Lei Ma

Shuangzhi Li, Zhijie Wang, Felix Juefei-Xu et al. · mit

Object detection through LiDAR-based point cloud has recently been important in autonomous driving. Although achieving high accuracy on public benchmarks, the state-of-the-art detectors may still go wrong and cause a heavy loss due to the widespread corruptions in the real world like rain, snow, sensor noise, etc. Nevertheless, there is a lack of a large-scale dataset covering diverse scenes and realistic corruption types with different severities to develop practical and robust point cloud detectors, which is challenging due to the heavy collection costs. To alleviate the challenge and start the first step for robust point cloud detection, we propose the physical-aware simulation methods to generate degraded point clouds under different real-world common corruptions. Then, for the first attempt, we construct a benchmark based on the physical-aware common corruptions for point cloud detectors, which contains a total of 1,122,150 examples covering 7,481 scenes, 25 common corruption types, and 6 severities. With such a novel benchmark, we conduct extensive empirical studies on 8 state-of-the-art detectors that contain 6 different detection frameworks. Thus we get several insight observations revealing the vulnerabilities of the detectors and indicating the enhancement directions. Moreover, we further study the effectiveness of existing robustness enhancement methods based on data augmentation and data denoising. The benchmark can potentially be a new platform for evaluating point cloud detectors, opening a door for developing novel robustness enhancement methods.

Yi Liu, Yuekang Li, Gelei Deng et al.

The popularity of automatic speech recognition (ASR) systems nowadays leads to an increasing need for improving their accessibility. Handling stuttering speech is an important feature for accessible ASR systems. To improve the accessibility of ASR systems for stutterers, we need to expose and analyze the failures of ASR systems on stuttering speech. The speech datasets recorded from stutterers are not diverse enough to expose most of the failures. Furthermore, these datasets lack ground truth information about the non-stuttered text, rendering them unsuitable as comprehensive test suites. Therefore, a methodology for generating stuttering speech as test inputs to test and analyze the performance of ASR systems is needed. However, generating valid test inputs in this scenario is challenging. The reason is that although the generated test inputs should mimic how stutterers speak, they should also be diverse enough to trigger more failures. To address the challenge, we propose ASTER, a technique for automatically testing the accessibility of ASR systems. ASTER can generate valid test cases by injecting five different types of stuttering. The generated test cases can both simulate realistic stuttering speech and expose failures in ASR systems. Moreover, ASTER can further enhance the quality of the test cases with a multi-objective optimization-based seed updating algorithm. We implemented ASTER as a framework and evaluated it on four open-source ASR models and three commercial ASR systems. We conduct a comprehensive evaluation of ASTER and find that it significantly increases the word error rate, match error rate, and word information loss in the evaluated ASR systems. Additionally, our user study demonstrates that the generated stuttering audio is indistinguishable from real-world stuttering audio clips.

Yinghua Li, Xueqi Dang, Haoye Tian et al.

The integration of artificial intelligence (AI) into mobile applications has significantly transformed various domains, enhancing user experiences and providing personalized services through advanced machine learning (ML) and deep learning (DL) technologies. AI-driven mobile apps typically refer to applications that leverage ML/DL technologies to perform key tasks such as image recognition and natural language processing. In this paper, we conducted the most extensive empirical study on AI applications, exploring on-device ML apps, on-device DL apps, and AI service-supported (cloud-based) apps. Our study encompasses 56,682 real-world AI applications, focusing on three crucial perspectives: 1) Application analysis, where we analyze the popularity of AI apps and investigate the update states of AI apps; 2) Framework and model analysis, where we analyze AI framework usage and AI model protection; 3) User analysis, where we examine user privacy protection and user review attitudes. Our study has strong implications for AI app developers, users, and AI R\&D. On one hand, our findings highlight the growing trend of AI integration in mobile applications, demonstrating the widespread adoption of various AI frameworks and models. On the other hand, our findings emphasize the need for robust model protection to enhance app security. Additionally, our study highlights the importance of user privacy and presents user attitudes towards the AI technologies utilized in current AI apps. We provide our AI app dataset (currently the most extensive AI app dataset) as an open-source resource for future research on AI technologies utilized in mobile applications.

Lei Ma, Nicolas Boullé, Yu-Sen Yang et al.

Physics-informed operator learning provides an efficient framework for approximating solution operators of partial differential equations by combining observational data with governing physical laws. However, most existing methods implicitly assume that the prescribed governing equation is accurate. This assumption may fail in practical applications, where model simplifications, missing physical effects, parameter drift, or incomplete constitutive relations can lead to model misspecification. In this work, we propose a physics-guided operator correction framework for learning solution operators under misspecified governing equations. At the operator level, the target mapping is decomposed into a prior operator induced by an approximate physical model and a learnable correction operator that accounts for the remaining discrepancy. Although the formulation is architecture independent, we realize it using a serial DeepONet architecture, where the first DeepONet provides a prior prediction and the second DeepONet learns an additive correction conditioned on both the input function and the prior prediction. The learned correction is incorporated into the physics residual and trained together with data-consistency constraints, allowing the model to retain useful physical structure while adapting to inaccurate governing equations. Numerical experiments on diffusion-reaction, Burgers, cavity flow, and hyperelastic problems show that the proposed method substantially reduces errors induced by misspecified physics. Additional tests under sparse and noisy observations further demonstrate the robustness of the framework and its ability to provide informative uncertainty estimates through deep ensembles.

Shan Zhang, Yongxin He, Mingming Zhang et al.

Real-world synthetic image detectors often generalize poorly under domain shift despite strong in-domain performance. Using unsupervised UMAP projections, we find that natural and synthetic features remain partially separable on unseen datasets, yet performance still drops, suggesting that the classification head overfits to training-domain artifacts. Therefore, the key is to learn more transferable representations so that the decision criterion is more stable and robust to domain shifts. Based on the structural fact that synthetic images are produced by diverse generators, we propose a hierarchical contrastive learning framework that improves the separability between natural and synthetic images while preserving generator identity information. It jointly optimizes (i) a coarse contrastive objective between natural and synthetic images and (ii) a fine contrastive objective among synthetic images using generator identities. Trained on WildFake, our method achieves an average AUROC gain of +10.22 on cross-domain evaluation over Chameleon, AIGIBench, Community Forensics, and GenImage under the same settings as the strong baseline DIRE. For few-shot adaptation, we freeze the backbone and fit an SVM head on 10 labeled samples per class, improving AUROC by +10.64 on AIGIBench and +17.41 on Chameleon, averaged over 12 widely used detectors. Our code is publicly available at: https://github.com/heyongxin233/FiSeR.

Lei Ma, Jingyang Zhang, Ke Deng et al.

Dental template and parametric dental models are important tools for various applications in digital dentistry. However, constructing an unbiased dental template and accurate parametric dental models remains a challenging task due to the complex anatomical and morphological dental structures and also low volume ratio of the teeth. In this study, we develop an unbiased dental template by constructing an accurate dental atlas from CBCT images with guidance of teeth segmentation. First, to address the challenges, we propose to enhance the CBCT images and their segmentation images, including image cropping, image masking and segmentation intensity reassigning. Then, we further use the segmentation images to perform co-registration with the CBCT images to generate an accurate dental atlas, from which an unbiased dental template can be generated. By leveraging the unbiased dental template, we construct parametric dental models by estimating point-to-point correspondences between the dental models and employing Principal Component Analysis to determine shape subspaces of the parametric dental models. A total of 159 CBCT images of real subjects are collected to perform the constructions. Experimental results demonstrate effectiveness of our proposed method in constructing unbiased dental template and parametric dental model. The developed dental template and parametric dental models are available at https://github.com/Marvin0724/Teeth_template.

Yang Li, Gongle Xue, Yijia Guo et al.

Reinforcement learning with verifiable rewards (RLVR), especially Group Relative Policy Optimization (GRPO), has been widely used to improve reasoning in large language models. However, outcome-level rewards provide only sparse supervision, and group-relative advantages vanish when all sampled trajectories for a prompt are either correct or incorrect. On-Policy Self-Distillation (OPSD) offers dense token-level guidance, but its token preferences are not necessarily aligned with trajectory correctness; empirical diagnostics show that OPSD signals behave differently on correct and incorrect rollouts, with teacher-positive and teacher-negative gap signals exhibiting different noise profiles. These diagnostics are conducted under an OPSD-style privileged teacher context for analysis only, whereas CAST training uses answer-free self-teacher scoring.Motivated by these observations, this work proposes CAST, an answer-free self-distillation method for GRPO-style RLVR. CAST keeps the verifier-grounded GRPO objective, but uses a stop-gradient self-teacher to shape token-level advantages according to trajectory correctness. Unlike prior self-distilled RLVR methods, CAST does not require reference-solution-conditioned teacher scoring, keeps the self-teacher log-probability gap active throughout training, and applies bidirectional local advantage sign reversal: teacher-negative tokens in correct trajectories can receive negative token-level advantages, while teacher-positive tokens in incorrect trajectories can receive bounded positive local advantages. For zero-variance all-correct and all-wrong groups, CAST assigns bounded sign-constrained base advantages, so these otherwise zero-gradient groups can contribute verifier-signed token feedback. Experiments on mathematical reasoning show that CAST improves RLVR training while retaining a lightweight, verifier-grounded trajectory-level objective.

Yao Su, Zhentian Qian, Lei Ma et al.

Brain extraction, registration and segmentation are indispensable preprocessing steps in neuroimaging studies. The aim is to extract the brain from raw imaging scans (i.e., extraction step), align it with a target brain image (i.e., registration step) and label the anatomical brain regions (i.e., segmentation step). Conventional studies typically focus on developing separate methods for the extraction, registration and segmentation tasks in a supervised setting. The performance of these methods is largely contingent on the quantity of training samples and the extent of visual inspections carried out by experts for error correction. Nevertheless, collecting voxel-level labels and performing manual quality control on high-dimensional neuroimages (e.g., 3D MRI) are expensive and time-consuming in many medical studies. In this paper, we study the problem of one-shot joint extraction, registration and segmentation in neuroimaging data, which exploits only one labeled template image (a.k.a. atlas) and a few unlabeled raw images for training. We propose a unified end-to-end framework, called JERS, to jointly optimize the extraction, registration and segmentation tasks, allowing feedback among them. Specifically, we use a group of extraction, registration and segmentation modules to learn the extraction mask, transformation and segmentation mask, where modules are interconnected and mutually reinforced by self-supervision. Empirical results on real-world datasets demonstrate that our proposed method performs exceptionally in the extraction, registration and segmentation tasks. Our code and data can be found at https://github.com/Anonymous4545/JERS

Jingyang Zhang, Peng Xue, Ran Gu et al.

In clinical practice, a segmentation network is often required to continually learn on a sequential data stream from multiple sites rather than a consolidated set, due to the storage cost and privacy restriction. However, during the continual learning process, existing methods are usually restricted in either network memorizability on previous sites or generalizability on unseen sites. This paper aims to tackle the challenging problem of Synchronous Memorizability and Generalizability (SMG) and to simultaneously improve performance on both previous and unseen sites, with a novel proposed SMG-learning framework. First, we propose a Synchronous Gradient Alignment (SGA) objective, which not only promotes the network memorizability by enforcing coordinated optimization for a small exemplar set from previous sites (called replay buffer), but also enhances the generalizability by facilitating site-invariance under simulated domain shift. Second, to simplify the optimization of SGA objective, we design a Dual-Meta algorithm that approximates the SGA objective as dual meta-objectives for optimization without expensive computation overhead. Third, for efficient rehearsal, we configure the replay buffer comprehensively considering additional inter-site diversity to reduce redundancy. Experiments on prostate MRI data sequentially acquired from six institutes demonstrate that our method can simultaneously achieve higher memorizability and generalizability over state-of-the-art methods. Code is available at https://github.com/jingyzhang/SMG-Learning.

Lujie Xia, Ziluo Ding, Rui Zhao et al. · pku

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers architecture, it applies dilated convolutions on temporal dimension to extract features on multi-temporal scales with few parameters. And we design layer attention to dynamically fuse these features. Moreover, we propose an unsupervised learning method for optical flow estimation in a spike-based manner to break the dependence on labeled data. In addition, to verify the robustness, we also build a spike-based synthetic validation dataset for extreme scenarios in autonomous driving, denoted as SSES dataset. It consists of various corner cases. Experiments show that our method can predict optical flow from spike streams in different high-speed scenes, including real scenes. For instance, our method gets $15\%$ and $19\%$ error reduction from the best spike-based work, SCFlow, in $Δt=10$ and $Δt=20$ respectively which are the same settings as the previous works.

Yibing Liu, Chris Xing Tian, Haoliang Li et al. · pku

The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, i.e., in-distribution (InD). In this paper, we study the OOD problem from a neuron activation view. We first formulate neuron activation states by considering both the neuron output and its influence on model decisions. Then, to characterize the relationship between neurons and OOD issues, we introduce the \textit{neuron activation coverage} (NAC) -- a simple measure for neuron behaviors under InD data. Leveraging our NAC, we show that 1) InD and OOD inputs can be largely separated based on the neuron behavior, which significantly eases the OOD detection problem and beats the 21 previous methods over three benchmarks (CIFAR-10, CIFAR-100, and ImageNet-1K). 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness. Compared to prevalent InD validation criteria, we show that NAC not only can select more robust models, but also has a stronger correlation with OOD test performance.

Yang Hou, Qing Guo, Yihao Huang et al.

In recent years, as various realistic face forgery techniques known as DeepFake improves by leaps and bounds,more and more DeepFake detection techniques have been proposed. These methods typically rely on detecting statistical differences between natural (i.e., real) and DeepFakegenerated images in both spatial and frequency domains. In this work, we propose to explicitly minimize the statistical differences to evade state-of-the-art DeepFake detectors. To this end, we propose a statistical consistency attack (StatAttack) against DeepFake detectors, which contains two main parts. First, we select several statistical-sensitive natural degradations (i.e., exposure, blur, and noise) and add them to the fake images in an adversarial way. Second, we find that the statistical differences between natural and DeepFake images are positively associated with the distribution shifting between the two kinds of images, and we propose to use a distribution-aware loss to guide the optimization of different degradations. As a result, the feature distributions of generated adversarial examples is close to the natural images.Furthermore, we extend the StatAttack to a more powerful version, MStatAttack, where we extend the single-layer degradation to multi-layer degradations sequentially and use the loss to tune the combination weights jointly. Comprehensive experimental results on four spatial-based detectors and two frequency-based detectors with four datasets demonstrate the effectiveness of our proposed attack method in both white-box and black-box settings.

Xiaofei Xie, Tianlin Li, Jian Wang et al.

Deep learning has recently been widely applied to many applications across different domains, e.g., image classification and audio recognition. However, the quality of Deep Neural Networks (DNNs) still raises concerns in the practical operational environment, which calls for systematic testing, especially in safety-critical scenarios. Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs. However, due to the blackbox nature of DNN, the existing structural coverage criteria are difficult to interpret, making it hard to understand the underlying principles of these criteria. The relationship between the structural coverage and the decision logic of DNNs is unknown. Moreover, recent studies have further revealed the non-existence of correlation between the structural coverage and DNN defect detection, which further posts concerns on what a suitable DNN testing criterion should be. In this paper, we propose the interpretable coverage criteria through constructing the decision structure of a DNN. Mirroring the control flow graph of the traditional program, we first extract a decision graph from a DNN based on its interpretation, where a path of the decision graph represents a decision logic of the DNN. Based on the control flow and data flow of the decision graph, we propose two variants of path coverage to measure the adequacy of the test cases in exercising the decision logic. The higher the path coverage, the more diverse decision logic the DNN is expected to be explored. Our large-scale evaluation results demonstrate that: the path in the decision graph is effective in characterizing the decision of the DNN, and the proposed coverage criteria are also sensitive with errors including natural errors and adversarial examples, and strongly correlated with the output impartiality.

Yuchen Shao, Yuheng Huang, Jiawei Shen et al.

Large language models (LLMs) provide effective solutions in various application scenarios, with the support of retrieval-augmented generation (RAG). However, developers face challenges in integrating LLM and RAG into software systems, due to lacking interface specifications, various requirements from software context, and complicated system management. In this paper, we have conducted a comprehensive study of 100 open-source applications that incorporate LLMs with RAG support, and identified 18 defect patterns. Our study reveals that 77% of these applications contain more than three types of integration defects that degrade software functionality, efficiency, and security. Guided by our study, we propose systematic guidelines for resolving these defects in software life cycle. We also construct an open-source defect library Hydrangea.

Zhijie Wang, Yuheng Huang, Da Song et al.

Recurrent Neural Networks (RNNs) have been widely used in Natural Language Processing (NLP) tasks given its superior performance on processing sequential data. However, it is challenging to interpret and debug RNNs due to the inherent complexity and the lack of transparency of RNNs. While many explainable AI (XAI) techniques have been proposed for RNNs, most of them only support local explanations rather than global explanations. In this paper, we present DeepSeer, an interactive system that provides both global and local explanations of RNN behavior in multiple tightly-coordinated views for model understanding and debugging. The core of DeepSeer is a state abstraction method that bundles semantically similar hidden states in an RNN model and abstracts the model as a finite state machine. Users can explore the global model behavior by inspecting text patterns associated with each state and the transitions between states. Users can also dive into individual predictions by inspecting the state trace and intermediate prediction results of a given input. A between-subjects user study with 28 participants shows that, compared with a popular XAI technique, LIME, participants using DeepSeer made a deeper and more comprehensive assessment of RNN model behavior, identified the root causes of incorrect predictions more accurately, and came up with more actionable plans to improve the model performance.

Qiang Hu, Yuejun Guo, Xiaofei Xie et al.

Deep learning (DL) plays a more and more important role in our daily life due to its competitive performance in industrial application domains. As the core of DL-enabled systems, deep neural networks (DNNs) need to be carefully evaluated to ensure the produced models match the expected requirements. In practice, the \emph{de facto standard} to assess the quality of DNNs in the industry is to check their performance (accuracy) on a collected set of labeled test data. However, preparing such labeled data is often not easy partly because of the huge labeling effort, i.e., data labeling is labor-intensive, especially with the massive new incoming unlabeled data every day. Recent studies show that test selection for DNN is a promising direction that tackles this issue by selecting minimal representative data to label and using these data to assess the model. However, it still requires human effort and cannot be automatic. In this paper, we propose a novel technique, named \textit{Aries}, that can estimate the performance of DNNs on new unlabeled data using only the information obtained from the original test data. The key insight behind our technique is that the model should have similar prediction accuracy on the data which have similar distances to the decision boundary. We performed a large-scale evaluation of our technique on two famous datasets, CIFAR-10 and Tiny-ImageNet, four widely studied DNN models including ResNet101 and DenseNet121, and 13 types of data transformation methods. Results show that the estimated accuracy by \textit{Aries} is only 0.03\% -- 2.60\% off the true accuracy. Besides, \textit{Aries} also outperforms the state-of-the-art labeling-free methods in 50 out of 52 cases and selection-labeling-based methods in 96 out of 128 cases.

Liwen hu, Lei Ma, Zhaofei Yu et al. · pku

As a neuromorphic sensor with high temporal resolution, the spike camera shows enormous potential in high-speed visual tasks. However, the high-speed sampling of light propagation processes by existing cameras brings unavoidable noise phenomena. Eliminating the unique noise in spike stream is always a key point for spike-based methods. No previous work has addressed the detailed noise mechanism of the spike camera. To this end, we propose a systematic noise model for spike camera based on its unique circuit. In addition, we carefully constructed the noise evaluation equation and experimental scenarios to measure noise variables. Based on our noise model, the first benchmark for spike stream denoising is proposed which includes clear (noisy) spike stream. Further, we design a tailored spike stream denoising framework (DnSS) where denoised spike stream is obtained by decoding inferred inter-spike intervals. Experiments show that DnSS has promising performance on the proposed benchmark. Eventually, DnSS can be generalized well on real spike stream.

Jianing Li, Jiaming Liu, Xiaobao Wei et al. · pku

Depth estimation is essential for various important real-world applications such as autonomous driving. However, it suffers from severe performance degradation in high-velocity scenario since traditional cameras can only capture blurred images. To deal with this problem, the spike camera is designed to capture the pixel-wise luminance intensity at high frame rate. However, depth estimation with spike camera remains very challenging using traditional monocular or stereo depth estimation algorithms, which are based on the photometric consistency. In this paper, we propose a novel Uncertainty-Guided Depth Fusion (UGDF) framework to fuse the predictions of monocular and stereo depth estimation networks for spike camera. Our framework is motivated by the fact that stereo spike depth estimation achieves better results at close range while monocular spike depth estimation obtains better results at long range. Therefore, we introduce a dual-task depth estimation architecture with a joint training strategy and estimate the distributed uncertainty to fuse the monocular and stereo results. In order to demonstrate the advantage of spike depth estimation over traditional camera depth estimation, we contribute a spike-depth dataset named CitySpike20K, which contains 20K paired samples, for spike depth estimation. UGDF achieves state-of-the-art results on CitySpike20K, surpassing all monocular or stereo spike depth estimation baselines. We conduct extensive experiments to evaluate the effectiveness and generalization of our method on CitySpike20K. To the best of our knowledge, our framework is the first dual-task fusion framework for spike camera depth estimation. Code and dataset will be released.

Zhibo Liu, Yuanyuan Yuan, Shuai Wang et al.

Due to their widespread use on heterogeneous hardware devices, deep learning (DL) models are compiled into executables by DL compilers to fully leverage low-level hardware primitives. This approach allows DL computations to be undertaken at low cost across a variety of computing platforms, including CPUs, GPUs, and various hardware accelerators. We present BTD (Bin to DNN), a decompiler for deep neural network (DNN) executables. BTD takes DNN executables and outputs full model specifications, including types of DNN operators, network topology, dimensions, and parameters that are (nearly) identical to those of the input models. BTD delivers a practical framework to process DNN executables compiled by different DL compilers and with full optimizations enabled on x86 platforms. It employs learning-based techniques to infer DNN operators, dynamic analysis to reveal network architectures, and symbolic execution to facilitate inferring dimensions and parameters of DNN operators. Our evaluation reveals that BTD enables accurate recovery of full specifications of complex DNNs with millions of parameters (e.g., ResNet). The recovered DNN specifications can be re-compiled into a new DNN executable exhibiting identical behavior to the input executable. We show that BTD can boost two representative attacks, adversarial example generation and knowledge stealing, against DNN executables. We also demonstrate cross-architecture legacy code reuse using BTD, and envision BTD being used for other critical downstream tasks like DNN security hardening and patching.

Lei Ma, Jinyang Liu, Tieying Zhang et al.

Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure is lost when stored as flat sequences. As a result, state-of-the-art methods often miss true dependencies within executions while learning spurious correlations across unrelated events. We propose KRONE, the first hierarchical anomaly detection framework that automatically derives execution hierarchies from flat logs to enable modular, multi-level anomaly detection. At its core, the KRONE Log Abstraction Model extracts application-specific semantic hierarchies, which are used to recursively decompose log sequences into coherent execution units, referred to as KRONE Seqs. This transforms sequence-level detection into a set of modular KRONE Seq-level detection tasks. For each test KRONE Seq, KRONE adopts a hybrid modular detection strategy that routes between an efficient level-independent Local-Context detector for rapid filtering and a Nested-Aware detector that captures cross-level semantic dependencies, augmented with LLM-based anomaly detection and explanation. KRONE further optimizes detection through cached result reuse and early-exit strategies along the hierarchy. Experiments on three public benchmarks and one industrial dataset from ByteDance Cloud demonstrate that KRONE achieves substantial improvements in accuracy (42.49% to 87.98%), F1 score, data efficiency (117.3x reduction), resource efficiency (43.7x reduction), and interpretability. KRONE improves F1-score by 10.07% (82.76% to 92.83%) over prior methods while reducing LLM usage to only 1.1% to 3.3% of the test data. Code: https://github.com/LeiMa0324/KRONE Demo: https://leima0324.github.io/KRONE_Demo_official/

Qiang Hu, Yuejun Guo, Xiaofei Xie et al.

Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation. Although DL has been becoming a driving force for large-scale source code analysis in the big code era, limited progress has been made on distribution shift analysis and benchmarking for source code tasks. To fill this gap, this paper initiates to propose CodeS, a distribution shift benchmark dataset, for source code learning. Specifically, CodeS supports two programming languages (Java and Python) and five shift types (task, programmer, time-stamp, token, and concrete syntax tree). Extensive experiments based on CodeS reveal that 1) out-of-distribution detectors from other domains (e.g., computer vision) do not generalize to source code, 2) all code classification models suffer from distribution shifts, 3) representation-based shifts have a higher impact on the model than others, and 4) pre-trained bimodal models are relatively more resistant to distribution shifts.

Zhuo Li, Derui Zhu, Yujing Hu et al.

Existing Deep Reinforcement Learning (DRL) algorithms suffer from sample inefficiency. Generally, episodic control-based approaches are solutions that leverage highly-rewarded past experiences to improve sample efficiency of DRL algorithms. However, previous episodic control-based approaches fail to utilize the latent information from the historical behaviors (e.g., state transitions, topological similarities, etc.) and lack scalability during DRL training. This work introduces Neural Episodic Control with State Abstraction (NECSA), a simple but effective state abstraction-based episodic control containing a more comprehensive episodic memory, a novel state evaluation, and a multi-step state analysis. We evaluate our approach to the MuJoCo and Atari tasks in OpenAI gym domains. The experimental results indicate that NECSA achieves higher sample efficiency than the state-of-the-art episodic control-based approaches. Our data and code are available at the project website\footnote{\url{https://sites.google.com/view/drl-necsa}}.

Wenqiang Zu, Shenghao Xie, Qing Zhao et al.

Foundation models pre-trained on large-scale data have been widely witnessed to achieve success in various natural imaging downstream tasks. Parameter-efficient fine-tuning (PEFT) methods aim to adapt foundation models to new domains by updating only a small portion of parameters in order to reduce computational overhead. However, the effectiveness of these PEFT methods, especially in cross-domain few-shot scenarios, e.g., medical image analysis, has not been fully explored. In this work, we facilitate the study of the performance of PEFT when adapting foundation models to medical image classification tasks. Furthermore, to alleviate the limitations of prompt introducing ways and approximation capabilities on Transformer architectures of mainstream prompt tuning methods, we propose the Embedded Prompt Tuning (EPT) method by embedding prompt tokens into the expanded channels. We also find that there are anomalies in the feature space distribution of foundation models during pre-training process, and prompt tuning can help mitigate this negative impact. To explain this phenomenon, we also introduce a novel perspective to understand prompt tuning: Prompt tuning is a distribution calibrator. And we support it by analyzing patch-wise scaling and feature separation operations contained in EPT. Our experiments show that EPT outperforms several state-of-the-art fine-tuning methods by a significant margin on few-shot medical image classification tasks, and completes the fine-tuning process within highly competitive time, indicating EPT is an effective PEFT method. The source code is available at github.com/zuwenqiang/EPT.

Xuhong Ren, Jianlang Chen, Felix Juefei-Xu et al.

Network architecture search (NAS), in particular the differentiable architecture search (DARTS) method, has shown a great power to learn excellent model architectures on the specific dataset of interest. In contrast to using a fixed dataset, in this work, we focus on a different but important scenario for NAS: how to refine a deployed network's model architecture to enhance its robustness with the guidance of a few collected and misclassified examples that are degraded by some real-world unknown corruptions having a specific pattern (e.g., noise, blur, etc.). To this end, we first conduct an empirical study to validate that the model architectures can be definitely related to the corruption patterns. Surprisingly, by just adding a few corrupted and misclassified examples (e.g., $10^3$ examples) to the clean training dataset (e.g., $5.0 \times 10^4$ examples), we can refine the model architecture and enhance the robustness significantly. To make it more practical, the key problem, i.e., how to select the proper failure examples for the effective NAS guidance, should be carefully investigated. Then, we propose a novel core-failure-set guided DARTS that embeds a K-center-greedy algorithm for DARTS to select suitable corrupted failure examples to refine the model architecture. We use our method for DARTS-refined DNNs on the clean as well as 15 corruptions with the guidance of four specific real-world corruptions. Compared with the state-of-the-art NAS as well as data-augmentation-based enhancement methods, our final method can achieve higher accuracy on both corrupted datasets and the original clean dataset. On some of the corruption patterns, we can achieve as high as over 45% absolute accuracy improvements.

Zhongyu Fang, Aoyun He, Qihui Yu et al.

Multimodal emotion analysis performed better in emotion recognition depending on more comprehensive emotional clues and multimodal emotion dataset. In this paper, we developed a large multimodal emotion dataset, named "HED" dataset, to facilitate the emotion recognition task, and accordingly propose a multimodal emotion recognition method. To promote recognition accuracy, "Feature After Feature" framework was used to explore crucial emotional information from the aligned face, body and text samples. We employ various benchmarks to evaluate the "HED" dataset and compare the performance with our method. The results show that the five classification accuracy of the proposed multimodal fusion method is about 83.75%, and the performance is improved by 1.83%, 9.38%, and 21.62% respectively compared with that of individual modalities. The complementarity between each channel is effectively used to improve the performance of emotion recognition. We had also established a multimodal online emotion prediction platform, aiming to provide free emotion prediction to more users.

Yu Pan, Yanni Hu, Yuguang Yang et al.

Contrastive cross-modality pretraining has recently exhibited impressive success in diverse fields, whereas there is limited research on their merits in speech emotion recognition (SER). In this paper, we propose GEmo-CLAP, a kind of gender-attribute-enhanced contrastive language-audio pretraining (CLAP) method for SER. Specifically, we first construct an effective emotion CLAP (Emo-CLAP) for SER, using pre-trained text and audio encoders. Second, given the significance of gender information in SER, two novel multi-task learning based GEmo-CLAP (ML-GEmo-CLAP) and soft label based GEmo-CLAP (SL-GEmo-CLAP) models are further proposed to incorporate gender information of speech signals, forming more reasonable objectives. Experiments on IEMOCAP indicate that our proposed two GEmo-CLAPs consistently outperform Emo-CLAP with different pre-trained models. Remarkably, the proposed WavLM-based SL-GEmo-CLAP obtains the best WAR of 83.16\%, which performs better than state-of-the-art SER methods.

Xinyu Gao, Zhijie Wang, Yang Feng et al.

Multi-Sensor Fusion (MSF) based perception systems have been the foundation in supporting many industrial applications and domains, such as self-driving cars, robotic arms, and unmanned aerial vehicles. Over the past few years, the fast progress in data-driven artificial intelligence (AI) has brought a fast-increasing trend to empower MSF systems by deep learning techniques to further improve performance, especially on intelligent systems and their perception systems. Although quite a few AI-enabled MSF perception systems and techniques have been proposed, up to the present, limited benchmarks that focus on MSF perception are publicly available. Given that many intelligent systems such as self-driving cars are operated in safety-critical contexts where perception systems play an important role, there comes an urgent need for a more in-depth understanding of the performance and reliability of these MSF systems. To bridge this gap, we initiate an early step in this direction and construct a public benchmark of AI-enabled MSF-based perception systems including three commonly adopted tasks (i.e., object detection, object tracking, and depth completion). Based on this, to comprehensively understand MSF systems' robustness and reliability, we design 14 common and realistic corruption patterns to synthesize large-scale corrupted datasets. We further perform a systematic evaluation of these systems through our large-scale evaluation. Our results reveal the vulnerability of the current AI-enabled MSF perception systems, calling for researchers and practitioners to take robustness and reliability into account when designing AI-enabled MSF.

Lei Ma, Jincong Han, Zhaoxin Wang et al. · pku

Large-scale multimodal language models (LMMs) have achieved remarkable success in general domains. However, the exploration of diagnostic language models based on multimodal cephalometric medical data remains limited. In this paper, we propose a novel multimodal cephalometric analysis and diagnostic dialogue model. Firstly, a multimodal orthodontic medical dataset is constructed, comprising cephalometric images and doctor-patient dialogue data, with automatic analysis of cephalometric landmarks using U-net and generation of diagnostic reports. Then, the cephalometric dataset and generated diagnostic reports are separately fine-tuned on Minigpt-4 and VisualGLM. Results demonstrate that the CephGPT-4 model exhibits excellent performance and has the potential to revolutionize orthodontic measurement and diagnostic applications. These innovations hold revolutionary application potential in the field of orthodontics.

Peng Xue, Jingyang Zhang, Lei Ma et al.

Image registration of liver dynamic contrast-enhanced computed tomography (DCE-CT) is crucial for diagnosis and image-guided surgical planning of liver cancer. However, intensity variations due to the flow of contrast agents combined with complex spatial motion induced by respiration brings great challenge to existing intensity-based registration methods. To address these problems, we propose a novel structure-aware registration method by incorporating structural information of related organs with segmentation-guided deep registration network. Existing segmentation-guided registration methods only focus on volumetric registration inside the paired organ segmentations, ignoring the inherent attributes of their anatomical structures. In addition, such paired organ segmentations are not always available in DCE-CT images due to the flow of contrast agents. Different from existing segmentation-guided registration methods, our proposed method extracts structural information in hierarchical geometric perspectives of line and surface. Then, according to the extracted structural information, structure-aware constraints are constructed and imposed on the forward and backward deformation field simultaneously. In this way, all available organ segmentations, including unpaired ones, can be fully utilized to avoid the side effect of contrast agent and preserve the topology of organs during registration. Extensive experiments on an in-house liver DCE-CT dataset and a public LiTS dataset show that our proposed method can achieve higher registration accuracy and preserve anatomical structure more effectively than state-of-the-art methods.

Zhijie Wang, Yuheng Huang, Lei Ma et al.

Deep learning (DL) has become a driving force and has been widely adopted in many domains and applications with competitive performance. In practice, to solve the nontrivial and complicated tasks in real-world applications, DL is often not used standalone, but instead contributes as a piece of gadget of a larger complex AI system. Although there comes a fast increasing trend to study the quality issues of deep neural networks (DNNs) at the model level, few studies have been performed to investigate the quality of DNNs at both the unit level and the potential impacts on the system level. More importantly, it also lacks systematic investigation on how to perform the risk assessment for AI systems from unit level to system level. To bridge this gap, this paper initiates an early exploratory study of AI system risk assessment from both the data distribution and uncertainty angles to address these issues. We propose a general framework with an exploratory study for analyzing AI systems. After large-scale (700+ experimental configurations and 5000+ GPU hours) experiments and in-depth investigations, we reached a few key interesting findings that highlight the practical need and opportunities for more in-depth investigations into AI systems.

Yu Pan, Yuguang Yang, Yuheng Huang et al.

Despite notable progress, speech emotion recognition (SER) remains challenging due to the intricate and ambiguous nature of speech emotion, particularly in wild world. While current studies primarily focus on recognition and generalization abilities, our research pioneers an investigation into the reliability of SER methods in the presence of semantic data shifts and explores how to exert fine-grained control over various attributes inherent in speech signals to enhance speech emotion modeling. In this paper, we first introduce MSAC-SERNet, a novel unified SER framework capable of simultaneously handling both single-corpus and cross-corpus SER. Specifically, concentrating exclusively on the speech emotion attribute, a novel CNN-based SER model is presented to extract discriminative emotional representations, guided by additive margin softmax loss. Considering information overlap between various speech attributes, we propose a novel learning paradigm based on correlations of different speech attributes, termed Multiple Speech Attribute Control (MSAC), which empowers the proposed SER model to simultaneously capture fine-grained emotion-related features while mitigating the negative impact of emotion-agnostic representations. Furthermore, we make a first attempt to examine the reliability of the MSAC-SERNet framework using out-of-distribution detection methods. Experiments on both single-corpus and cross-corpus SER scenarios indicate that MSAC-SERNet not only consistently outperforms the baseline in all aspects, but achieves superior performance compared to state-of-the-art SER approaches.

Zhehua Zhou, Jiayang Song, Kunpeng Yao et al.

Motivated by the substantial achievements observed in Large Language Models (LLMs) in the field of natural language processing, recent research has commenced investigations into the application of LLMs for complex, long-horizon sequential task planning challenges in robotics. LLMs are advantageous in offering the potential to enhance the generalizability as task-agnostic planners and facilitate flexible interaction between human instructors and planning systems. However, task plans generated by LLMs often lack feasibility and correctness. To address this challenge, we introduce ISR-LLM, a novel framework that improves LLM-based planning through an iterative self-refinement process. The framework operates through three sequential steps: preprocessing, planning, and iterative self-refinement. During preprocessing, an LLM translator is employed to convert natural language input into a Planning Domain Definition Language (PDDL) formulation. In the planning phase, an LLM planner formulates an initial plan, which is then assessed and refined in the iterative self-refinement step by using a validator. We examine the performance of ISR-LLM across three distinct planning domains. The results show that ISR-LLM is able to achieve markedly higher success rates in task accomplishments compared to state-of-the-art LLM-based planners. Moreover, it also preserves the broad applicability and generalizability of working with natural language instructions.

Yuheng Huang, Jiayang Song, Zhijie Wang et al.

The recent performance leap of Large Language Models (LLMs) opens up new opportunities across numerous industrial applications and domains. However, erroneous generations, such as false predictions, misinformation, and hallucination made by LLMs, have also raised severe concerns for the trustworthiness of LLMs', especially in safety-, security- and reliability-sensitive scenarios, potentially hindering real-world adoptions. While uncertainty estimation has shown its potential for interpreting the prediction risks made by general machine learning (ML) models, little is known about whether and to what extent it can help explore an LLM's capabilities and counteract its undesired behavior. To bridge the gap, in this paper, we initiate an exploratory study on the risk assessment of LLMs from the lens of uncertainty. In particular, we experiment with twelve uncertainty estimation methods and four LLMs on four prominent natural language processing (NLP) tasks to investigate to what extent uncertainty estimation techniques could help characterize the prediction risks of LLMs. Our findings validate the effectiveness of uncertainty estimation for revealing LLMs' uncertain/non-factual predictions. In addition to general NLP tasks, we extensively conduct experiments with four LLMs for code generation on two datasets. We find that uncertainty estimation can potentially uncover buggy programs generated by LLMs. Insights from our study shed light on future design and development for reliable LLMs, facilitating further research toward enhancing the trustworthiness of LLMs.

Yiming Liang, Ge Zhang, Xingwei Qu et al.

Large Language Models (LLMs) have achieved significant advancements, however, the common learning paradigm treats LLMs as passive information repositories, neglecting their potential for active learning and alignment. Some approaches train LLMs using their own generated synthetic data, exploring the possibility of active alignment. However, there is still a huge gap between these one-time alignment methods and the continuous automatic alignment of humans. In this paper, we introduce \textbf{I-SHEEP}, an \textbf{I}terative \textbf{S}elf-En\textbf{H}anc\textbf{E}m\textbf{E}nt \textbf{P}aradigm.This human-like paradigm enables LLMs to \textbf{continuously self-align from scratch with nothing}. Compared to the one-time alignment method Dromedary \cite{sun2023principledriven}, which refers to the first iteration in this paper, I-SHEEP can significantly enhance capacities on both Qwen and Llama models. I-SHEEP achieves a maximum relative improvement of 78.2\% in the Alpaca Eval, 24.0\% in the MT Bench, and an absolute increase of 8.88\% in the IFEval accuracy over subsequent iterations in Qwen-1.5 72B model. Additionally, I-SHEEP surpasses the base model in various standard benchmark generation tasks, achieving an average improvement of 24.77\% in code generation tasks, 12.04\% in TrivialQA, and 20.29\% in SQuAD. We also provide new insights based on the experiment results. Our codes, datasets, and models are available at \textbf{https://anonymous.4open.science/r/I-SHEEP}.

Jiayang Song, Zhehua Zhou, Jiawei Liu et al.

Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large Language Models (LLMs) have been extensively adopted to address tasks demanding in-depth common-sense knowledge, such as reasoning and planning. Recognizing that reward function design is also inherently linked to such knowledge, LLM offers a promising potential in this context. Motivated by this, we propose in this work a novel LLM framework with a self-refinement mechanism for automated reward function design. The framework commences with the LLM formulating an initial reward function based on natural language inputs. Then, the performance of the reward function is assessed, and the results are presented back to the LLM for guiding its self-refinement process. We examine the performance of our proposed framework through a variety of continuous robotic control tasks across three diverse robotic systems. The results indicate that our LLM-designed reward functions are able to rival or even surpass manually designed reward functions, highlighting the efficacy and applicability of our approach.

Renzhi Wang, Zhehua Zhou, Jiayang Song et al.

Cyber-Physical Systems (CPSs) are increasingly prevalent across various industrial and daily-life domains, with applications ranging from robotic operations to autonomous driving. With recent advancements in artificial intelligence (AI), learning-based components, especially AI controllers, have become essential in enhancing the functionality and efficiency of CPSs. However, the lack of interpretability in these AI controllers presents challenges to the safety and quality assurance of AI-enabled CPSs (AI-CPSs). Existing methods for improving the safety of AI controllers often involve neural network repair, which requires retraining with additional adversarial examples or access to detailed internal information of the neural network. Hence, these approaches have limited applicability for black-box policies, where only the inputs and outputs are accessible during operation. To overcome this, we propose MORTAR, a runtime action repair framework designed for AI-CPSs in this work. MORTAR begins by constructing a prediction model that forecasts the quality of actions proposed by the AI controller. If an unsafe action is detected, MORTAR then initiates a repair process to correct it. The generation of repaired actions is achieved through an optimization process guided by the safety estimates from the prediction model. We evaluate the effectiveness of MORTAR across various CPS tasks and AI controllers. The results demonstrate that MORTAR can efficiently improve task completion rates of AI controllers under specified safety specifications. Meanwhile, it also maintains minimal computational overhead, ensuring real-time operation of the AI-CPSs.

Da Song, Yuheng Huang, Boqi Chen et al.

The integration of large language models (LLMs) into autonomous agents has enabled complex tool use, yet in high-stakes domains, these systems must strictly adhere to regulatory standards beyond simple functional correctness. However, existing benchmarks often overlook implicit regulatory compliance, thus failing to evaluate whether LLMs can autonomously enforce mandatory safety constraints. To fill this gap, we introduce LogiSafetyGen, a framework that converts unstructured regulations into Linear Temporal Logic oracles and employs logic-guided fuzzing to synthesize valid, safety-critical traces. Building on this framework, we construct LogiSafetyBench, a benchmark comprising 240 human-verified tasks that require LLMs to generate Python programs that satisfy both functional objectives and latent compliance rules. Evaluations of 13 state-of-the-art (SOTA) LLMs reveal that larger models, despite achieving better functional correctness, frequently prioritize task completion over safety, which results in non-compliant behavior.

Da Song, Xuan Xie, Jiayang Song et al.

Over the past decade, Artificial Intelligence (AI) has had great success recently and is being used in a wide range of academic and industrial fields. More recently, LLMs have made rapid advancements that have propelled AI to a new level, enabling even more diverse applications and industrial domains with intelligence, particularly in areas like software engineering and natural language processing. Nevertheless, a number of emerging trustworthiness concerns and issues exhibited in LLMs have already recently received much attention, without properly solving which the widespread adoption of LLMs could be greatly hindered in practice. The distinctive characteristics of LLMs, such as the self-attention mechanism, extremely large model scale, and autoregressive generation schema, differ from classic AI software based on CNNs and RNNs and present new challenges for quality analysis. Up to the present, it still lacks universal and systematic analysis techniques for LLMs despite the urgent industrial demand. Towards bridging this gap, we initiate an early exploratory study and propose a universal analysis framework for LLMs, LUNA, designed to be general and extensible, to enable versatile analysis of LLMs from multiple quality perspectives in a human-interpretable manner. In particular, we first leverage the data from desired trustworthiness perspectives to construct an abstract model as an auxiliary analysis asset, which is empowered by various abstract model construction methods. To assess the quality of the abstract model, we collect and define a number of evaluation metrics, aiming at both abstract model level and the semantics level. Then, the semantics, which is the degree of satisfaction of the LLM w.r.t. the trustworthiness perspective, is bound to and enriches the abstract model with semantics, which enables more detailed analysis applications for diverse purposes.

Yuheng Huang, Jiayang Song, Qiang Hu et al.

Performance evaluation plays a crucial role in the development life cycle of large language models (LLMs). It estimates the model's capability, elucidates behavior characteristics, and facilitates the identification of potential issues and limitations, thereby guiding further improvement. Given that LLMs' diverse task-handling abilities stem from large volumes of training data, a comprehensive evaluation also necessitates abundant, well-annotated, and representative test data to assess LLM performance across various downstream tasks. However, the demand for high-quality test data often entails substantial time, computational resources, and manual efforts, sometimes causing the evaluation to be inefficient or impractical. To address these challenges, researchers propose active testing, which estimates the overall performance by selecting a subset of test data. Nevertheless, the existing active testing methods tend to be inefficient, even inapplicable, given the unique new challenges of LLMs (e.g., diverse task types, increased model complexity, and unavailability of training data). To mitigate such limitations and expedite the development cycle of LLMs, in this work, we introduce AcTracer, an active testing framework tailored for LLMs that strategically selects a small subset of test data to achieve a more accurate performance estimation for LLMs. AcTracer utilizes both internal and external information from LLMs to guide the test sampling process, reducing variance through a multi-stage pool-based active selection. Our experiment results demonstrate that AcTracer achieves state-of-the-art performance compared to existing methods across various tasks.

Lei Ma, Peng Xue, Yuning Gu et al.

In recent years, the demand for dental implants has surged, driven by their high success rates and esthetic advantages. However, accurate prediction of missing teeth for precise digital implant planning remains a challenge due to the intricate nature of dental structures and the variability in tooth loss patterns. This study presents a novel framework for accurate prediction of missing teeth in different patterns, facilitating digital implant planning. The proposed framework begins by estimating point-to-point correspondence among a dataset of dental mesh models reconstructed from CBCT images of healthy subjects. Subsequently, tooth dictionaries are constructed for each tooth type, encoding their position and shape information based on the established point-to-point correspondence. To predict missing teeth in a given dental mesh model, sparse coefficients are learned by sparsely representing adjacent teeth of the missing teeth using the corresponding tooth dictionaries. These coefficients are then applied to the dictionaries of the missing teeth to generate accurate predictions of their positions and shapes. The evaluation results on real subjects shows that our proposed framework achieves an average prediction error of 1.04mm for predictions of single missing tooth and an average prediction error of 1.33mm for the prediction of 14 missing teeth, which demonstrates its capability of accurately predicting missing teeth in various patterns. By accurately predicting missing teeth, dental professionals can improve the planning and placement of dental implants, leading to better esthetic and functional outcomes for patients undergoing dental implant procedures.

Jiayang Song, Yuheng Huang, Zhehua Zhou et al.

As safety remains a crucial concern throughout the development lifecycle of Large Language Models (LLMs), researchers and industrial practitioners have increasingly focused on safeguarding and aligning LLM behaviors with human preferences and ethical standards. LLMs, trained on extensive multilingual corpora, exhibit powerful generalization abilities across diverse languages and domains. However, current safety alignment practices predominantly focus on single-language scenarios, which leaves their effectiveness in complex multilingual contexts, especially for those complex mixed-language formats, largely unexplored. In this study, we introduce Multilingual Blending, a mixed-language query-response scheme designed to evaluate the safety alignment of various state-of-the-art LLMs (e.g., GPT-4o, GPT-3.5, Llama3) under sophisticated, multilingual conditions. We further investigate language patterns such as language availability, morphology, and language family that could impact the effectiveness of Multilingual Blending in compromising the safeguards of LLMs. Our experimental results show that, without meticulously crafted prompt templates, Multilingual Blending significantly amplifies the detriment of malicious queries, leading to dramatically increased bypass rates in LLM safety alignment (67.23% on GPT-3.5 and 40.34% on GPT-4o), far exceeding those of single-language baselines. Moreover, the performance of Multilingual Blending varies notably based on intrinsic linguistic properties, with languages of different morphology and from diverse families being more prone to evading safety alignments. These findings underscore the necessity of evaluating LLMs and developing corresponding safety alignment strategies in a complex, multilingual context to align with their superior cross-language generalization capabilities.

Bonan Kou, Shengmai Chen, Zhijie Wang et al.

Large Language Models (LLMs) have recently been widely used for code generation. Due to the complexity and opacity of LLMs, little is known about how these models generate code. We made the first attempt to bridge this knowledge gap by investigating whether LLMs attend to the same parts of a task description as human programmers during code generation. An analysis of six LLMs, including GPT-4, on two popular code generation benchmarks revealed a consistent misalignment between LLMs' and programmers' attention. We manually analyzed 211 incorrect code snippets and found five attention patterns that can be used to explain many code generation errors. Finally, a user study showed that model attention computed by a perturbation-based method is often favored by human programmers. Our findings highlight the need for human-aligned LLMs for better interpretability and programmer trust.

Lei Ma, Suhani Chaudhary, Ethan Shanbaum et al.

Logs are ubiquitous in modern systems. Unfortunately, their unstructured nature in flat sequences limits understanding of execution behaviors, hindering effective anomaly diagnosis. To address this, Krone introduces a novel hierarchical log abstraction that transforms flat log sequences into semantically coherent units across entity, action, and status levels. Building on this abstraction, Krone introduces a hierarchical orchestration framework that decomposes flat log sequences into hierarchical execution units and performs modular detection over them. It executes and optimizes the modular detection tasks across levels, enabling precise anomaly detection, localization, and explanation with selective invocation of LLM-based reasoning. In this work, we present Krone-viz, an interactive visualization system based on Krone, which makes hierarchical log analysis interpretable and actionable for software engineers and system operators. Demonstrated on the widely used HDFS benchmark dataset, Krone-viz supports: 1) examining hierarchical decompositions of flat log sequences, 2) inspecting detection results and abnormal segments identified by Krone with LLM-generated explanations, and 3) reusing, reviewing, and revising knowledge generated by LLMs with human-in-the-loop guardrails. The code of Krone-viz is available at https://github.com/LeiMa0324/KRONE_Demo_official, and we deploy a live demo at https://leima0324.github.io/KRONE_Demo_official.

Da Song, Zhijie Wang, Yuheng Huang et al.

Machine Learning (ML) has been widely used in Natural Language Processing (NLP) applications. A fundamental assumption in ML is that training data and real-world data should follow a similar distribution. However, a deployed ML model may suffer from out-of-distribution (OOD) issues due to distribution shifts in the real-world data. Though many algorithms have been proposed to detect OOD data from text corpora, there is still a lack of interactive tool support for ML developers. In this work, we propose DeepLens, an interactive system that helps users detect and explore OOD issues in massive text corpora. Users can efficiently explore different OOD types in DeepLens with the help of a text clustering method. Users can also dig into a specific text by inspecting salient words highlighted through neuron activation analysis. In a within-subjects user study with 24 participants, participants using DeepLens were able to find nearly twice more types of OOD issues accurately with 22% more confidence compared with a variant of DeepLens that has no interaction or visualization support.

Yijia Guo, Yuanxi Bai, Liwen Hu et al.

We proposed Precomputed RadianceTransfer of GaussianSplats (PRTGS), a real-time high-quality relighting method for Gaussian splats in low-frequency lighting environments that captures soft shadows and interreflections by precomputing 3D Gaussian splats' radiance transfer. Existing studies have demonstrated that 3D Gaussian splatting (3DGS) outperforms neural fields' efficiency for dynamic lighting scenarios. However, the current relighting method based on 3DGS still struggles to compute high-quality shadow and indirect illumination in real time for dynamic light, leading to unrealistic rendering results. We solve this problem by precomputing the expensive transport simulations required for complex transfer functions like shadowing, the resulting transfer functions are represented as dense sets of vectors or matrices for every Gaussian splat. We introduce distinct precomputing methods tailored for training and rendering stages, along with unique ray tracing and indirect lighting precomputation techniques for 3D Gaussian splats to accelerate training speed and compute accurate indirect lighting related to environment light. Experimental analyses demonstrate that our approach achieves state-of-the-art visual quality while maintaining competitive training times and allows high-quality real-time (30+ fps) relighting for dynamic light and relatively complex scenes at 1080p resolution.

Yuchen Tian, Weixiang Yan, Qian Yang et al. · berkeley, mila

Large Language Models (LLMs) have made significant progress in code generation, offering developers groundbreaking automated programming support. However, LLMs often generate code that is syntactically correct and even semantically plausible, but may not execute as expected or fulfill specified requirements. This phenomenon of hallucinations in the code domain has not been systematically explored. To advance the community's understanding and research on this issue, we introduce the concept of code hallucinations and propose a classification method for code hallucination based on execution verification. We categorize code hallucinations into four main types: mapping, naming, resource, and logic hallucinations, with each category further divided into different subcategories to understand and address the unique challenges faced by LLMs in code generation with finer granularity. Additionally, we present a dynamic detection algorithm called CodeHalu designed to detect and quantify code hallucinations. We also introduce the CodeHaluEval benchmark, which includes 8,883 samples from 699 tasks, to systematically and quantitatively evaluate code hallucinations. By evaluating 17 popular LLMs using this benchmark, we reveal significant differences in their accuracy and reliability in code generation, offering detailed insights for further improving the code generation capabilities of LLMs. The CodeHalu benchmark and code are publicly available at https://github.com/yuchen814/CodeHalu.

Shengyi Hua, Fang Yan, Tianle Shen et al.

Large amounts of digitized histopathological data display a promising future for developing pathological foundation models via self-supervised learning methods. Foundation models pretrained with these methods serve as a good basis for downstream tasks. However, the gap between natural and histopathological images hinders the direct application of existing methods. In this work, we present PathoDuet, a series of pretrained models on histopathological images, and a new self-supervised learning framework in histopathology. The framework is featured by a newly-introduced pretext token and later task raisers to explicitly utilize certain relations between images, like multiple magnifications and multiple stains. Based on this, two pretext tasks, cross-scale positioning and cross-stain transferring, are designed to pretrain the model on Hematoxylin and Eosin (H&E) images and transfer the model to immunohistochemistry (IHC) images, respectively. To validate the efficacy of our models, we evaluate the performance over a wide variety of downstream tasks, including patch-level colorectal cancer subtyping and whole slide image (WSI)-level classification in H&E field, together with expression level prediction of IHC marker, tumor identification and slide-level qualitative analysis in IHC field. The experimental results show the superiority of our models over most tasks and the efficacy of proposed pretext tasks. The codes and models are available at https://github.com/openmedlab/PathoDuet.

Jingyu Zhang, Fan Wang, Jacky Keung et al.

Deep learning (DL)-based systems can exhibit unexpected behavior when exposed to out-of-distribution (OOD) scenarios, posing serious risks in safety-critical domains such as malware detection and autonomous driving. This underscores the importance of thoroughly testing such systems before deployment. To this end, researchers have proposed a wide range of test selection metrics designed to effectively select inputs. However, prior evaluations of metrics reveal three key limitations: (1) narrow testing objectives, for example, many studies assess metrics only for fault detection, leaving their effectiveness for performance estimation unclear; (2) limited coverage of OOD scenarios, with natural and label shifts are rarely considered; (3) Biased dataset selection, where most work focuses on image data while other modalities remain underexplored. Consequently, a unified benchmark that examines how these metrics perform under multiple testing objectives, diverse OOD scenarios, and different data modalities is still lacking. This leaves practitioners uncertain about which test selection metrics are most suitable for their specific objectives and contexts. To address this gap, we conduct an extensive empirical study of 15 existing metrics, evaluating them under three testing objectives (fault detection, performance estimation, and retraining guidance), five types of OOD scenarios (corrupted, adversarial, temporal, natural, and label shifts), three data modalities (image, text, and Android packages), and 13 DL models. In total, our study encompasses 1,640 experimental scenarios, offering a comprehensive evaluation and statistical analysis.

Derui Zhu, Dingfan Chen, Qing Li et al.

Despite tremendous advancements in large language models (LLMs) over recent years, a notably urgent challenge for their practical deployment is the phenomenon of hallucination, where the model fabricates facts and produces non-factual statements. In response, we propose PoLLMgraph, a Polygraph for LLMs, as an effective model-based white-box detection and forecasting approach. PoLLMgraph distinctly differs from the large body of existing research that concentrates on addressing such challenges through black-box evaluations. In particular, we demonstrate that hallucination can be effectively detected by analyzing the LLM's internal state transition dynamics during generation via tractable probabilistic models. Experimental results on various open-source LLMs confirm the efficacy of PoLLMgraph, outperforming state-of-the-art methods by a considerable margin, evidenced by over 20% improvement in AUC-ROC on common benchmarking datasets like TruthfulQA. Our work paves a new way for model-based white-box analysis of LLMs, motivating the research community to further explore, understand, and refine the intricate dynamics of LLM behaviors.

Xiongfei Wu, Mingfei Cheng, Xiaoning Ren et al.

Recent advances in foundation models (FMs), including large language models (LLMs), vision-language models (VLMs), and world models, have opened new opportunities for autonomous driving systems (ADSs) in perception, reasoning, decision-making, and interaction. However, ADSs are safety-critical cyber-physical systems, and integrating FMs into them raises substantial software engineering challenges in data curation, system design, deployment, evaluation, and assurance. To clarify this rapidly evolving landscape, we present an initial roadmap, grounded in a structured literature review, for integrating FMs into autonomous driving across three dimensions: FM infrastructure, in-vehicle integration, and practical deployment. For each dimension, we summarize the state of the art, identify key challenges, and highlight open research opportunities. Based on this analysis, we outline research directions for building reliable, safe, and trustworthy FM-enabled ADSs.