For SATD classification, few-shot ICL approach, incorporating examples and category descriptions in prompts, outperforms the zero-shot approach and even surpasses the fine-tuned smaller Flan-T5 models. Moreover, our experiments demonstrate that incorporating contextual information, such as surrounding code, into the SATD classification task enables larger fine-tuned LLMs to improve their performance., Comment: This is the preprint version of a paper that has been submitted to Empirical Software Engineering

Acoustic scene classification (ASC) is highly important in the real world. Recently, deep learning-based methods have been widely employed for acoustic scene classification. However, these methods are currently not lightweight enough as well as their performance is not satisfactory. To solve these problems, we propose a deep space separable distillation network. Firstly, the network performs high-low frequency decomposition on the log-mel spectrogram, significantly reducing computational complexity while maintaining model performance. Secondly, we specially design three lightweight operators for ASC, including Separable Convolution (SC), Orthonormal Separable Convolution (OSC), and Separable Partial Convolution (SPC). These operators exhibit highly efficient feature extraction capabilities in acoustic scene classification tasks. The experimental results demonstrate that the proposed method achieves a performance gain of 9.8% compared to the currently popular deep learning methods, while also having smaller parameter count and computational complexity.

Most fake news detection methods learn latent feature representations based on neural networks, which makes them black boxes to classify a piece of news without giving any justification. Existing explainable systems generate veracity justifications from investigative journalism, which suffer from debunking delayed and low efficiency. Recent studies simply assume that the justification is equivalent to the majority opinions expressed in the wisdom of crowds. However, the opinions typically contain some inaccurate or biased information since the wisdom of crowds is uncensored. To detect fake news from a sea of diverse, crowded and even competing narratives, in this paper, we propose a novel defense-based explainable fake news detection framework. Specifically, we first propose an evidence extraction module to split the wisdom of crowds into two competing parties and respectively detect salient evidences. To gain concise insights from evidences, we then design a prompt-based module that utilizes a large language model to generate justifications by inferring reasons towards two possible veracities. Finally, we propose a defense-based inference module to determine veracity via modeling the defense among these justifications. Extensive experiments conducted on two real-world benchmarks demonstrate that our proposed method outperforms state-of-the-art baselines in terms of fake news detection and provides high-quality justifications., Comment: 12 pages, WWW'2024

Electrons on Kagome lattice exhibit a wealth of features including Dirac points, van Hove singularities and flatbands. When the Fermi level is placed at the van Hove saddle point, the Fermi surface is perfectly nested and a rich variety of electronic instabilities is known to occur. The material realization of such scenario is a recently discovered Kagome system CsV3Sb5 whose superconductivity near charge-density wave instability at low temperatures points to an unconventional, non-electron-phonon, pairing mechanism. Here we use a recently developed combination of density functional theory with momentum and frequency-resolved self-energies deduced from the so-called fluctuational-exchange-type random phase approximation to study charge fluctuation mediated pairing tendencies in CsV3Sb5. Based on our numerical diagonalization of the BCS gap equation, two competing solutions emerge from these calculations with A_{1g} (anisotropic s-wave-like) and B_{2g} (d_{x2-y2},d_{xy}-like) symmetries of the superconducting order parameter. Our evaluated Eliashberg spectral functions {\alpha}2F({\omega}) are purely due to electronic correlations; they were found to be strongly peaked in the vicinity of frequency 7 meV that sets the scale of charge fluctuations. The superconducting coupling constants for the leading pairing channels are estimated as a function of the nearest neighbor Coulomb interaction V, a well-known prime parameter of the extended Hubbard model. They were found in the range of 0.2-0.4 depending on V. We evaluate the superconducting T_{c} close to the values that are observed experimentally that point to the charge fluctuations to provide a substantial contribution to the pairing mechanism in CsV3Sb5., Comment: 6 pages, 4 figures