Zhenyu Chen

Jiawen Zhu, Zhenyu Chen, Zeqi Hao et al.

Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment Anything Model (SAM) attracts much attention. In this report, we propose HQTrack, a framework for High Quality Tracking anything in videos. HQTrack mainly consists of a video multi-object segmenter (VMOS) and a mask refiner (MR). Given the object to be tracked in the initial frame of a video, VMOS propagates the object masks to the current frame. The mask results at this stage are not accurate enough since VMOS is trained on several closeset video object segmentation (VOS) datasets, which has limited ability to generalize to complex and corner scenes. To further improve the quality of tracking masks, a pretrained MR model is employed to refine the tracking results. As a compelling testament to the effectiveness of our paradigm, without employing any tricks such as test-time data augmentations and model ensemble, HQTrack ranks the 2nd place in the Visual Object Tracking and Segmentation (VOTS2023) challenge. Code and models are available at https://github.com/jiawen-zhu/HQTrack.

Quanjun Zhang, Chengyu Gao, Yu Han et al.

Large Language Models (LLMs) have enabled intelligent agents that autonomously interact with environments and invoke external tools. Recently, agent-based software repair has drawn wide attention, as repair agents can localize bugs, generate patches, and achieve state-of-the-art performance on repository-level benchmarks (e.g., SWE-Bench). However, existing approaches usually adopt a localize-then-fix paradigm, jumping directly from "where the bug is" to "how to fix it", leaving a fundamental reasoning gap. To this end, we propose SGAgent, a Suggestion-Guided multi-Agent framework for repository-level software repair, which follows a localize-suggest-fix paradigm. SGAgent introduces a suggestion phase to strengthen the transition from localization to repair: the suggester starts from the buggy locations, incrementally retrieves relevant context until it fully understands the bug, and provides actionable repair suggestions. We further construct a Knowledge Graph (KG) from the target repository and develop a KG-based toolkit to strengthen SGAgent's global contextual awareness and repository-level reasoning. Three specialized sub-agents (i.e., localizer, suggester, and fixer) collaborate to achieve automated end-to-end software repair. We evaluate SGAgent on SWE-Bench-Lite. SGAgent with Claude-3.5 achieves 51.3% repair accuracy, 81.2% file-level, and 52.4% function-level localization accuracy at an average cost of $1.48 per instance, outperforming all baselines using the same base model. SGAgent also generalizes well across base LLMs, reaching a 60.7% resolution rate with Claude-4. When extended to vulnerability repair, it achieves 48.0% on VUL4J and VJBench, demonstrating strong generalization across tasks and programming languages.

Sirui Liu, Jun Zhang, Haotian Chu et al.

Proteins are essential component of human life and their structures are important for function and mechanism analysis. Recent work has shown the potential of AI-driven methods for protein structure prediction. However, the development of new models is restricted by the lack of dataset and benchmark training procedure. To the best of our knowledge, the existing open source datasets are far less to satisfy the needs of modern protein sequence-structure related research. To solve this problem, we present the first million-level protein structure prediction dataset with high coverage and diversity, named as PSP. This dataset consists of 570k true structure sequences (10TB) and 745k complementary distillation sequences (15TB). We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset. We validate the utility of this dataset for training by participating CAMEO contest in which our model won the first place. We hope our PSP dataset together with the training benchmark can enable a broader community of AI/biology researchers for AI-driven protein related research.

Yue Wang, Yuan Zhao, Shengcheng Yu et al.

Agentic AI is increasingly being integrated into software engineering workflows. In crowdsourced testing, however, the large volume and uneven quality of submitted reports still create a substantial review burden for developers. In prior work, we developed and validated a multi-agent assessment backbone based on the LLM-as-a-Judge paradigm. That backbone assesses reports along three dimensions--textuality, adequacy, and competitiveness--and was shown to align well with human consensus while substantially reducing assessment effort. Yet reliable automated judging does not by itself show whether agent outputs can improve human work when embedded into workflow. This paper studies that missing question in the context of crowdsourced testing. We investigate whether assessment-derived, actionable feedback can improve how testers revise reports, perform on later tasks, and transfer reporting practices across applications. To do so, we conducted a controlled four-stage human-subject study with 20 testers across three real-world applications. The results show that agent-generated feedback supports immediate improvements in revised reports, better first submissions on a new task after prior feedback exposure, and evidence of partial but meaningful transfer to a later application. A post-task questionnaire completed by 17 participants complements these artifact-based findings by suggesting that the feedback was generally understandable, acted upon in revision, and carried into later tasks, while also revealing remaining friction in specificity and execution. Overall, the study provides empirical evidence that, in the studied crowdsourced testing setting, assessment agents can serve not only as post-hoc judges but also as workflow-integrated feedback providers that support upstream report-quality improvement.

Tingxu Han, Yi Zhang, Wei Song et al.

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.

Yuchen Chen, Yuan Xiao, Chunrong Fang et al.

The proliferation of large language models for code (CodeLMs) and open-source contributions has heightened concerns over unauthorized use of source code datasets. While watermarking provides a viable protection mechanism by embedding ownership signals, existing methods rely on detectable trigger-target patterns and are limited to source-code tasks, overlooking other scenarios such as decompilation tasks. In this paper, we propose DuCodeMark, a stealthy and robust dual-purpose watermarking method for code datasets that generalizes across both source-code tasks and decompilation tasks. DuCodeMark parses each code sample into an abstract syntax tree (AST), applies language-specific style transformations to construct stealthy trigger-target pairs, and injects repressible poisoned features into a subset of return-typed samples to enhance robustness against watermark removal or evasion. These features remain inactive during normal training but are activated upon watermark removal, degrading model performance. For verification, DuCodeMark employs a black-box method based on the independent-samples $t$-test. We conduct a comprehensive evaluation of DuCodeMark across 72 settings spanning two code tasks, two programming languages, three CodeLMs, and six decoding temperatures. The results demonstrate that it consistently achieves strong verifiability ($p < 0.05$), high stealthiness (suspicion rate $\leq$ 0.36), robustness against both watermark and poisoning attacks (recall $\leq$ 0.57), and a substantial drop in model performance upon watermark removal (Pass@1 drops by 28.6%), underscoring its practicality and resilience.

Yuan Xiao, Yuchen Chen, Shiqing Ma et al.

The robustness of neural network classifiers is important in the safety-critical domain and can be quantified by robustness verification. At present, efficient and scalable verification techniques are always sound but incomplete, and thus, the improvement of verified robustness results is the key criterion to evaluate the performance of incomplete verification approaches. The multi-variate function MaxPool is widely adopted yet challenging to verify. In this paper, we present Ti-Lin, a robustness verifier for MaxPool-based CNNs with Tight Linear Approximation. Following the sequel of minimizing the over-approximation zone of the non-linear function of CNNs, we are the first to propose the provably neuron-wise tightest linear bounds for the MaxPool function. By our proposed linear bounds, we can certify larger robustness results for CNNs. We evaluate the effectiveness of Ti-Lin on different verification frameworks with open-sourced benchmarks, including LeNet, PointNet, and networks trained on the MNIST, CIFAR-10, Tiny ImageNet and ModelNet40 datasets. Experimental results show that Ti-Lin significantly outperforms the state-of-the-art methods across all networks with up to 78.6% improvement in terms of the certified accuracy with almost the same time consumption as the fastest tool. Our code is available at https://github.com/xiaoyuanpigo/Ti-Lin-Hybrid-Lin.

Weisong Sun, Yun Miao, Yuekang Li et al.

To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of code-related tasks. In this paper, we undertake a systematic and comprehensive study on code summarization in the era of LLMs, which covers multiple aspects involved in the workflow of LLM-based code summarization. Specifically, we begin by examining prevalent automated evaluation methods for assessing the quality of summaries generated by LLMs and find that the results of the GPT-4 evaluation method are most closely aligned with human evaluation. Then, we explore the effectiveness of five prompting techniques (zero-shot, few-shot, chain-of-thought, critique, and expert) in adapting LLMs to code summarization tasks. Contrary to expectations, advanced prompting techniques may not outperform simple zero-shot prompting. Next, we investigate the impact of LLMs' model settings (including top\_p and temperature parameters) on the quality of generated summaries. We find the impact of the two parameters on summary quality varies by the base LLM and programming language, but their impacts are similar. Moreover, we canvass LLMs' abilities to summarize code snippets in distinct types of programming languages. The results reveal that LLMs perform suboptimally when summarizing code written in logic programming languages compared to other language types. Finally, we unexpectedly find that CodeLlama-Instruct with 7B parameters can outperform advanced GPT-4 in generating summaries describing code implementation details and asserting code properties. We hope that our findings can provide a comprehensive understanding of code summarization in the era of LLMs.

Shijie Chang, Zeqi Hao, Ben Kang et al.

In this paper, we introduce 3rd place solution for PVUW2023 VSS track. Semantic segmentation is a fundamental task in computer vision with numerous real-world applications. We have explored various image-level visual backbones and segmentation heads to tackle the problem of video semantic segmentation. Through our experimentation, we find that InternImage-H as the backbone and Mask2former as the segmentation head achieves the best performance. In addition, we explore two post-precessing methods: CascadePSP and Segment Anything Model (SAM). Ultimately, our approach obtains 62.60\% and 64.84\% mIoU on the VSPW test set1 and final test set, respectively, securing the third position in the PVUW2023 VSS track.

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.

Shengcheng Yu, Yuchen Ling, Chunrong Fang et al.

The assurance of mobile app GUI has become increasingly important, as the GUI serves as the primary medium of interaction between users and apps. Although numerous automated GUI testing approaches have been developed with diverse strategies, a substantial gap remains between these approaches and the underlying app business logic. Most existing approaches focus on general exploration rather than the completion of specific testing scenarios, often resulting in missed coverage of critical functionalities. Inspired by the manual testing process, which treats business logic, driven testing scenarios as the fundamental unit of testing, this paper introduces an approach that leverages large language models (LLMs) to comprehend the semantics expressed in app GUIs and their contextual relevance to given testing scenarios. Building upon this capability, we propose ScenGen, a novel scenario-guided LLM-based GUI testing framework that employs a multi-agent collaboration mechanism to simulate and automate the phases of manual testing. ScenGen integrates five agents. The Observer perceives the app GUI state by extracting and structuring GUI widgets and layouts, thereby interpreting the semantic information presented in the GUI. This information is then passed to the Decider, which makes scenario-driven decisions with the guidance of LLMs to identify target widgets and determine appropriate actions toward fulfilling specific testing goals. The Executor executes the decided operations on the app, while the Supervisor verifies whether the execution results align with the intended testing scenario completion, ensuring traceability and consistency in test generation and execution. Finally, the Recorder records the corresponding GUI operations into the context memory as a knowledge base for subsequent decision-making and concurrently monitors runtime bug occurrences.

Haichuan Hu, Guoqing Xie, Quanjun Zhang et al.

Large Language Models (LLMs) have shown promise for automated vulnerability repair (AVR), but they still face several limitations, including the lack of intra-vulnerability experience accumulation and the lack of cross-vulnerability experience reuse. As a result, LLMs may repeatedly make similar mistakes during iterative repair and underutilize valuable repair knowledge from historical vulnerabilities. To address these challenges, we propose EvoRepair, the first experience-based self-evolving AVR agent framework that enables LLMs to accumulate, refine, and leverage domain-specific knowledge across long-horizon vulnerability repairs. EvoRepair follows a cyclic learn-and-repair process that retrieves relevant past experiences to guide repair, extracts new experiences from repair trajectories, and updates an experience bank using quality-aware scoring. We evaluate EvoRepair against 12 representative vulnerability repair baselines on PATCHEVAL and SEC-bench using GPT-5-mini. Results show that EvoRepair achieves the best overall performance, reaching 93.47% on PATCHEVAL, 87.00% on SEC-bench, and 90.46% overall. In particular, EvoRepair outperforms latest LLM-based baseline LoopRepair by 39.56% and 33.50% on PATCHEVAL and SEC-bench, respectively, and surpasses IntentFix by 70.86% and 50.50%. Across both benchmarks, EvoRepair also exceeds the recent self-evolving agent Live-SWE-Agent by 6.98% overall. Additional transfer experiments on VUL4J further demonstrate the robustness of EvoRepair across models, programming languages, and datasets. These findings demonstrate that experience-based self-evolution substantially strengthens agentic AVR and goes beyond existing self-evolving techniques.

Jiayang Bai, Zhen He, Shan Yang et al.

Predicting panoramic indoor lighting from a single perspective image is a fundamental but highly ill-posed problem in computer vision and graphics. To achieve locale-aware and robust prediction, this problem can be decomposed into three sub-tasks: depth-based image warping, panorama inpainting and high-dynamic-range (HDR) reconstruction, among which the success of panorama inpainting plays a key role. Recent methods mostly rely on convolutional neural networks (CNNs) to fill the missing contents in the warped panorama. However, they usually achieve suboptimal performance since the missing contents occupy a very large portion in the panoramic space while CNNs are plagued by limited receptive fields. The spatially-varying distortion in the spherical signals further increases the difficulty for conventional CNNs. To address these issues, we propose a local-to-global strategy for large-scale panorama inpainting. In our method, a depth-guided local inpainting is first applied on the warped panorama to fill small but dense holes. Then, a transformer-based network, dubbed PanoTransformer, is designed to hallucinate reasonable global structures in the large holes. To avoid distortion, we further employ cubemap projection in our design of PanoTransformer. The high-quality panorama recovered at any locale helps us to capture spatially-varying indoor illumination with physically-plausible global structures and fine details.

Fuyun Wang, Xingyu Gao, Zhenyu Chen et al.

Session-based recommendation (SBR) aims to predict the next item at a certain time point based on anonymous user behavior sequences. Existing methods typically model session representation based on simple item transition information. However, since session-based data consists of limited users' short-term interactions, modeling session representation by capturing fixed item transition information from a single dimension suffers from data sparsity. In this paper, we propose a novel contrastive multi-level graph neural networks (CM-GNN) to better exploit complex and high-order item transition information. Specifically, CM-GNN applies local-level graph convolutional network (L-GCN) and global-level network (G-GCN) on the current session and all the sessions respectively, to effectively capture pairwise relations over all the sessions by aggregation strategy. Meanwhile, CM-GNN applies hyper-level graph convolutional network (H-GCN) to capture high-order information among all the item transitions. CM-GNN further introduces an attention-based fusion module to learn pairwise relation-based session representation by fusing the item representations generated by L-GCN and G-GCN. CM-GNN averages the item representations obtained by H-GCN to obtain high-order relation-based session representation. Moreover, to convert the high-order item transition information into the pairwise relation-based session representation, CM-GNN maximizes the mutual information between the representations derived from the fusion module and the average pool layer by contrastive learning paradigm. We conduct extensive experiments on multiple widely used benchmark datasets to validate the efficacy of the proposed method. The encouraging results demonstrate that our proposed method outperforms the state-of-the-art SBR techniques.

Zixiang Xian, Rubing Huang, Dave Towey et al.

Artificial intelligence (AI) has revolutionized software engineering (SE) by enhancing software development efficiency. The advent of pre-trained models (PTMs) leveraging transfer learning has significantly advanced AI for SE. However, existing PTMs that operate on individual code tokens suffer from several limitations: They are costly to train and fine-tune; and they rely heavily on labeled data for fine-tuning on task-specific datasets. In this paper, we present TransformCode, a novel framework that learns code embeddings in a contrastive learning manner. Our framework is encoder-agnostic and language-agnostic, which means that it can leverage any encoder model and handle any programming language. We also propose a novel data-augmentation technique called abstract syntax tree (AST) transformation, which applies syntactic and semantic transformations to the original code snippets, to generate more diverse and robust samples for contrastive learning. Our framework has several advantages over existing methods: (1) It is flexible and adaptable, because it can easily be extended to other downstream tasks that require code representation (such as code-clone detection and classification); (2) it is efficient and scalable, because it does not require a large model or a large amount of training data, and it can support any programming language; (3) it is not limited to unsupervised learning, but can also be applied to some supervised learning tasks by incorporating task-specific labels or objectives; and (4) it can also adjust the number of encoder parameters based on computing resources. We evaluate our framework on several code-related tasks, and demonstrate its effectiveness and superiority over the state-of-the-art methods such as SourcererCC, Code2vec, and InferCode.

Haichuan Hu, Quanjun Zhang, Ye Shang et al.

Context engineering has emerged as a pivotal paradigm for unlocking the potential of Large Language Models (LLMs) in Software Engineering (SE) tasks, enabling performance gains at test time without model fine-tuning. Despite its success, existing research lacks a systematic taxonomy of SE-specific context types and a dedicated benchmark to quantify the heterogeneous effects of different contexts across core SE workflows. To address this gap, we propose CL4SE (Context Learning for Software Engineering), a comprehensive benchmark featuring a fine-grained taxonomy of four SE-oriented context types (interpretable examples, project-specific context, procedural decision-making context, and positive & negative context), each mapped to a representative task (code generation, code summarization, code review, and patch correctness assessment). We construct high-quality datasets comprising over 13,000 samples from more than 30 open-source projects and evaluate five mainstream LLMs across nine metrics. Extensive experiments demonstrate that context learning yields an average performance improvement of 24.7% across all tasks. Specifically, procedural context boosts code review performance by up to 33% (Qwen3-Max), mixed positive-negative context improves patch assessment by 30% (DeepSeek-V3), project-specific context increases code summarization BLEU by 14.78% (GPT-Oss-120B), and interpretable examples enhance code generation PASS@1 by 5.72% (DeepSeek-V3). CL4SE establishes the first standardized evaluation framework for SE context learning, provides actionable empirical insights into task-specific context design, and releases a large-scale dataset to facilitate reproducible research in this domain.

Chunrong Fang, Weisong Sun, Yuchen Chen et al.

(Source) code summarization aims to automatically generate succinct natural language summaries for given code snippets. Such summaries play a significant role in promoting developers to understand and maintain code. Inspired by neural machine translation, deep learning-based code summarization techniques widely adopt an encoder-decoder framework, where the encoder transforms given code snippets into context vectors, and the decoder decodes context vectors into summaries. Recently, large-scale pre-trained models for source code are equipped with encoders capable of producing general context vectors and have achieved substantial improvements on code summarization. However, although they are usually trained mainly on code-focused tasks and can capture general code features, they still fall short in capturing specific features that need to be summarized. This paper proposes a novel approach to improve code summarization based on summary-focused tasks. Specifically, we exploit a multi-task learning paradigm to train the encoder on three summary-focused tasks to enhance its ability to learn code-summary alignment, including unidirectional language modeling (ULM), masked language modeling (MLM), and action word prediction (AWP). Unlike pre-trained models that mainly predict masked tokens in code snippets, we design ULM and MLM to predict masked words in summaries. Intuitively, predicting words based on given code snippets would help learn the code-summary alignment. Additionally, we introduce the domain-specific task AWP to enhance the ability of the encoder to learn the alignment between action words and code snippets. The extensive experiments on four datasets demonstrate that our approach, called ESALE significantly outperforms baselines in all three widely used metrics, including BLEU, METEOR, and ROUGE-L.

Pan Wang, Yang Liu, Guile Wu et al.

4D spatial intelligence involves perceiving and processing how objects move or change over time. Humans naturally possess 4D spatial intelligence, supporting a broad spectrum of spatial reasoning abilities. To what extent can Multimodal Large Language Models (MLLMs) achieve human-level 4D spatial intelligence? In this work, we present Spatial4D-Bench, a versatile 4D spatial intelligence benchmark designed to comprehensively assess the 4D spatial reasoning abilities of MLLMs. Unlike existing spatial intelligence benchmarks that are often small-scale or limited in diversity, Spatial4D-Bench provides a large-scale, multi-task evaluation benchmark consisting of ~40,000 question-answer pairs covering 18 well-defined tasks. We systematically organize these tasks into six cognitive categories: object understanding, scene understanding, spatial relationship understanding, spatiotemporal relationship understanding, spatial reasoning and spatiotemporal reasoning. Spatial4D-Bench thereby offers a structured and comprehensive benchmark for evaluating the spatial cognition abilities of MLLMs, covering a broad spectrum of tasks that parallel the versatility of human spatial intelligence. We benchmark various state-of-the-art open-source and proprietary MLLMs on Spatial4D-Bench and reveal their substantial limitations in a wide variety of 4D spatial reasoning aspects, such as route plan, action recognition, and physical plausibility reasoning. We hope that the findings provided in this work offer valuable insights to the community and that our benchmark can facilitate the development of more capable MLLMs toward human-level 4D spatial intelligence. More resources can be found on our project page.

Tingxu Han, Zhenting Wang, Chunrong Fang et al.

Reasoning is critical for large language models (LLMs) to excel in a wide range of tasks. While methods like Chain-of-Thought (CoT) reasoning and enhance LLM performance by decomposing problems into intermediate steps, they also incur significant overhead in token usage, leading to increased costs. We find that the reasoning process of current LLMs is unnecessarily lengthy and it can be compressed by including a reasonable token budget in the prompt, but the choice of token budget plays a crucial role in the actual compression effectiveness. We then propose a token-budget-aware LLM reasoning framework that dynamically adjusts the number of reasoning tokens based on the reasoning complexity of each problem. Experiments show that our method effectively reduces token costs in CoT reasoning with only a slight performance reduction, offering a practical solution to balance efficiency and accuracy in LLM reasoning. Code: https://github.com/GeniusHTX/TALE

Weisong Sun, Yuchen Chen, Chunrong Fang et al.

Neural code models (NCMs) have been widely used to address various code understanding tasks, such as defect detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCMs function normally on normal/clean code snippets, but exhibit adversary-expected behavior on poisoned code snippets injected with the adversary-crafted trigger. It poses a significant security threat. Therefore, there is an urgent need for effective techniques to detect and eliminate backdoors stealthily implanted in NCMs. To address this issue, in this paper, we innovatively propose a backdoor elimination technique for secure code understanding, called EliBadCode. EliBadCode eliminates backdoors in NCMs by inverting/reverse-engineering and unlearning backdoor triggers. Specifically, EliBadCode first filters the model vocabulary for trigger tokens based on the naming conventions of specific programming languages to reduce the trigger search space and cost. Then, EliBadCode introduces a sample-specific trigger position identification method, which can reduce the interference of non-backdoor (adversarial) perturbations for subsequent trigger inversion, thereby producing effective inverted backdoor triggers efficiently. Backdoor triggers can be viewed as backdoor (adversarial) perturbations. Subsequently, EliBadCode employs a Greedy Coordinate Gradient algorithm to optimize the inverted trigger and designs a trigger anchoring method to purify the inverted trigger. Finally, EliBadCode eliminates backdoors through model unlearning. We evaluate the effectiveness of EliBadCode in eliminating backdoors implanted in multiple NCMs used for three safety-critical code understanding tasks. The results demonstrate that EliBadCode can effectively eliminate backdoors while having minimal adverse effects on the normal functionality of the model.

Ye Shang, Quanjun Zhang, Haichuan Hu et al.

As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, bypassing the task of locating affected tests from the full project and excluding the need for new tests entirely. We present TEBench, the first project-level benchmark for test evolution. Given a project repository and a code-changing commit, TEBench requires systems to autonomously identify tests requiring modification, determine where new tests are needed, and produce the corresponding test patch. We construct TEBench through a four-stage pipeline over Defects4J projects, curating 314 task instances from 10 projects with developer-written ground truth. Each instance is annotated with one or more of three evolution types: Test-Breaking (tests that fail), Test-Stale (tests that pass but no longer meaningfully validate updated behavior), and Test-Missing (new tests needed for introduced behavior). We evaluate seven configurations spanning three industrial agent frameworks (Claude Code, Codex CLI, OpenCode) and six base models, alongside a heuristic baseline. All seven configurations converge on an identification F1 of 45.7% to 49.4%, revealing a shared performance ceiling across both frameworks and base models. Test-Stale is the most challenging type, averaging F1 around 36%, since configurations rely on execution failure signals and lack proactive semantic reasoning. On the update task, configurations produce highly executable test modifications whose surface form diverges substantially from ground truth. Trajectory analysis reveals a reactive "execute-fail-fix" loop that succeeds for breaking tests but structurally cannot address stale or missing tests. TEBench is available at https://github.com/iSEngLab/TEBench with a leaderboard at https://tebench-leadership.vercel.app.

Xiaodie Lin, Zhenyu Chen, Zhaohui Wei

Quantifying unknown quantum entanglement experimentally is a difficult task, but also becomes more and more necessary because of the fast development of quantum engineering. Machine learning provides practical solutions to this fundamental problem, where one has to train a proper machine learning model to predict entanglement measures of unknown quantum states based on experimentally measurable data, say moments or correlation data produced by local measurements. In this paper, we compare the performance of these two different machine learning approaches systematically. Particularly, we first show that the approach based on moments enjoys a remarkable advantage over that based on correlation data, though the cost of measuring moments is much higher. Next, since correlation data is much easier to obtain experimentally, we try to better its performance by proposing a hybrid quantum-classical machine learning framework for this problem, where the key is to train optimal local measurements to generate more informative correlation data. Our numerical simulations show that the new framework brings us comparable performance with the approach based on moments to quantify unknown entanglement. Our work implies that it is already practical to fulfill such tasks on near-term quantum devices.

Quanjun Zhang, Ye Shang, Haichuan Hu et al.

Automated program repair (APR) attempts to reduce manual debugging efforts and plays a vital role in software maintenance. Despite remarkable progress, APR is still limited in generating overfitting patches, i.e., patches passing available test suites but incorrect. This issue, known as patch overfitting, has become a key concern in the APR community, with numerous approaches proposed to address it. Very recent work proposes a pre-trained language model (PLM)-based automated patch correctness assessment (APCA) approach, indicating the potential of such PLMs in reasoning about patch correctness. Despite being promising, it is still far from perfect due to various limitations, such as the training paradigm and training dataset. In this paper, we present ComPass, a PLM-based APCA approach that leverages contrastive learning and data augmentation to address the technical limitations of prior work. Our work is inspired by the opportunity to integrate contrastive learning with recent PLMs in the field of patch correctness assessment, where large-scale labeled patches are difficult to obtain. ComPass utilizes code transformation rules to generate semantic-preserving code snippets for both unlabeled pre-training corpus and labeled fine-tuning patches. ComPass then pre-trains PLMs with contrastive learning, which captures code features with the same semantics but different structures. ComPass finally integrates representation embeddings of patch code snippets and fine-tunes PLMs with a binary classifier jointly to assess patch code correctness. Experimental results on 2274 real-world patches from Defects4J demonstrate that ComPass achieves an accuracy of 88.35%, significantly outperforming state-of-the-art baseline APPT.

Tingxu Han, Wei Song, Weisong Sun et al.

With the development of deep learning, Neural Code Models (NCMs) such as CodeBERT and CodeLlama are widely used for code understanding tasks, including defect detection and code classification. However, recent studies have revealed that NCMs are vulnerable to adversarial examples, inputs with subtle perturbations that induce incorrect predictions while remaining difficult to detect. Existing defenses address this issue via data augmentation to empirically improve robustness, but they are costly, offer no theoretical robustness guarantees, and typically require white-box access to model internals, such as gradients. To address the above challenges, we propose ENBECOME, a novel black-box training-free and lightweight adversarial defense. ENBECOME is designed to both enhance empirical robustness and report certified robustness boundaries for NCMs. ENBECOME operates solely during inference, introducing random, semantics-preserving perturbations to input code snippets to smooth the NCM's decision boundaries. This smoothing enables ENBECOME to formally certify a robustness radius within which adversarial examples can never induce misclassification, a property known as certified robustness. We conduct comprehensive experiments across multiple NCM architectures and tasks. Results show that ENBECOME significantly reduces attack success rates while maintaining high accuracy. For example, in defect detection, it reduces the average ASR from 42.43% to 9.74% with only a 0.29% drop in accuracy. Results show that ENBECOME significantly reduces attack success rates while maintaining high accuracy. For example, in defect detection, it reduces the average ASR from 42.43% to 9.74% with only a 0.29% drop in accuracy. Furthermore, ENBECOME achieves an average certified robustness radius of 1.63, meaning that adversarial modifications to no more than 1.63 identifiers are provably ineffective.

Shengcheng Yu, Yuchen Ling, Chunrong Fang et al.

The rapid proliferation and increasing complexity of software demand robust quality assurance, with graphical user interface (GUI) testing playing a pivotal role. Crowdsourced testing has proven effective in this context by leveraging the diversity of human testers to achieve rich, scenario-based coverage across varied devices, user behaviors, and usage environments. In parallel, automated testing, particularly with the advent of large language models (LLMs), offers significant advantages in controllability, reproducibility, and efficiency, enabling scalable and systematic exploration. However, automated approaches often lack the behavioral diversity characteristic of human testers, limiting their capability to fully simulate real-world testing dynamics. To address this gap, we present PersonaTester, a novel personified-LLM-based framework designed to automate crowdsourced GUI testing. By injecting representative personas, defined along three orthogonal dimensions: testing mindset, exploration strategy, and interaction habit, into LLM-based agents, PersonaTester enables the simulation of diverse human-like testing behaviors in a controllable and repeatable manner. Experimental results demonstrate that PersonaTester faithfully reproduces the behavioral patterns of real crowdworkers, exhibiting strong intra-persona consistency and clear inter-persona variability (117.86% -- 126.23% improvement over the baseline). Moreover, persona-guided testing agents consistently generate more effective test events and trigger more crashes (100+) and functional bugs (11) than the baseline without persona, thus substantially advancing the realism and effectiveness of automated crowdsourced GUI testing.

Zixiang Xian, Chenhui Cui, Rubing Huang et al.

The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code clustering. However, existing methods for source code embedding, including those based on LLMs, often rely on costly supervised training or fine-tuning for domain adaptation. This paper proposes a novel approach to embedding source code by combining large language and sentence embedding models. This approach attempts to eliminate the need for task-specific training or fine-tuning and to effectively address the issue of erroneous information commonly found in LLM-generated outputs. To evaluate the performance of our proposed approach, we conducted a series of experiments on three datasets with different programming languages by considering various LLMs and sentence embedding models. The experimental results have demonstrated the effectiveness and superiority of our approach over the state-of-the-art unsupervised approaches, such as SourcererCC, Code2vec, InferCode, TransformCode, and LLM2Vec. Our findings highlight the potential of our approach to advance the field of SE by providing robust and efficient solutions for source code embedding tasks.

Peng Yang, Yunfeng Zhu, Chao Chang et al.

The rapid integration of Large Language Models (LLMs) into software engineering practice is reshaping how software testing activities are performed. LLMs are increasingly used to support software testing. Consequently, software testing education must evolve to prepare students for this new paradigm. However, while students have already begun to use LLMs in an ad hoc manner for testing tasks, there is limited empirical understanding of how such usage influences their testing behaviors, judgment, and learning outcomes. It is necessary to conduct a systematic investigation into how students learn to evaluate, control, and refine LLM-assisted testing results. This paper presents a mixed-methods, two-phase exploratory study on human-LLM collaboration in software testing education. In Phase I, we analyze classroom learning artifacts and interaction records from 15 students, together with a large-scale survey conducted in a national software testing competition (337 valid responses), to identify recurring prompt-related difficulties across testing tasks. The results reveal systematic interaction breakdowns, including missing contextual information, insufficient constraints, rigid one-shot prompting, and limited strategy-driven iteration, with automated test script generation emerging as a particularly heterogeneous and effort-intensive interaction context. Building on these findings, Phase II conducts an illustrative classroom practice that operationalizes the observed breakdowns into a lightweight, stage-aware prompt scaffold for test script generation, guiding students to explicitly articulate execution-relevant information such as environmental assumptions, interaction grounding, synchronization, and validation intent, and reporting descriptive shifts in students' testing-related articulation when interacting with LLMs.

Yuan Xiao, Jiaming Wang, Yuchen Chen et al.

The widespread availability of large-scale code datasets has accelerated the development of code large language models (CodeLLMs), raising concerns about unauthorized dataset usage. Dataset poisoning offers a proactive defense by reducing the utility of such unauthorized training. However, existing poisoning methods often require full dataset poisoning and introduce transformations that break code compilability. In this paper, we introduce FunPoison, a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths. FunPoison leverages reusable statement-level templates with automatic repair and conservative safety checking to ensure side-effect freedom, while a type-aware synthesis module suppresses static analysis warnings and enhances stealth. Extensive experiments show that FunPoison achieves effective poisoning by contaminating only 10% of the dataset, while maintaining 100% compilability and functional correctness, and remains robust against various advanced code sanitization techniques.

Xiaoqi Zhao, Youwei Pang, Zhenyu Chen et al.

We conduct a comprehensive study on a new task named power battery detection (PBD), which aims to localize the dense cathode and anode plates endpoints from X-ray images to evaluate the quality of power batteries. Existing manufacturers usually rely on human eye observation to complete PBD, which makes it difficult to balance the accuracy and efficiency of detection. To address this issue and drive more attention into this meaningful task, we first elaborately collect a dataset, called X-ray PBD, which has $1,500$ diverse X-ray images selected from thousands of power batteries of $5$ manufacturers, with $7$ different visual interference. Then, we propose a novel segmentation-based solution for PBD, termed multi-dimensional collaborative network (MDCNet). With the help of line and counting predictors, the representation of the point segmentation branch can be improved at both semantic and detail aspects.Besides, we design an effective distance-adaptive mask generation strategy, which can alleviate the visual challenge caused by the inconsistent distribution density of plates to provide MDCNet with stable supervision. Without any bells and whistles, our segmentation-based MDCNet consistently outperforms various other corner detection, crowd counting and general/tiny object detection-based solutions, making it a strong baseline that can help facilitate future research in PBD. Finally, we share some potential difficulties and works for future researches. The source code and datasets will be publicly available at \href{https://github.com/Xiaoqi-Zhao-DLUT/X-ray-PBD}{X-ray PBD}.

Yifei Ge, Zhenpeng Chen, Weisong Sun et al.

The widespread availability of large-scale code datasets has fueled the rapid development of large language models (LLMs) for code-related tasks. These datasets may include sensitive personally identifiable information (PII), which can lead to privacy leakage when LLMs memorize and reproduce it. However, existing privacy-leakage detection methods rely on ad-hoc prompt construction (manually or automatically designed). Therefore, they do not adequately approximate the real-world contexts in which PII appears in code corpora, making it difficult to extract realistic privacy leakage. In this paper, we propose a pipeline that simulates practical privacy-related code generation scenarios and adopts a test-driven strategy to elicit the memorized information from the generated test cases. We further introduce an automatically constructed privacy feature library that replaces manual prompt engineering by providing realistic templates and examples to guide test case generation. Large-scale experiments on 5 widely used LLMs show that our pipeline exposes more confirmed privacy leakage, achieving a 2.56 times increase in detected leakage compared to existing baselines.

Weisong Sun, Yuchen Chen, Mengzhe Yuan et al.

Neural code models (NCMs) have demonstrated extraordinary capabilities in code intelligence tasks. Meanwhile, the security of NCMs and NCMs-based systems has garnered increasing attention. In particular, NCMs are often trained on large-scale data from potentially untrustworthy sources, providing attackers with the opportunity to manipulate them by inserting crafted samples into the data. This type of attack is called a code poisoning attack (also known as a backdoor attack). It allows attackers to implant backdoors in NCMs and thus control model behavior, which poses a significant security threat. However, there is still a lack of effective techniques for detecting various complex code poisoning attacks. In this paper, we propose an innovative and lightweight technique for code poisoning detection named KillBadCode. KillBadCode is designed based on our insight that code poisoning disrupts the naturalness of code. Specifically, KillBadCode first builds a code language model (CodeLM) on a lightweight $n$-gram language model. Then, given poisoned data, KillBadCode utilizes CodeLM to identify those tokens in (poisoned) code snippets that will make the code snippets more natural after being deleted as trigger tokens. Considering that the removal of some normal tokens in a single sample might also enhance code naturalness, leading to a high false positive rate (FPR), we aggregate the cumulative improvement of each token across all samples. Finally, KillBadCode purifies the poisoned data by removing all poisoned samples containing the identified trigger tokens. The experimental results on two code poisoning attacks and four code intelligence tasks demonstrate that KillBadCode significantly outperforms four baselines. More importantly, KillBadCode is very efficient, with a minimum time consumption of only 5 minutes, and is 25 times faster than the best baseline on average.

Ding Yang, Ruixiang Qian, Zhao Wei et al.

REST APIs enable collaboration among microservices. A single fault in a REST API can bring down the entire microservice system and cause significant financial losses, underscoring the importance of REST API testing. Effectively testing REST APIs requires thoroughly exercising the functionalities behind them. To this end, existing techniques leverage REST specifications (e.g., Swagger or OpenAPI) to generate test cases. Using the resource constraints extracted from specifications, these techniques work well for testing simple, business-insensitive functionalities, such as resource creation, retrieval, update, and deletion. However, for complex, business-sensitive functionalities, these specification-based techniques often fall short, since exercising such functionalities requires additional business constraints that are typically absent from REST specifications. In this paper, we present LoBREST, a log-based, business-aware REST API testing technique that leverages historical request logs (HRLogs) to effectively exercise the business-sensitive functionalities behind REST APIs. To obtain compact operation sequences that preserve clean and complete business constraints, LoBREST first employs a locality-slicing strategy to partition HRLogs into smaller slices. Then, to ensure the effectiveness of the obtained slices, LoBREST enhances them in two steps: (1) adding slices for operations missing from HRLogs, and (2) completing missing resources within the slices. Finally, to improve test adequacy, LoBREST uses these enhanced slices as initial seeds to perform business-aware fuzzing. LoBREST outperformed eight tools (including Arat-rl, Morest, and Deeprest) across 17 real-world services. It achieved top operation coverage on 16 services and line coverage on 15, averaging 2.1x and 1.2x improvements over the runner-up. LoBREST detected 108 5XX bugs, including 38 found by no other tool.

Yuan Xiao, Shiqing Ma, Juan Zhai et al.

The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, within which any perturbation does not alter the original input's classification result. It is challenging due to nonlinear components, such as MaxPool. At present, many verification methods are sound but risk losing some precision to enhance efficiency and scalability, and thus, a certified lower bound is a crucial criterion for evaluating the performance of verification tools. In this paper, we present MaxLin, a robustness verifier for MaxPool-based CNNs with tight linear approximation. By tightening the linear approximation of the MaxPool function, we can certify larger certified lower bounds of CNNs. We evaluate MaxLin with open-sourced benchmarks, including LeNet and networks trained on the MNIST, CIFAR-10, and Tiny ImageNet datasets. The results show that MaxLin outperforms state-of-the-art tools with up to 110.60% improvement regarding the certified lower bound and 5.13 $\times$ speedup for the same neural networks. Our code is available at https://github.com/xiaoyuanpigo/maxlin.

Tingting Xu, Yun Miao, Chunrong Fang et al.

(Source) code summarization is the task of automatically generating natural language summaries (also called comments) for given code snippets. Recently, with the successful application of large language models (LLMs) in numerous fields, software engineering researchers have also attempted to adapt LLMs to solve code summarization tasks. The main adaptation schemes include instruction prompting, task-oriented (full-parameter) fine-tuning, and parameter-efficient fine-tuning (PEFT). However, instruction prompting involves designing crafted prompts and requires users to have professional domain knowledge, while task-oriented fine-tuning requires high training costs, and effective, tailored PEFT methods for code summarization are still lacking. This paper proposes an effective prompt learning framework for code summarization called PromptCS. It no longer requires users to rack their brains to design effective prompts. Instead, PromptCS trains a prompt agent that can generate continuous prompts to unleash the potential for LLMs in code summarization. Compared to the human-written discrete prompt, the continuous prompts are produced under the guidance of LLMs and are therefore easier to understand by LLMs. PromptCS is non-invasive to LLMs and freezes the parameters of LLMs when training the prompt agent, which can greatly reduce the requirements for training resources. Our comprehensive experimental results show that PromptCS significantly outperforms instruction prompting schemes (including zero-shot learning and few-shot learning) on all four widely used metrics, and is comparable to the task-oriented fine-tuning scheme. In some base LLMs, e.g., StarCoderBase-1B and -3B, PromptCS even outperforms the task-oriented fine-tuning scheme. More importantly, the training efficiency of PromptCS is faster than the task-oriented fine-tuning scheme, with a more pronounced advantage on larger LLMs.

Tingxu Han, Shenghan Huang, Ziqi Ding et al.

In this paper, we study a defense against poisoned encoders in SSL called distillation, which is a defense used in supervised learning originally. Distillation aims to distill knowledge from a given model (a.k.a the teacher net) and transfer it to another (a.k.a the student net). Now, we use it to distill benign knowledge from poisoned pre-trained encoders and transfer it to a new encoder, resulting in a clean pre-trained encoder. In particular, we conduct an empirical study on the effectiveness and performance of distillation against poisoned encoders. Using two state-of-the-art backdoor attacks against pre-trained image encoders and four commonly used image classification datasets, our experimental results show that distillation can reduce attack success rate from 80.87% to 27.51% while suffering a 6.35% loss in accuracy. Moreover, we investigate the impact of three core components of distillation on performance: teacher net, student net, and distillation loss. By comparing 4 different teacher nets, 3 student nets, and 6 distillation losses, we find that fine-tuned teacher nets, warm-up-training-based student nets, and attention-based distillation loss perform best, respectively.

Tingxu Han, Weisong Sun, Yanrong Hu et al.

Text-to-image diffusion models have shown an impressive ability to generate high-quality images from input textual descriptions. However, concerns have been raised about the potential for these models to create content that infringes on copyrights or depicts disturbing subject matter. Removing specific concepts from these models is a promising potential solution to this problem. However, existing methods for concept removal do not work well in practical but challenging scenarios where concepts need to be continuously removed. Specifically, these methods lead to poor alignment between the text prompts and the generated image after the continuous removal process. To address this issue, we propose a novel approach called CCRT that includes a designed knowledge distillation paradigm. It constrains the text-image alignment behavior during the continuous concept removal process by using a set of text prompts generated through our genetic algorithm, which employs a designed fuzzing strategy. We conduct extensive experiments involving the removal of various concepts. The results evaluated through both algorithmic metrics and human studies demonstrate that our CCRT can effectively remove the targeted concepts in a continuous manner while maintaining the high generation quality (e.g., text-image alignment) of the model.

Yueming Xu, Jiahui Zhang, Ze Huang et al.

Despite the impressive progress on understanding and generating images shown by the recent unified architectures, the integration of 3D tasks remains challenging and largely unexplored. In this paper, we introduce UniUGG, the first unified understanding and generation framework for 3D modalities. Our unified framework employs an LLM to comprehend and decode sentences and 3D representations. At its core, we propose a spatial decoder leveraging a latent diffusion model to generate high-quality 3D representations. This allows for the generation and imagination of 3D scenes based on a reference image and an arbitrary view transformation, while remaining supports for spatial visual question answering (VQA) tasks. Additionally, we propose a geometric-semantic learning strategy to pretrain the vision encoder. This design jointly captures the input's semantic and geometric cues, enhancing both spatial understanding and generation. Extensive experimental results demonstrate the superiority of our method in visual representation, spatial understanding, and 3D generation. The source code will be released upon paper acceptance.

Zicheng Ma, Chuanliu Fan, Zhicong Wang et al.

Large language models have made remarkable progress in the field of molecular science, particularly in understanding and generating functional small molecules. This success is largely attributed to the effectiveness of molecular tokenization strategies. In protein science, the amino acid sequence serves as the sole tokenizer for LLMs. However, many fundamental challenges in protein science are inherently structure-dependent. The absence of structure-aware tokens significantly limits the capabilities of LLMs for comprehensive biomolecular comprehension and multimodal generation. To address these challenges, we introduce a novel framework, ProtTeX, which tokenizes the protein sequences, structures, and textual information into a unified discrete space. This innovative approach enables joint training of the LLM exclusively through the Next-Token Prediction paradigm, facilitating multimodal protein reasoning and generation. ProtTeX enables general LLMs to perceive and process protein structures through sequential text input, leverage structural information as intermediate reasoning components, and generate or manipulate structures via sequential text output. Experiments demonstrate that our model achieves significant improvements in protein function prediction, outperforming the state-of-the-art domain expert model with a twofold increase in accuracy. Our framework enables high-quality conformational generation and customizable protein design. For the first time, we demonstrate that by adopting the standard training and inference pipelines from the LLM domain, ProtTeX empowers decoder-only LLMs to effectively address diverse spectrum of protein-related tasks.

Binxiao Huang, Zhihao Li, Shiyong Liu et al.

3D Gaussian splatting (3DGS) has demonstrated exceptional performance in image-based 3D reconstruction and real-time rendering. However, regions with complex textures require numerous Gaussians to capture significant color variations accurately, leading to inefficiencies in rendering speed. To address this challenge, we introduce a hybrid representation for indoor scenes that combines 3DGS with textured meshes. Our approach uses textured meshes to handle texture-rich flat areas, while retaining Gaussians to model intricate geometries. The proposed method begins by pruning and refining the extracted mesh to eliminate geometrically complex regions. We then employ a joint optimization for 3DGS and mesh, incorporating a warm-up strategy and transmittance-aware supervision to balance their contributions seamlessly.Extensive experiments demonstrate that the hybrid representation maintains comparable rendering quality and achieves superior frames per second FPS with fewer Gaussian primitives.

Quanjun Zhang, Chunrong Fang, Haichuan Hu et al.

Automated program repair (APR) attempts to generate correct patches and has drawn wide attention from both academia and industry in the past decades. However, APR is continuously struggling with the patch overfitting issue due to the weak test suites. Thus, to address the overfitting problem, the community has proposed an increasing number of approaches to predict patch correctness (APCA approaches). Among them, locally deep learning approaches aimed at automatically match designs has been emerging strongly. Such approaches typically encode input code snippets into well-designed representations and build a binary model for correctness prediction. Despite being fundamental in reason about patch correctness, code representation has not been systematically investigated. To bridge this gap, we perform the first extensive study to evaluate the performance of different code representations on predicting patch correctness from more than 500 trained APCA models. The experimental results on 15 benchmarks with four categories and 11 classifiers show that the graph-based code representation which is ill-explored in the literature, consistently outperforms other representations, e.g., an average accuracy of 82.6% for CPG across three GNN models. Moreover, we demonstrate that such representations can achieve comparable or better performance for three different previous APCA approaches, e.g., filtering out 87.09% overfitting patches by TREETRAIN with AST. We further find that integrating sequence-based representation into heuristic-based representation is able to yield an average improvement of 13.5% on five metrics. Overall, our study highlights the potential and challenges of utilizing code representation to reason about patch correctness, thus increasing the usability of off-the-shelf APR tools and reducing the manual debugging effort of developers in practice.

Zhenyu Chen, Bin Cheng, Minbo Gao et al.

Noise in quantum hardware is the primary obstacle to realizing the transformative potential of quantum computing. Quantum error mitigation (QEM) offers a promising pathway to enhance computational accuracy on near-term devices, yet existing methods face a difficult trade-off between performance, resource overhead, and theoretical guarantees. In this work, we introduce neighbor-informed learning (NIL), a versatile and scalable QEM framework that unifies and strengthens existing methods such as zero-noise extrapolation (ZNE) and probabilistic error cancellation (PEC), while offering improved flexibility, accuracy, efficiency, and robustness. NIL learns to predict the ideal output of a target quantum circuit from the noisy outputs of its structurally related ``neighbor'' circuits. A key innovation is our 2-design training method, which generates training data for our machine learning model. In contrast to conventional learning-based QEM protocols that create training circuits by replacing non-Clifford gates with uniformly random Clifford gates, our approach achieves higher accuracy and efficiency, as demonstrated by both theoretical analysis and numerical simulation. Furthermore, we prove that the required size of the training set scales only \emph{logarithmically} with the total number of neighbor circuits, enabling NIL to be applied to problems involving large-scale quantum circuits. Our work establishes a theoretically grounded and practically efficient framework for QEM, paving a viable path toward achieving quantum advantage on noisy hardware.

Zhenyu Chen, Yuguo Shao, Zhengwei Liu et al.

Quantum algorithms based on parameterized quantum circuits (PQCs) have enabled a wide range of applications on near-term quantum devices. However, existing PQC architectures face several challenges, among which the ``barren plateaus" phenomenon is particularly prominent. In such cases, the loss function concentrates exponentially with increasing system size, thereby hindering effective parameter optimization. To address this challenge, we propose a general and hardware-efficient method for eliminating barren plateaus in an arbitrary PQC. Specifically, our approach achieves this by inserting a layer of easily implementable quantum channels into the original PQC, each channel requiring only one ancilla qubit and four additional gates, yielding a modified PQC (MPQC) that is provably at least as expressive as the original PQC and, under mild assumptions, is guaranteed to be free from barren plateaus. Furthermore, by appropriately adjusting the structure of MPQCs, we rigorously prove that any parameter in the original PQC can be made trainable. Importantly, the absence of barren plateaus in MPQCs is robust against realistic noise, making our approach directly applicable to current noisy intermediate-scale quantum (NISQ) hardware. Numerically, we demonstrate the practicality of our method by modifying a commonly used PQC for thermal-state preparation. The results show that {barren plateaus are effectively eliminated} in this class of circuits with up to 100 qubits and 2400 layers, whereas the original ansatz suffers from severe gradient vanishing.

Tingxu Han, Wei Song, Ziqi Ding et al.

Large language models (LLMs) increasingly mediate decisions in domains where unfair treatment of demographic groups is unacceptable. Existing work probes when biased outputs appear, but gives little insight into the mechanisms that generate them, leaving existing mitigations largely fragile. In this paper, we conduct a systematic investigation LLM unfairness and propose DiffHeads, a lightweight debiasing framework for LLMs. We first compare Direct-Answer (DA) prompting to Chain-of-Thought (CoT) prompting across eight representative open- and closed-source LLMs. DA will trigger the nature bias part of LLM and improve measured unfairness by 534.5%-391.9% in both one-turn and two-turn dialogues. Next, we define a token-to-head contribution score that traces each token's influence back to individual attention heads. This reveals a small cluster of bias heads that activate under DA but stay largely dormant with CoT, providing the first causal link between prompting strategy and bias emergence. Finally, building on this insight, we propose DiffHeads that identifies bias heads through differential activation analysis between DA and CoT, and selectively masks only those heads. DiffHeads reduces unfairness by 49.4%, and 40.3% under DA and CoT, respectively, without harming model utility.

Jian Gao, Mengqi Yuan, Yifei Zeng et al.

Gaussian Splatting (GS) enables immersive rendering, but realistic 3D object-scene composition remains challenging. Baked appearance and shadow information in GS radiance fields cause inconsistencies when combining objects and scenes. Addressing this requires relightable object reconstruction and scene lighting estimation. For relightable object reconstruction, existing Gaussian-based inverse rendering methods often rely on ray tracing, leading to low efficiency. We introduce Surface Octahedral Probes (SOPs), which store lighting and occlusion information and allow efficient 3D querying via interpolation, avoiding expensive ray tracing. SOPs provide at least a 2x speedup in reconstruction and enable real-time shadow computation in Gaussian scenes. For lighting estimation, existing Gaussian-based inverse rendering methods struggle to model intricate light transport and often fail in complex scenes, while learning-based methods predict lighting from a single image and are viewpoint-sensitive. We observe that 3D object-scene composition primarily concerns the object's appearance and nearby shadows. Thus, we simplify the challenging task of full scene lighting estimation by focusing on the environment lighting at the object's placement. Specifically, we capture a 360 degrees reconstructed radiance field of the scene at the location and fine-tune a diffusion model to complete the lighting. Building on these advances, we propose ComGS, a novel 3D object-scene composition framework. Our method achieves high-quality, real-time rendering at around 28 FPS, produces visually harmonious results with vivid shadows, and requires only 36 seconds for editing. Code and dataset are available at https://nju-3dv.github.io/projects/ComGS/.

An Guo, Shuoxiao Zhang, Enyi Tang et al.

With the tremendous advancement of deep learning and communication technology, Vehicle-to-Everything (V2X) cooperative perception has the potential to address limitations in sensing distant objects and occlusion for a single-agent perception system. V2X cooperative perception systems are software systems characterized by diverse sensor types and cooperative agents, varying fusion schemes, and operation under different communication conditions. Therefore, their complex composition gives rise to numerous operational challenges. Furthermore, when cooperative perception systems produce erroneous predictions, the types of errors and their underlying causes remain insufficiently explored. To bridge this gap, we take an initial step by conducting an empirical study of V2X cooperative perception. To systematically evaluate the impact of cooperative perception on the ego vehicle's perception performance, we identify and analyze six prevalent error patterns in cooperative perception systems. We further conduct a systematic evaluation of the critical components of these systems through our large-scale study and identify the following key findings: (1) The LiDAR-based cooperation configuration exhibits the highest perception performance; (2) Vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communication exhibit distinct cooperative perception performance under different fusion schemes; (3) Increased cooperative perception errors may result in a higher frequency of driving violations; (4) Cooperative perception systems are not robust against communication interference when running online. Our results reveal potential risks and vulnerabilities in critical components of cooperative perception systems. We hope that our findings can better promote the design and repair of cooperative perception systems.

Yinglong Zou, Juan Zhai, Chunrong Fang et al.

Deep learning models play a vital role in autonomous driving systems, supporting critical functions such as environmental perception. To accelerate model inference, these deep learning models' deployment relies on automotive deep learning frameworks, for example, PaddleInference in Apollo and TensorRT in AutoWare. However, unlike deploying deep learning models on the cloud, vehicular environments experience extreme ambient temperatures varying from -40°C to 50°C, significantly impacting GPU temperature. Additionally, heats generated when computing further lead to the GPU temperature increase. These temperature fluctuations lead to dynamic GPU frequency adjustments through mechanisms such as DVFS. However, automotive deep learning frameworks are designed without considering the impact of temperature-induced frequency variations. When deployed on temperature-varying GPUs, these frameworks suffer critical quality issues: compute-intensive operators face delays or errors, high/mixed-precision operators suffer from precision errors, and time-series operators suffer from synchronization issues. The above quality issues cannot be detected by existing deep learning framework testing methods because they ignore temperature's effect on the deep learning framework quality. To bridge this gap, we propose ThermalGuardian, the first automotive deep learning framework testing method under temperature-varying environments. Specifically, ThermalGuardian generates test input models using model mutation rules targeting temperature-sensitive operators, simulates GPU temperature fluctuations based on Newton's law of cooling, and controls GPU frequency based on real-time GPU temperature.

Yuxuan Lin, Ruihang Chu, Zhenyu Chen et al.

Generative 3D reconstruction shows strong potential in incomplete observations. While sparse-view and single-image reconstruction are well-researched, partial observation remains underexplored. In this context, dense views are accessible only from a specific angular range, with other perspectives remaining inaccessible. This task presents two main challenges: (i) limited View Range: observations confined to a narrow angular scope prevent effective traditional interpolation techniques that require evenly distributed perspectives. (ii) inconsistent Generation: views created for invisible regions often lack coherence with both visible regions and each other, compromising reconstruction consistency. To address these challenges, we propose \method, a novel training-free approach that integrates the local dense observations and multi-source priors for reconstruction. Our method introduces a fusion-based strategy to effectively align these priors in DDIM sampling, thereby generating multi-view consistent images to supervise invisible views. We further design an iterative refinement strategy, which uses the geometric structures of the object to enhance reconstruction quality. Extensive experiments on multiple datasets show the superiority of our method over SOTAs, especially in invisible regions.

Yifei Deng, Chenglong Li, Zhenyu Chen et al.

The performance of traditional text-image person retrieval task is easily affected by lighting variations due to imaging limitations of visible spectrum sensors. In recent years, cross-modal information fusion has emerged as an effective strategy to enhance retrieval robustness. By integrating complementary information from different spectral modalities, it becomes possible to achieve more stable person recognition and matching under complex real-world conditions. Motivated by this, we introduce a novel task: Text-RGBT Person Retrieval, which incorporates cross-spectrum information fusion by combining the complementary cues from visible and thermal modalities for robust person retrieval in challenging environments. The key challenge of Text-RGBT person retrieval lies in aligning text with multi-modal visual features. However, the inherent heterogeneity between visible and thermal modalities may interfere with the alignment between vision and language. To handle this problem, we propose a Decoupled Cross-modal Alignment network (DCAlign), which sufficiently mines the relationships between modality-specific and modality-collaborative visual with the text, for Text-RGBT person retrieval. To promote the research and development of this field, we create a high-quality Text-RGBT person retrieval dataset, RGBT-PEDES. RGBT-PEDES contains 1,822 identities from different age groups and genders with 4,723 pairs of calibrated RGB and T images, and covers high-diverse scenes from both daytime and nighttime with a various of challenges such as occlusion, weak alignment and adverse lighting conditions. Additionally, we carefully annotate 7,987 fine-grained textual descriptions for all RGBT person image pairs. Extensive experiments on RGBT-PEDES demonstrate that our method outperforms existing text-image person retrieval methods.

Tingxu Han, Weisong Sun, Ziqi Ding et al.

Self-supervised learning (SSL) is increasingly attractive for pre-training encoders without requiring labeled data. Downstream tasks built on top of those pre-trained encoders can achieve nearly state-of-the-art performance. The pre-trained encoders by SSL, however, are vulnerable to backdoor attacks as demonstrated by existing studies. Numerous backdoor mitigation techniques are designed for downstream task models. However, their effectiveness is impaired and limited when adapted to pre-trained encoders, due to the lack of label information when pre-training. To address backdoor attacks against pre-trained encoders, in this paper, we innovatively propose a mutual information guided backdoor mitigation technique, named MIMIC. MIMIC treats the potentially backdoored encoder as the teacher net and employs knowledge distillation to distill a clean student encoder from the teacher net. Different from existing knowledge distillation approaches, MIMIC initializes the student with random weights, inheriting no backdoors from teacher nets. Then MIMIC leverages mutual information between each layer and extracted features to locate where benign knowledge lies in the teacher net, with which distillation is deployed to clone clean features from teacher to student. We craft the distillation loss with two aspects, including clone loss and attention loss, aiming to mitigate backdoors and maintain encoder performance at the same time. Our evaluation conducted on two backdoor attacks in SSL demonstrates that MIMIC can significantly reduce the attack success rate by only utilizing <5% of clean data, surpassing seven state-of-the-art backdoor mitigation techniques.

Weisong Sun, Chunrong Fang, Yudu You et al.

To support software developers in understanding and maintaining programs, various automatic code summarization techniques have been proposed to generate a concise natural language comment for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of natural language processing tasks. Among them, ChatGPT is the most popular one which has attracted wide attention from the software engineering community. However, it still remains unclear how ChatGPT performs in (automatic) code summarization. Therefore, in this paper, we focus on evaluating ChatGPT on a widely-used Python dataset called CSN-Python and comparing it with several state-of-the-art (SOTA) code summarization models. Specifically, we first explore an appropriate prompt to guide ChatGPT to generate in-distribution comments. Then, we use such a prompt to ask ChatGPT to generate comments for all code snippets in the CSN-Python test set. We adopt three widely-used metrics (including BLEU, METEOR, and ROUGE-L) to measure the quality of the comments generated by ChatGPT and SOTA models (including NCS, CodeBERT, and CodeT5). The experimental results show that in terms of BLEU and ROUGE-L, ChatGPT's code summarization performance is significantly worse than all three SOTA models. We also present some cases and discuss the advantages and disadvantages of ChatGPT in code summarization. Based on the findings, we outline several open challenges and opportunities in ChatGPT-based code summarization.