Xin Xia

Runsheng Xu, Hao Xiang, Zhengzhong Tu et al.

In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles. We present a robust cooperative perception framework with V2X communication using a novel vision Transformer. Specifically, we build a holistic attention model, namely V2X-ViT, to effectively fuse information across on-road agents (i.e., vehicles and infrastructure). V2X-ViT consists of alternating layers of heterogeneous multi-agent self-attention and multi-scale window self-attention, which captures inter-agent interaction and per-agent spatial relationships. These key modules are designed in a unified Transformer architecture to handle common V2X challenges, including asynchronous information sharing, pose errors, and heterogeneity of V2X components. To validate our approach, we create a large-scale V2X perception dataset using CARLA and OpenCDA. Extensive experimental results demonstrate that V2X-ViT sets new state-of-the-art performance for 3D object detection and achieves robust performance even under harsh, noisy environments. The code is available at https://github.com/DerrickXuNu/v2x-vit.

Jiashi Li, Xin Xia, Wei Li et al.

Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and CoreML. This poses a distinct challenge: Can a visual neural network be designed to infer as fast as CNNs and perform as powerful as ViTs? Recent works have tried to design CNN-Transformer hybrid architectures to address this issue, yet the overall performance of these works is far away from satisfactory. To end these, we propose a next generation vision Transformer for efficient deployment in realistic industrial scenarios, namely Next-ViT, which dominates both CNNs and ViTs from the perspective of latency/accuracy trade-off. In this work, the Next Convolution Block (NCB) and Next Transformer Block (NTB) are respectively developed to capture local and global information with deployment-friendly mechanisms. Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks. Extensive experiments show that Next-ViT significantly outperforms existing CNNs, ViTs and CNN-Transformer hybrid architectures with respect to the latency/accuracy trade-off across various vision tasks. On TensorRT, Next-ViT surpasses ResNet by 5.5 mAP (from 40.4 to 45.9) on COCO detection and 7.7% mIoU (from 38.8% to 46.5%) on ADE20K segmentation under similar latency. Meanwhile, it achieves comparable performance with CSWin, while the inference speed is accelerated by 3.6x. On CoreML, Next-ViT surpasses EfficientFormer by 4.6 mAP (from 42.6 to 47.2) on COCO detection and 3.5% mIoU (from 45.1% to 48.6%) on ADE20K segmentation under similar latency. Our code and models are made public at: https://github.com/bytedance/Next-ViT

Hao Xiang, Runsheng Xu, Xin Xia et al.

Recent advancements in Vehicle-to-Everything communication technology have enabled autonomous vehicles to share sensory information to obtain better perception performance. With the rapid growth of autonomous vehicles and intelligent infrastructure, the V2X perception systems will soon be deployed at scale, which raises a safety-critical question: \textit{how can we evaluate and improve its performance under challenging traffic scenarios before the real-world deployment?} Collecting diverse large-scale real-world test scenes seems to be the most straightforward solution, but it is expensive and time-consuming, and the collections can only cover limited scenarios. To this end, we propose the first open adversarial scene generator V2XP-ASG that can produce realistic, challenging scenes for modern LiDAR-based multi-agent perception systems. V2XP-ASG learns to construct an adversarial collaboration graph and simultaneously perturb multiple agents' poses in an adversarial and plausible manner. The experiments demonstrate that V2XP-ASG can effectively identify challenging scenes for a large range of V2X perception systems. Meanwhile, by training on the limited number of generated challenging scenes, the accuracy of V2X perception systems can be further improved by 12.3\% on challenging and 4\% on normal scenes. Our code will be released at https://github.com/XHwind/V2XP-ASG.

Yun Wang, Xin Xia, Xuansheng Wu et al.

LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric construction. Human experts bypass this bottleneck through evaluation heuristics developed over extensive practice. We ask whether LLMs can learn similar heuristics directly from scoring experience, and formalize this as the concept of assessment skills: item-independent natural-language procedural knowledge that guides LLMs through specific stages of the scoring workflow. Focusing on rubric construction as a first instantiation, we propose an iterative framework that decomposes a skill into a fixed scaffold and learnable item-agnostic rules, refining the rules through LLM-driven diagnosis of scoring errors and validation-gated selection. The framework requires no expert-written rubric. On all ten ASAP-SAS items, optimized skills substantially improve LLM-based scoring and frequently surpass the dataset-provided expert rubric. Cross-item transfer experiments further reveal that learned skills capture both generalizable and item-specific patterns.

Team Seedance, De Chen, Liyang Chen et al. · gatech

Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users.

Runsheng Xu, Xin Xia, Jinlong Li et al.

Modern perception systems of autonomous vehicles are known to be sensitive to occlusions and lack the capability of long perceiving range. It has been one of the key bottlenecks that prevents Level 5 autonomy. Recent research has demonstrated that the Vehicle-to-Vehicle (V2V) cooperative perception system has great potential to revolutionize the autonomous driving industry. However, the lack of a real-world dataset hinders the progress of this field. To facilitate the development of cooperative perception, we present V2V4Real, the first large-scale real-world multi-modal dataset for V2V perception. The data is collected by two vehicles equipped with multi-modal sensors driving together through diverse scenarios. Our V2V4Real dataset covers a driving area of 410 km, comprising 20K LiDAR frames, 40K RGB frames, 240K annotated 3D bounding boxes for 5 classes, and HDMaps that cover all the driving routes. V2V4Real introduces three perception tasks, including cooperative 3D object detection, cooperative 3D object tracking, and Sim2Real domain adaptation for cooperative perception. We provide comprehensive benchmarks of recent cooperative perception algorithms on three tasks. The V2V4Real dataset can be found at https://research.seas.ucla.edu/mobility-lab/v2v4real/.

Seth Z. Zhao, Hao Xiang, Chenfeng Xu et al.

Existing Vehicle-to-Everything (V2X) cooperative perception methods rely on accurate multi-agent 3D annotations. Nevertheless, it is time-consuming and expensive to collect and annotate real-world data, especially for V2X systems. In this paper, we present a self-supervised learning framwork for V2X cooperative perception, which utilizes the vast amount of unlabeled 3D V2X data to enhance the perception performance. Specifically, multi-agent sensing information is aggregated to form a holistic view and a novel proxy task is formulated to reconstruct the LiDAR point clouds across multiple connected agents to better reason multi-agent spatial correlations. Besides, we develop a V2X bird-eye-view (BEV) guided masking strategy which effectively allows the model to pay attention to 3D features across heterogeneous V2X agents (i.e., vehicles and infrastructure) in the BEV space. Noticeably, such a masking strategy effectively pretrains the 3D encoder with a multi-agent LiDAR point cloud reconstruction objective and is compatible with mainstream cooperative perception backbones. Our approach, validated through extensive experiments on representative datasets (i.e., V2X-Real, V2V4Real, and OPV2V) and multiple state-of-the-art cooperative perception methods (i.e., AttFuse, F-Cooper, and V2X-ViT), leads to a performance boost across all V2X settings. Notably, CooPre achieves a 4% mAP improvement on V2X-Real dataset and surpasses baseline performance using only 50% of the training data, highlighting its data efficiency. Additionally, we demonstrate the framework's powerful performance in cross-domain transferability and robustness under challenging scenarios. The code will be made publicly available at https://github.com/ucla-mobility/CooPre.

Jia Li, Yongmin Li, Ge Li et al.

Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in software projects. Code summarization aims to generate natural language descriptions automatically for source code. Code summaries are highly structured and have repetitive patterns. Besides the patternized words, a code summary also contains important keywords, which are the key to reflecting the functionality of the code. However, the state-of-the-art approaches perform poorly on predicting the keywords, which leads to the generated summaries suffering a loss in informativeness. To alleviate this problem, this paper proposes a novel retrieve-and-edit approach named EditSum for code summarization. Specifically, EditSum first retrieves a similar code snippet from a pre-defined corpus and treats its summary as a prototype summary to learn the pattern. Then, EditSum edits the prototype automatically to combine the pattern in the prototype with the semantic information of input code. Our motivation is that the retrieved prototype provides a good start-point for post-generation because the summaries of similar code snippets often have the same pattern. The post-editing process further reuses the patternized words in the prototype and generates keywords based on the semantic information of input code. We conduct experiments on a large-scale Java corpus and experimental results demonstrate that EditSum outperforms the state-of-the-art approaches by a substantial margin. The human evaluation also proves the summaries generated by EditSum are more informative and useful. We also verify that EditSum performs well on predicting the patternized words and keywords.

Mouxiang Chen, Zhongxin Liu, He Tao et al.

Selecting the best code solution from multiple generated ones is an essential task in code generation, which can be achieved by using some reliable validators (e.g., developer-written test cases) for assistance. Since reliable test cases are not always available and can be expensive to build in practice, researchers propose to automatically generate test cases to assess code solutions. However, when both code solutions and test cases are plausible and not reliable, selecting the best solution becomes challenging. Although some heuristic strategies have been proposed to tackle this problem, they lack a strong theoretical guarantee and it is still an open question whether an optimal selection strategy exists. Our work contributes in two ways. First, we show that within a Bayesian framework, the optimal selection strategy can be defined based on the posterior probability of the observed passing states between solutions and tests. The problem of identifying the best solution is then framed as an integer programming problem. Second, we propose an efficient approach for approximating this optimal (yet uncomputable) strategy, where the approximation error is bounded by the correctness of prior knowledge. We then incorporate effective prior knowledge to tailor code generation tasks. Both theoretical and empirical studies confirm that existing heuristics are limited in selecting the best solutions with plausible test cases. Our proposed approximated optimal strategy B4 significantly surpasses existing heuristics in selecting code solutions generated by large language models (LLMs) with LLM-generated tests, achieving a relative performance improvement by up to 50% over the strongest heuristic and 246% over the random selection in the most challenging scenarios. Our code is publicly available at https://github.com/ZJU-CTAG/B4.

Zhongxin Liu, Zhijie Tang, Xin Xia et al.

Representing code changes as numeric feature vectors, i.e., code change representations, is usually an essential step to automate many software engineering tasks related to code changes, e.g., commit message generation and just-in-time defect prediction. Intuitively, the quality of code change representations is crucial for the effectiveness of automated approaches. Prior work on code changes usually designs and evaluates code change representation approaches for a specific task, and little work has investigated code change encoders that can be used and jointly trained on various tasks. To fill this gap, this work proposes a novel Code Change Representation learning approach named CCRep, which can learn to encode code changes as feature vectors for diverse downstream tasks. Specifically, CCRep regards a code change as the combination of its before-change and after-change code, leverages a pre-trained code model to obtain high-quality contextual embeddings of code, and uses a novel mechanism named query back to extract and encode the changed code fragments and make them explicitly interact with the whole code change. To evaluate CCRep and demonstrate its applicability to diverse code-change-related tasks, we apply it to three tasks: commit message generation, patch correctness assessment, and just-in-time defect prediction. Experimental results show that CCRep outperforms the state-of-the-art techniques on each task.

Haoye Tian, Xunzhu Tang, Andrew Habib et al.

In this work, we propose a novel perspective to the problem of patch correctness assessment: a correct patch implements changes that "answer" to a problem posed by buggy behaviour. Concretely, we turn the patch correctness assessment into a Question Answering problem. To tackle this problem, our intuition is that natural language processing can provide the necessary representations and models for assessing the semantic correlation between a bug (question) and a patch (answer). Specifically, we consider as inputs the bug reports as well as the natural language description of the generated patches. Our approach, Quatrain, first considers state of the art commit message generation models to produce the relevant inputs associated to each generated patch. Then we leverage a neural network architecture to learn the semantic correlation between bug reports and commit messages. Experiments on a large dataset of 9135 patches generated for three bug datasets (Defects4j, Bugs.jar and Bears) show that Quatrain can achieve an AUC of 0.886 on predicting patch correctness, and recalling 93% correct patches while filtering out 62% incorrect patches. Our experimental results further demonstrate the influence of inputs quality on prediction performance. We further perform experiments to highlight that the model indeed learns the relationship between bug reports and code change descriptions for the prediction. Finally, we compare against prior work and discuss the benefits of our approach.

Wuhan Chen, Min Gao, Xin Xia et al.

Large language models (LLMs) have recently shown promise in recommendation by providing rich semantic knowledge. While most existing approaches rely on external textual corpora to align LLMs with recommender systems, we revisit a more fundamental yet underexplored question: Can recommendation benefit from LLM token embeddings alone without textual input? Through a systematic empirical study, we show that directly injecting token embeddings from a single LLM into sequential recommenders leads to unstable or limited gains, due to semantic misalignment, insufficient task adaptation, and the restricted coverage of individual LLMs. To address these challenges, we propose MLTFR, a Multi-LLM Token Filtering and Routing framework for corpus-free sequential recommendation. MLTFR follows an interaction-guided LLM knowledge integration paradigm, where task-relevant token embeddings are selected via user-guided token filtering to suppress noisy and irrelevant vocabulary signals. To overcome the limitations of single-LLM representations, MLTFR integrates multiple LLM token spaces through a Mixture-of-Experts architecture, with a Fisher-weighted semantic consensus expert to balance heterogeneous experts and prevent domination during training. By jointly filtering informative tokens and aggregating complementary semantic knowledge across multiple LLMs, MLTFR enables stable and effective utilization of LLM token embeddings without textual inputs or backbone modification. Extensive experiments demonstrate that MLTFR consistently outperforms state-of-the-art sequential recommendation baselines and existing alignment methods. Our code is available at: https://github.com/ccwwhhh/MLTFR.

Wei Li, Xing Wang, Xin Xia et al.

Vision Transformers have witnessed prevailing success in a series of vision tasks. However, these Transformers often rely on extensive computational costs to achieve high performance, which is burdensome to deploy on resource-constrained devices. To alleviate this issue, we draw lessons from depthwise separable convolution and imitate its ideology to design an efficient Transformer backbone, i.e., Separable Vision Transformer, abbreviated as SepViT. SepViT helps to carry out the local-global information interaction within and among the windows in sequential order via a depthwise separable self-attention. The novel window token embedding and grouped self-attention are employed to compute the attention relationship among windows with negligible cost and establish long-range visual interactions across multiple windows, respectively. Extensive experiments on general-purpose vision benchmarks demonstrate that SepViT can achieve a state-of-the-art trade-off between performance and latency. Among them, SepViT achieves 84.2% top-1 accuracy on ImageNet-1K classification while decreasing the latency by 40%, compared to the ones with similar accuracy (e.g., CSWin). Furthermore, SepViT achieves 51.0% mIoU on ADE20K semantic segmentation task, 47.9 AP on the RetinaNet-based COCO detection task, 49.4 box AP and 44.6 mask AP on Mask R-CNN-based COCO object detection and instance segmentation tasks.

Jia Li, Zhuo Li, Huangzhao Zhang et al.

In the software engineering community, deep learning (DL) has recently been applied to many source code processing tasks. Due to the poor interpretability of DL models, their security vulnerabilities require scrutiny. Recently, researchers have identified an emergent security threat, namely poison attack. The attackers aim to inject insidious backdoors into models by poisoning the training data with poison samples. Poisoned models work normally with clean inputs but produce targeted erroneous results with poisoned inputs embedded with triggers. By activating backdoors, attackers can manipulate the poisoned models in security-related scenarios. To verify the vulnerability of existing deep source code processing models to the poison attack, we present a poison attack framework for source code named CodePoisoner as a strong imaginary enemy. CodePoisoner can produce compilable even human-imperceptible poison samples and attack models by poisoning the training data with poison samples. To defend against the poison attack, we further propose an effective defense approach named CodeDetector to detect poison samples in the training data. CodeDetector can be applied to many model architectures and effectively defend against multiple poison attack approaches. We apply our CodePoisoner and CodeDetector to three tasks, including defect detection, clone detection, and code repair. The results show that (1) CodePoisoner achieves a high attack success rate (max: 100%) in misleading models to targeted erroneous behaviors. It validates that existing deep source code processing models have a strong vulnerability to the poison attack. (2) CodeDetector effectively defends against multiple poison attack approaches by detecting (max: 100%) poison samples in the training data. We hope this work can help practitioners notice the poison attack and inspire the design of more advanced defense techniques.

Xin Xia, Jiashi Li, Jie Wu et al.

We revisit the existing excellent Transformers from the perspective of practical application. Most of them are not even as efficient as the basic ResNets series and deviate from the realistic deployment scenario. It may be due to the current criterion to measure computation efficiency, such as FLOPs or parameters is one-sided, sub-optimal, and hardware-insensitive. Thus, this paper directly treats the TensorRT latency on the specific hardware as an efficiency metric, which provides more comprehensive feedback involving computational capacity, memory cost, and bandwidth. Based on a series of controlled experiments, this work derives four practical guidelines for TensorRT-oriented and deployment-friendly network design, e.g., early CNN and late Transformer at stage-level, early Transformer and late CNN at block-level. Accordingly, a family of TensortRT-oriented Transformers is presented, abbreviated as TRT-ViT. Extensive experiments demonstrate that TRT-ViT significantly outperforms existing ConvNets and vision Transformers with respect to the latency/accuracy trade-off across diverse visual tasks, e.g., image classification, object detection and semantic segmentation. For example, at 82.7% ImageNet-1k top-1 accuracy, TRT-ViT is 2.7$\times$ faster than CSWin and 2.0$\times$ faster than Twins. On the MS-COCO object detection task, TRT-ViT achieves comparable performance with Twins, while the inference speed is increased by 2.8$\times$.

Shuhan Liu, Zhiyi Zhao, Xing Hu et al.

Repository-level code agents have shown strong promise in real-world feature addition tasks, making reliable evaluation of their capabilities increasingly important. However, existing benchmarks primarily evaluate these agents as black boxes based on final test correctness, providing limited insight into how they reason and where failures arise. To address this limitation, we introduce RACE-bench, a reasoning-augmented benchmark for evaluating code agents on repository-level feature addition tasks. RACE-bench contains 528 real-world feature addition instances from 12 open-source repositories. Each instance is paired with executable patch verification and structured intermediate reasoning ground truth covering issue understanding, file localization, implementation tasks, and step decomposition. Based on this design, we introduce a dual-track evaluation framework that jointly measures patch correctness and intermediate reasoning quality. We evaluate three representative repository-level code agents on RACE-bench. On the full benchmark, Resolved Rates range from 29% to 70% across different agents. Our reasoning-level analysis further shows that while current agents perform well at understanding high-level intent, their performance degrades substantially when translating intent into concrete implementation steps. We also find that apply-success but test-fail cases exhibit lower reasoning recall (35.7% decrease) and higher over-prediction (94.1% increase) compared to successful cases. These findings highlight the importance of evaluating repository-level code agents beyond final patch correctness by examining the quality of their reasoning processes.

Hailong Ma, Xin Xia, Xing Wang et al.

Recently, Transformer networks have achieved impressive results on a variety of vision tasks. However, most of them are computationally expensive and not suitable for real-world mobile applications. In this work, we present Mobile Convolutional Vision Transformer (MoCoViT), which improves in performance and efficiency by introducing transformer into mobile convolutional networks to leverage the benefits of both architectures. Different from recent works on vision transformer, the mobile transformer block in MoCoViT is carefully designed for mobile devices and is very lightweight, accomplished through two primary modifications: the Mobile Self-Attention (MoSA) module and the Mobile Feed Forward Network (MoFFN). MoSA simplifies the calculation of the attention map through Branch Sharing scheme while MoFFN serves as a mobile version of MLP in the transformer, further reducing the computation by a large margin. Comprehensive experiments verify that our proposed MoCoViT family outperform state-of-the-art portable CNNs and transformer neural architectures on various vision tasks. On ImageNet classification, it achieves 74.5% top-1 accuracy at 147M FLOPs, gaining 1.2% over MobileNetV3 with less computations. And on the COCO object detection task, MoCoViT outperforms GhostNet by 2.1 AP in RetinaNet framework.

Zirui Chen, Qi Zhan, Jiayuan Zhou et al.

Open-source software supply chain security relies heavily on assessing affected versions of library vulnerabilities. While prior studies have leveraged exploits for verifying vulnerability affected versions, they point out a key limitation that exploits are version-specific and cannot be directly applied across library versions. Despite being widely acknowledged, this limitation has not been systematically validated at scale, leaving the actual applicability of exploits across versions unexplored. To fill this gap, we conduct the first large-scale empirical study on exploit applicability across library versions. We construct a comprehensive dataset consisting of 259 exploits spanning 128 Java libraries and 28,150 historical versions, covering 61 CWEs that account for 76.33% of vulnerabilities in Maven. Leveraging this dataset, we execute each exploit against the library version history and compare the execution outcomes with our manually annotated ground-truth affected versions. We further investigate the root causes of inconsistencies between exploit execution and ground truth, and explore strategies for exploit migration. Our results (RQ1) show that, even without migration, exploits achieve 83.0% recall and 99.3% precision in identifying affected versions in Java, outperforming most widely used vulnerability databases and assessment tools. Notably, this capability enables us to contribute 796 confirmed missing affected versions to the CPE dictionary. We investigate the remaining exploit failures (RQ2) and find that they mainly stem from compatibility issues introduced by library evolution and changing environmental constraints. Based on these observations, we manually migrate exploits for 1,885 versions and distill a taxonomy of 10 strategies from these successful adaptation cases (RQ3), thereby increasing the overall recall to 96.1%.

Haichao Zhang, Jiashi Li, Xin Xia et al.

Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the image classification task. However, the architecture which is searched through the classification task is sub-optimal because of the gap between the task of image and object detection. As while work focuses on backbone network architecture search for mobile device object detection is limited, mainly because the backbone always requires expensive ImageNet pre-training. Accordingly, it is necessary to study the approach of network architecture search for mobile device object detection without expensive pre-training. In this work, we propose a mobile object detection backbone network architecture search algorithm which is a kind of evolutionary optimized method based on non-dominated sorting for NAS scenarios. It can quickly search to obtain the backbone network architecture within certain constraints. It better solves the problem of suboptimal linear combination accuracy and computational cost. The proposed approach can search the backbone networks with different depths, widths, or expansion sizes via a technique of weight mapping, making it possible to use NAS for mobile devices detection tasks a lot more efficiently. In our experiments, we verify the effectiveness of the proposed approach on YoloX-Lite, a lightweight version of the target detection framework. Under similar computational complexity, the accuracy of the backbone network architecture we search for is 2.0% mAP higher than MobileDet. Our improved backbone network can reduce the computational effort while improving the accuracy of the object detection network. To prove its effectiveness, a series of ablation studies have been carried out and the working mechanism has been analyzed in detail.

Zhixia Zhang, Zixuan Huang, Xin Xia et al.

We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new learning paradigm that addresses the inefficiencies of isolated on-policy optimization. HACRL enables collaborative optimization with independent execution: heterogeneous agents share verified rollouts during training to mutually improve, while operating independently at inference time. Unlike LLM-based multi-agent reinforcement learning (MARL), HACRL does not require coordinated deployment, and unlike on-/off-policy distillation, it enables bidirectional mutual learning among heterogeneous agents rather than one-directional teacher-to-student transfer. Building on this paradigm, we propose HACPO, a collaborative RL algorithm that enables principled rollout sharing to maximize sample utilization and cross-agent knowledge transfer. To mitigate capability discrepancies and policy distribution shifts, HACPO introduces four tailored mechanisms with theoretical guarantees on unbiased advantage estimation and optimization correctness. Extensive experiments across diverse heterogeneous model combinations and reasoning benchmarks show that HACPO consistently improves all participating agents, outperforming GSPO by an average of 3.3\% while using only half the rollout cost.

Junkai Chen, Zhiyuan Pan, Xing Hu et al.

Large language models for code (i.e., code LLMs) have shown strong code understanding and generation capabilities. To evaluate the capabilities of code LLMs in various aspects, many benchmarks have been proposed (e.g., HumanEval and ClassEval). Code reasoning is one of the most essential abilities of code LLMs, but existing benchmarks for code reasoning are not sufficient. Typically, they focus on predicting the input and output of a program, ignoring the evaluation of the intermediate behavior during program execution, as well as the logical consistency (e.g., the model should not give the correct output if the prediction of execution path is wrong) when performing the reasoning. To address these problems, in this paper, we propose a framework, namely REval, for evaluating code reasoning abilities and consistency of code LLMs with program execution. We utilize existing code benchmarks and adapt them to new benchmarks within our framework. A large-scale empirical study is conducted and most LLMs show unsatisfactory performance on both Runtime Behavior Reasoning (i.e., an average accuracy of 44.4%) and Incremental Consistency Evaluation (i.e., an average IC score of 10.3). Evaluation results of current code LLMs reflect the urgent need for the community to strengthen the code reasoning capability of code LLMs. Our code, data, and \newname leaderboard are available at https://r-eval.github.io.

Zixuan Huang, Xin Xia, Yuxi Ren et al.

Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. Recent studies show that longer reasoning chains are frequently uncorrelated with correctness and can even be detrimental to accuracy. In a further in-depth analysis of this phenomenon, we surprisingly uncover and empirically verify that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms. Motivated by this, we introduce SAGE (Self-Aware Guided Efficient Reasoning), a novel sampling paradigm that unleashes this efficient reasoning potential. Furthermore, integrating SAGE as mixed sampling into group-based reinforcement learning (SAGE-RL) enables SAGE-RL to effectively incorporate SAGE-discovered efficient reasoning patterns into standard pass@1 inference, markedly enhancing both the reasoning accuracy and efficiency of LRMs across multiple challenging mathematical benchmarks.

Zixuan Huang, Xin Xia, Yuxi Ren et al.

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model, exploit spurious reward patterns instead of faithfully capturing human intent. Prior mitigations primarily relies on surface semantic information and fails to efficiently address the misalignment between the reward model (RM) and the policy model caused by continuous policy distribution shifts. This inevitably leads to an increasing reward discrepancy, exacerbating reward overoptimization. To address these limitations, we introduce R2M (Real-Time Aligned Reward Model), a novel lightweight RLHF framework. R2M goes beyond vanilla reward models that solely depend on the semantic representations of a pretrained LLM. Instead, it leverages the evolving hidden states of the policy (namely policy feedback) to align with the real-time distribution shift of the policy during the RL process. This work points to a promising new direction for improving the performance of reward models through real-time utilization of feedback from policy models.

Hao Duong Le, Xin Xia, Zhang Chen

Causal discovery aims to identify causal relationships between variables and is a critical research area in machine learning. Traditional methods focus on statistical or machine learning algorithms to uncover causal links from structured data, often overlooking the valuable contextual information provided by metadata. Large language models (LLMs) have shown promise in creating unified causal discovery frameworks by incorporating both structured data and metadata. However, their potential in multi-agent settings remains largely unexplored. To address this gap, we introduce the Multi-Agent Causal Discovery Framework (MAC), which consists of two key modules: the Debate-Coding Module (DCM) and the Meta-Debate Module (MDM). The DCM begins with a multi-agent debating and coding process, where agents use both structured data and metadata to collaboratively select the most suitable statistical causal discovery (SCD) method. The selected SCD is then applied to the structured data to generate an initial causal graph. This causal graph is transformed into causal metadata through the Meta Fusion mechanism. With all the metadata, MDM then refines the causal structure by leveraging a multi-agent debating framework. Extensive experiments across five datasets demonstrate that MAC outperforms both traditional statistical causal discovery methods and existing LLM-based approaches, achieving state-of-the-art performance.

Xin Xia, Yansen Su, Chunhou Zheng et al.

Machine learning methods have been used to accelerate the molecule optimization process. However, efficient search for optimized molecules satisfying several properties with scarce labeled data remains a challenge for machine learning molecule optimization. In this study, we propose MOMO, a multi-objective molecule optimization framework to address the challenge by combining learning of chemical knowledge with Pareto-based multi-objective evolutionary search. To learn chemistry, it employs a self-supervised codec to construct an implicit chemical space and acquire the continues representation of molecules. To explore the established chemical space, MOMO uses multi-objective evolution to comprehensively and efficiently search for similar molecules with multiple desirable properties. We demonstrate the high performance of MOMO on four multi-objective property and similarity optimization tasks, and illustrate the search capability of MOMO through case studies. Remarkably, our approach significantly outperforms previous approaches in optimizing three objectives simultaneously. The results show the optimization capability of MOMO, suggesting to improve the success rate of lead molecule optimization.

Shufan Wang, Xing Hu, Junkai Chen et al.

With the widespread application of large language models (LLMs) in the field of code intelligence, increasing attention has been paid to the reliability and controllability of their outputs in code reasoning tasks. Confidence estimation serves as an effective and convenient approach for evaluating these aspects. This paper proposes a confidence analysis and enhancement framework for LLMs tailored to code reasoning tasks. We conduct a comprehensive empirical study on the confidence reliability of mainstream LLMs across different tasks, and further evaluate the effectiveness of techniques such as prompt strategy optimisation and mathematical calibration (e.g., Platt Scaling) in improving confidence reliability. Our results show that DeepSeek-Reasoner achieves the best performance across various tasks, outperforming other models by up to $0.680$, $0.636$, and $13.652$ in terms of ECE, Brier Score, and Performance Score, respectively. The hybrid strategy combining the reassess prompt strategy and Platt Scaling achieves improvements of up to $0.541$, $0.628$, and $15.084$ over the original performance in the aforementioned three metrics. These results indicate that models with reasoning capabilities demonstrate superior confidence reliability, and that the hybrid strategy is the most effective in enhancing the confidence reliability of various models. Meanwhile, we elucidate the impact of different task complexities, model scales, and strategies on confidence performance, and highlight that the confidence of current LLMs in complex reasoning tasks still has considerable room for improvement. This study not only provides a research foundation and technical reference for the application of confidence in LLM-assisted software engineering, but also points the way for future optimisation and engineering deployment of confidence mechanisms.

Xinyu Liu, Yukai Zhao, Xing Hu et al.

Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for systematic security evaluation. Current auditing mechanisms are effective at identifying explicit code payloads and predefined threat contents through security scanning. These detection mechanisms are bypassed if malicious behaviors lack direct injection and are instead synthesized dynamically at runtime through the agent's inherent generative capabilities. Exploring this blind spot, we introduce Semantic Compliance Hijacking (SCH), a payload-less supply chain attack targeting autonomous coding environments. The SCH approach translates malicious goals into unstructured natural language instructions formatted as necessary compliance rules, leading the agent to generate and execute unauthorized code. To assess the real-world viability of this attack, we developed an automated pipeline to evaluate its effectiveness across a test matrix comprising three mainstream agent frameworks and three distinct foundation models using contextualized scenarios. The findings demonstrate the pervasive nature of this threat, with SCH achieving peak success rates of up to 77.67% for confidentiality breaches and 67.33% for Remote Code Execution (RCE) under the most vulnerable configurations. Furthermore, the introduction of Multi-Skill Automated Optimization (MS-AO) further boosted attack efficacy. By omitting recognizable Abstract Syntax Tree (AST) signatures and explicit harmful intents, the manipulated skill files maintained a 0.00% detection rate, evading current scanning tools. This research highlights an underexplored attack surface within agent supply chains, pointing to a necessary transition from signature-based detection models toward semantic intent validation.

Ruiqi Wang, Xinchen Wang, Cuiyun Gao et al.

Large language models (LLMs) have been increasingly deployed in real-world software engineering, fostering the development of code evaluation metrics to study the quality of LLM-generated code. Conventional rule-based metrics merely score programs based on their surface-level similarities with reference programs instead of analyzing functionality and code quality in depth. To address this limitation, researchers have developed LLM-as-a-judge metrics, prompting LLMs to evaluate and score code, and curated various code evaluation benchmarks to validate their effectiveness. However, these benchmarks suffer from critical limitations, hindering reliable assessments of evaluation capability: Some feature coarse-grained binary labels, which reduce rich code behavior to a single bit of information, obscuring subtle errors. Others propose fine-grained but subjective, vaguely-defined evaluation criteria, introducing unreliability in manually-annotated scores, which is the ground-truth they rely on. Furthermore, they often use uncontrolled data synthesis methods, leading to unbalanced score distributions that poorly represent real-world code generation scenarios. To curate a diverse benchmark with programs of well-balanced distributions across various quality levels and streamline the manual annotation procedure, we propose AXIOM, a novel perturbation-based framework for synthesizing code evaluation benchmarks at scale. It reframes program scores as the refinement effort needed for deployment, consisting of two stages: (1) Rule-guided perturbation, which prompts LLMs to apply sequences of predefined perturbation rules to existing high-quality programs to modify their functionality and code quality, enabling us to precisely control each program's target score to achieve balanced score distributions. (2) Multisource quality calibration, which first selects a subset of...

Qi Zhan, Xing Hu, Xin Xia et al.

Verifying whether two implementations of the same large model are equivalent across frameworks is difficult in practice. Even when they realize the same computation, their graphs may differ substantially in operator decomposition, tensor layout, and the use of fused or opaque kernels, making manual rewrite rules hard to build and maintain. We present Emerge, a framework for checking Implementation Equivalence over computation graphs of large-model implementations. Instead of writing rules manually, Emerge represents the two implementations in an e-graph, infers candidate relations from execution values, and synthesizes rewrite rules on demand when existing rules are insufficient. Each synthesized rule is validated using the strongest applicable method, including SMT- based checking for symbolically tractable cases and constraint-aware randomized testing for opaque kernels, and then propagated through e-graph rebuilding to establish larger equivalences. Our current implementation targets inference computation graphs captured from HuggingFace Transformers and vLLM. Our evaluation shows that Emerge establishes equivalence for correct implementation pairs at practical cost, while also providing useful by-products for debugging: it detects 10 of 13 known implementation bugs and uncovers 8 previously unknown implementation issues that were later confirmed by developers. In addition, Emerge synthesizes block-level rules that compare favorably with manually authored ones.

Yuan Shi, Bin Xia, Xiaoyu Jin et al.

Image restoration is a critical task in low-level computer vision, aiming to restore high-quality images from degraded inputs. Various models, such as convolutional neural networks (CNNs), generative adversarial networks (GANs), transformers, and diffusion models (DMs), have been employed to address this problem with significant impact. However, CNNs have limitations in capturing long-range dependencies. DMs require large prior models and computationally intensive denoising steps. Transformers have powerful modeling capabilities but face challenges due to quadratic complexity with input image size. To address these challenges, we propose VmambaIR, which introduces State Space Models (SSMs) with linear complexity into comprehensive image restoration tasks. We utilize a Unet architecture to stack our proposed Omni Selective Scan (OSS) blocks, consisting of an OSS module and an Efficient Feed-Forward Network (EFFN). Our proposed omni selective scan mechanism overcomes the unidirectional modeling limitation of SSMs by efficiently modeling image information flows in all six directions. Furthermore, we conducted a comprehensive evaluation of our VmambaIR across multiple image restoration tasks, including image deraining, single image super-resolution, and real-world image super-resolution. Extensive experimental results demonstrate that our proposed VmambaIR achieves state-of-the-art (SOTA) performance with much fewer computational resources and parameters. Our research highlights the potential of state space models as promising alternatives to the transformer and CNN architectures in serving as foundational frameworks for next-generation low-level visual tasks.

Xin Xia, Nejla Yuruk, Yun Wang et al.

Generative artificial intelligence (AI) offers scalable support for formative feedback, yet most AI-generated feedback relies on task-specific rubrics authored by domain experts. While effective, rubric authoring is time-consuming and limits scalability across instructional contexts. Learning progressions (LP) provide a theoretically grounded representation of students' developing understanding and may offer an alternative solution. This study examines whether an LP-driven rubric generation pipeline can produce AI-generated feedback comparable in quality to feedback guided by expert-authored task rubrics. We analyzed AI-generated feedback for written scientific explanations produced by 207 middle school students in a chemistry task. Two pipelines were compared: (a) feedback guided by a human expert-designed, task-specific rubric, and (b) feedback guided by a task-specific rubric automatically derived from a learning progression prior to grading and feedback generation. Two human coders evaluated feedback quality using a multi-dimensional rubric assessing Clarity, Accuracy, Relevance, Engagement and Motivation, and Reflectiveness (10 sub-dimensions). Inter-rater reliability was high, with percent agreement ranging from 89% to 100% and Cohen's kappa values for estimable dimensions (kappa = .66 to .88). Paired t-tests revealed no statistically significant differences between the two pipelines for Clarity (t1 = 0.00, p1 = 1.000; t2 = 0.84, p2 = .399), Relevance (t1 = 0.28, p1 = .782; t2 = -0.58, p2 = .565), Engagement and Motivation (t1 = 0.50, p1 = .618; t2 = -0.58, p2 = .565), or Reflectiveness (t = -0.45, p = .656). These findings suggest that the LP-driven rubric pipeline can serve as an alternative solution.

Yuxi Ren, Xin Xia, Yanzuo Lu et al.

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize into two distinct aspects: i) ODE Trajectory Preservation; and ii) ODE Trajectory Reformulation. However, these approaches suffer from severe performance degradation or domain shifts. To address these limitations, we propose Hyper-SD, a novel framework that synergistically amalgamates the advantages of ODE Trajectory Preservation and Reformulation, while maintaining near-lossless performance during step compression. Firstly, we introduce Trajectory Segmented Consistency Distillation to progressively perform consistent distillation within pre-defined time-step segments, which facilitates the preservation of the original ODE trajectory from a higher-order perspective. Secondly, we incorporate human feedback learning to boost the performance of the model in a low-step regime and mitigate the performance loss incurred by the distillation process. Thirdly, we integrate score distillation to further improve the low-step generation capability of the model and offer the first attempt to leverage a unified LoRA to support the inference process at all steps. Extensive experiments and user studies demonstrate that Hyper-SD achieves SOTA performance from 1 to 8 inference steps for both SDXL and SD1.5. For example, Hyper-SDXL surpasses SDXL-Lightning by +0.68 in CLIP Score and +0.51 in Aes Score in the 1-step inference.

Zhiyuan Pan, Xing Hu, Xin Xia et al.

In the era of large language models (LLMs), code benchmarks have become an important research area in software engineering and are widely used by practitioners. These benchmarks evaluate the performance of LLMs on specific code-related tasks, such as code understanding and generation. A critical step in constructing code benchmarks is the design of prompts. However, as existing code benchmarks typically rely on a single prompt template per task, they are prone to the issue of prompt sensitivity, where minor prompt variations could result in substantial performance variations, leading to unreliable evaluations of model capabilities. While previous studies have explored prompt sensitivity, their experimental designs and findings are limited to traditional natural language processing (NLP) tasks. In this paper, we present an empirical study to investigate prompt sensitivity in code benchmarks. We first propose a general framework that modifies prompt templates in a manner that preserves both their semantics and their structure as much as possible. Based on the framework, we conduct extensive experiments across eight code benchmark tasks on 10 representative open-source LLMs, with each task featuring 100 semantically similar prompt templates. We then analyze the evaluation results using various statistical metrics, focusing on both absolute and relative model performance. Our findings suggest that even slight prompt variations can lead to significant shifts in performance. Additionally, we observe that such variations can introduce inconsistencies in the performance rankings across different models. These insights highlight the need for considering prompt sensitivity when designing future code benchmarks, to ensure more reliable and accurate evaluation of LLM capabilities.

Junkai Chen, Zhenhao Li, Xing Hu et al.

Large language models (LLMs) achieve promising results in code generation based on a given natural language description. They have been integrated into open-source projects and commercial products to facilitate daily coding activities. The natural language description in the prompt is crucial for LLMs to comprehend users' requirements. Prior studies uncover that LLMs are sensitive to the changes in the prompts, including slight changes that look inconspicuous. However, the natural language descriptions often vary in real-world scenarios (e.g., different formats, grammar, and wording). Prior studies on the robustness of LLMs are often based on random perturbations and such perturbations may not actually happen. In this paper, we conduct a comprehensive study to investigate how are code LLMs robust to variations of natural language description in real-world scenarios. We summarize 18 categories of perturbations of natural language and 3 combinations of co-occurred categories based on our literature review and an online survey with practitioners. We propose an automated framework, NLPerturbator, which can perform perturbations of each category given a set of prompts. Through a series of experiments on code generation using six code LLMs, we find that the perturbed prompts can decrease the performance of code generation by a considerable margin (e.g., up to 21.2%, and 4.8% to 6.1% on average). Our study highlights the importance of enhancing the robustness of LLMs to real-world variations in the prompts, as well as the essentiality of attentively constructing the prompts.

Zhiyuan Pan, Xing Hu, Xin Xia et al.

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, repository-level code generation presents unique challenges, particularly due to the need to utilize information spread across multiple files within a repository. Specifically, successful generation depends on a solid grasp of both general, context-agnostic knowledge and specific, context-dependent knowledge. While LLMs are widely used for the context-agnostic aspect, existing retrieval-based approaches sometimes fall short as they are limited in obtaining a broader and deeper repository context. In this paper, we present CatCoder, a novel code generation framework designed for statically typed programming languages. CatCoder enhances repository-level code generation by integrating relevant code and type context. Specifically, it leverages static analyzers to extract type dependencies and merges this information with retrieved code to create comprehensive prompts for LLMs. To evaluate the effectiveness of CatCoder, we adapt and construct benchmarks that include 199 Java tasks and 90 Rust tasks. The results show that CatCoder outperforms the RepoCoder baseline by up to 14.44% and 17.35%, in terms of compile@k and pass@k scores. In addition, the generalizability of CatCoder is assessed using various LLMs, including both code-specialized models and general-purpose models. Our findings indicate consistent performance improvements across all models, which underlines the practicality of CatCoder. Furthermore, we evaluate the time consumption of CatCoder in a large open source repository, and the results demonstrate the scalability of CatCoder.

Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang et al.

With the increasing reliance on Open Source Software, users are exposed to third-party library vulnerabilities. Software Composition Analysis (SCA) tools have been created to alert users of such vulnerabilities. SCA requires the identification of vulnerability-fixing commits. Prior works have proposed methods that can automatically identify such vulnerability-fixing commits. However, identifying such commits is highly challenging, as only a very small minority of commits are vulnerability fixing. Moreover, code changes can be noisy and difficult to analyze. We observe that noise can occur at different levels of detail, making it challenging to detect vulnerability fixes accurately. To address these challenges and boost the effectiveness of prior works, we propose MiDas (Multi-Granularity Detector for Vulnerability Fixes). Unique from prior works, Midas constructs different neural networks for each level of code change granularity, corresponding to commit-level, file-level, hunk-level, and line-level, following their natural organization. It then utilizes an ensemble model that combines all base models to generate the final prediction. This design allows MiDas to better handle the noisy and highly imbalanced nature of vulnerability-fixing commit data. Additionally, to reduce the human effort required to inspect code changes, we have designed an effort-aware adjustment for Midas's outputs based on commit length. The evaluation results demonstrate that MiDas outperforms the current state-of-the-art baseline in terms of AUC by 4.9% and 13.7% on Java and Python-based datasets, respectively. Furthermore, in terms of two effort-aware metrics, EffortCost@L and Popt@L, MiDas also outperforms the state-of-the-art baseline, achieving improvements of up to 28.2% and 15.9% on Java, and 60% and 51.4% on Python, respectively.

Ziwen Wan, Junjie Shen, Jalen Chuang et al.

In high-level Autonomous Driving (AD) systems, behavioral planning is in charge of making high-level driving decisions such as cruising and stopping, and thus highly securitycritical. In this work, we perform the first systematic study of semantic security vulnerabilities specific to overly-conservative AD behavioral planning behaviors, i.e., those that can cause failed or significantly-degraded mission performance, which can be critical for AD services such as robo-taxi/delivery. We call them semantic Denial-of-Service (DoS) vulnerabilities, which we envision to be most generally exposed in practical AD systems due to the tendency for conservativeness to avoid safety incidents. To achieve high practicality and realism, we assume that the attacker can only introduce seemingly-benign external physical objects to the driving environment, e.g., off-road dumped cardboard boxes. To systematically discover such vulnerabilities, we design PlanFuzz, a novel dynamic testing approach that addresses various problem-specific design challenges. Specifically, we propose and identify planning invariants as novel testing oracles, and design new input generation to systematically enforce problemspecific constraints for attacker-introduced physical objects. We also design a novel behavioral planning vulnerability distance metric to effectively guide the discovery. We evaluate PlanFuzz on 3 planning implementations from practical open-source AD systems, and find that it can effectively discover 9 previouslyunknown semantic DoS vulnerabilities without false positives. We find all our new designs necessary, as without each design, statistically significant performance drops are generally observed. We further perform exploitation case studies using simulation and real-vehicle traces. We discuss root causes and potential fixes.

Junliang Yu, Hongzhi Yin, Xin Xia et al.

Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling the data sparsity issue. A typical pipeline of CL-based recommendation models is first augmenting the user-item bipartite graph with structure perturbations, and then maximizing the node representation consistency between different graph augmentations. Although this paradigm turns out to be effective, what underlies the performance gains is still a mystery. In this paper, we first experimentally disclose that, in CL-based recommendation models, CL operates by learning more evenly distributed user/item representations that can implicitly mitigate the popularity bias. Meanwhile, we reveal that the graph augmentations, which were considered necessary, just play a trivial role. Based on this finding, we propose a simple CL method which discards the graph augmentations and instead adds uniform noises to the embedding space for creating contrastive views. A comprehensive experimental study on three benchmark datasets demonstrates that, though it appears strikingly simple, the proposed method can smoothly adjust the uniformity of learned representations and has distinct advantages over its graph augmentation-based counterparts in terms of recommendation accuracy and training efficiency. The code is released at https://github.com/Coder-Yu/QRec.

Runsheng Xu, Yi Guo, Xu Han et al.

Although Cooperative Driving Automation (CDA) has attracted considerable attention in recent years, there remain numerous open challenges in this field. The gap between existing simulation platforms that mainly concentrate on single-vehicle intelligence and CDA development is one of the critical barriers, as it inhibits researchers from validating and comparing different CDA algorithms conveniently. To this end, we propose OpenCDA, a generalized framework and tool for developing and testing CDA systems. Specifically, OpenCDA is composed of three major components: a co-simulation platform with simulators of different purposes and resolutions, a full-stack cooperative driving system, and a scenario manager. Through the interactions of these three components, our framework offers a straightforward way for researchers to test different CDA algorithms at both levels of traffic and individual autonomy. More importantly, OpenCDA is highly modularized and installed with benchmark algorithms and test cases. Users can conveniently replace any default module with customized algorithms and use other default modules of the CDA platform to perform evaluations of the effectiveness of new functionalities in enhancing the overall CDA performance. An example of platooning implementation is used to illustrate the framework's capability for CDA research. The codes of OpenCDA are available in the https://github.com/ucla-mobility/OpenCDA.

Junliang Yu, Hongzhi Yin, Min Gao et al.

Self-supervised learning (SSL), which can automatically generate ground-truth samples from raw data, holds vast potential to improve recommender systems. Most existing SSL-based methods perturb the raw data graph with uniform node/edge dropout to generate new data views and then conduct the self-discrimination based contrastive learning over different views to learn generalizable representations. Under this scheme, only a bijective mapping is built between nodes in two different views, which means that the self-supervision signals from other nodes are being neglected. Due to the widely observed homophily in recommender systems, we argue that the supervisory signals from other nodes are also highly likely to benefit the representation learning for recommendation. To capture these signals, a general socially-aware SSL framework that integrates tri-training is proposed in this paper. Technically, our framework first augments the user data views with the user social information. And then under the regime of tri-training for multi-view encoding, the framework builds three graph encoders (one for recommendation) upon the augmented views and iteratively improves each encoder with self-supervision signals from other users, generated by the other two encoders. Since the tri-training operates on the augmented views of the same data sources for self-supervision signals, we name it self-supervised tri-training. Extensive experiments on multiple real-world datasets consistently validate the effectiveness of the self-supervised tri-training framework for improving recommendation. The code is released at https://github.com/Coder-Yu/QRec.

Junxiao Han, Shuiguang Deng, David Lo et al.

Open source software has drawn more and more attention from researchers, developers and companies nowadays. Meanwhile, many Chinese technology companies are embracing open source and choosing to open source their projects. Nevertheless, most previous studies are concentrated on international companies such as Microsoft or Google, while the practical values of open source projects of Chinese technology companies remain unclear. To address this issue, we conduct a mixed-method study to investigate the landscape of projects open sourced by three large Chinese technology companies, namely Baidu, Alibaba, and Tencent (BAT). We study the categories and characteristics of open source projects, the developer's perceptions towards open sourcing effort for these companies, and the internationalization effort of their open source projects. We collected 1,000 open source projects that were open sourced by BAT in GitHub and performed an online survey that received 101 responses from developers of these projects. Some key findings include: 1) BAT prefer to open source frontend development projects, 2) 88\% of the respondents are positive towards open sourcing software projects in their respective companies, 3) 64\% of the respondents reveal that the most common motivations for BAT to open source their projects are the desire to gain fame, expand their influence and gain recruitment advantage, 4) respondents believe that the most common internationalization effort is "providing an English version of readme files", 5) projects with more internationalization effort (i.e., include an English readme file) are more popular. Our findings provide directions for software engineering researchers and provide practical suggestions to software developers and Chinese technology companies.

Xin Xia, Hongzhi Yin, Junliang Yu et al.

Session-based recommendation (SBR) focuses on next-item prediction at a certain time point. As user profiles are generally not available in this scenario, capturing the user intent lying in the item transitions plays a pivotal role. Recent graph neural networks (GNNs) based SBR methods regard the item transitions as pairwise relations, which neglect the complex high-order information among items. Hypergraph provides a natural way to capture beyond-pairwise relations, while its potential for SBR has remained unexplored. In this paper, we fill this gap by modeling session-based data as a hypergraph and then propose a hypergraph convolutional network to improve SBR. Moreover, to enhance hypergraph modeling, we devise another graph convolutional network which is based on the line graph of the hypergraph and then integrate self-supervised learning into the training of the networks by maximizing mutual information between the session representations learned via the two networks, serving as an auxiliary task to improve the recommendation task. Since the two types of networks both are based on hypergraph, which can be seen as two channels for hypergraph modeling, we name our model \textbf{DHCN} (Dual Channel Hypergraph Convolutional Networks). Extensive experiments on three benchmark datasets demonstrate the superiority of our model over the SOTA methods, and the results validate the effectiveness of hypergraph modeling and self-supervised task. The implementation of our model is available at https://github.com/xiaxin1998/DHCN

Jiachi Chen, Xin Xia, David Lo et al.

Smart contracts are Turing-complete programs running on the blockchain. They are immutable and cannot be modified, even when bugs are detected. Therefore, ensuring smart contracts are bug-free and well-designed before deploying them to the blockchain is extremely important. A contract defect is an error, flaw or fault in a smart contract that causes it to produce an incorrect or unexpected result, or to behave in unintended ways. Detecting and removing contract defects can avoid potential bugs and make programs more robust. Our previous work defined 20 contract defects for smart contracts and divided them into five impact levels. According to our classification, contract defects with seriousness level between 1-3 can lead to unwanted behaviors, e.g., a contract being controlled by attackers. In this paper, we propose DefectChecker, a symbolic execution-based approach and tool to detect eight contract defects that can cause unwanted behaviors of smart contracts on the Ethereum blockchain platform. DefectChecker can detect contract defects from smart contracts bytecode. We compare DefectChecker with key previous works, including Oyente, Mythril and Securify by using an open-source dataset. Our experimental results show that DefectChecker performs much better than these tools in terms of both speed and accuracy. We also applied DefectChecker to 165,621 distinct smart contracts on the Ethereum platform. We found that 25,815 of these smart contracts contain at least one of the contract defects that belongs to impact level 1-3, including some real-world attacks.

Hao Xiang, Zhaoliang Zheng, Xin Xia et al.

Recent advancements in Vehicle-to-Everything (V2X) technologies have enabled autonomous vehicles to share sensing information to see through occlusions, greatly boosting the perception capability. However, there are no real-world datasets to facilitate the real V2X cooperative perception research -- existing datasets either only support Vehicle-to-Infrastructure cooperation or Vehicle-to-Vehicle cooperation. In this paper, we present V2X-Real, a large-scale dataset that includes a mixture of multiple vehicles and smart infrastructure to facilitate the V2X cooperative perception development with multi-modality sensing data. Our V2X-Real is collected using two connected automated vehicles and two smart infrastructure, which are all equipped with multi-modal sensors including LiDAR sensors and multi-view cameras. The whole dataset contains 33K LiDAR frames and 171K camera data with over 1.2M annotated bounding boxes of 10 categories in very challenging urban scenarios. According to the collaboration mode and ego perspective, we derive four types of datasets for Vehicle-Centric, Infrastructure-Centric, Vehicle-to-Vehicle, and Infrastructure-to-Infrastructure cooperative perception. Comprehensive multi-class multi-agent benchmarks of SOTA cooperative perception methods are provided. The V2X-Real dataset and codebase are available at https://mobility-lab.seas.ucla.edu/v2x-real.

Yu Gao, Lixue Gong, Qiushan Guo et al.

We present Seedream 3.0, a high-performance Chinese-English bilingual image generation foundation model. We develop several technical improvements to address existing challenges in Seedream 2.0, including alignment with complicated prompts, fine-grained typography generation, suboptimal visual aesthetics and fidelity, and limited image resolutions. Specifically, the advancements of Seedream 3.0 stem from improvements across the entire pipeline, from data construction to model deployment. At the data stratum, we double the dataset using a defect-aware training paradigm and a dual-axis collaborative data-sampling framework. Furthermore, we adopt several effective techniques such as mixed-resolution training, cross-modality RoPE, representation alignment loss, and resolution-aware timestep sampling in the pre-training phase. During the post-training stage, we utilize diversified aesthetic captions in SFT, and a VLM-based reward model with scaling, thereby achieving outputs that well align with human preferences. Furthermore, Seedream 3.0 pioneers a novel acceleration paradigm. By employing consistent noise expectation and importance-aware timestep sampling, we achieve a 4 to 8 times speedup while maintaining image quality. Seedream 3.0 demonstrates significant improvements over Seedream 2.0: it enhances overall capabilities, in particular for text-rendering in complicated Chinese characters which is important to professional typography generation. In addition, it provides native high-resolution output (up to 2K), allowing it to generate images with high visual quality.

Team Seawead, Ceyuan Yang, Zhijie Lin et al.

This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parameters (7B) called Seaweed-7B trained from scratch using 665,000 H100 GPU hours. Despite being trained with moderate computational resources, Seaweed-7B demonstrates highly competitive performance compared to contemporary video generation models of much larger size. Design choices are especially crucial in a resource-constrained setting. This technical report highlights the key design decisions that enhance the performance of the medium-sized diffusion model. Empirically, we make two observations: (1) Seaweed-7B achieves performance comparable to, or even surpasses, larger models trained on substantially greater GPU resources, and (2) our model, which exhibits strong generalization ability, can be effectively adapted across a wide range of downstream applications either by lightweight fine-tuning or continue training. See the project page at https://seaweed.video/

Shanchuan Lin, Xin Xia, Yuxi Ren et al.

The diffusion models are widely used for image and video generation, but their iterative generation process is slow and expansive. While existing distillation approaches have demonstrated the potential for one-step generation in the image domain, they still suffer from significant quality degradation. In this work, we propose Adversarial Post-Training (APT) against real data following diffusion pre-training for one-step video generation. To improve the training stability and quality, we introduce several improvements to the model architecture and training procedures, along with an approximated R1 regularization objective. Empirically, our experiments show that our adversarial post-trained model, Seaweed-APT, can generate 2-second, 1280x720, 24fps videos in real time using a single forward evaluation step. Additionally, our model is capable of generating 1024px images in a single step, achieving quality comparable to state-of-the-art methods.

Ruiqi Wang, Jiyu Guo, Cuiyun Gao et al.

Recently, large language models (LLMs) have been deployed to tackle various software engineering (SE) tasks like code generation, significantly advancing the automation of SE tasks. However, assessing the quality of these LLM-generated code and text remains challenging. The commonly used Pass@k metric necessitates extensive unit tests and configured environments, demands a high labor cost, and is not suitable for evaluating LLM-generated text. Conventional metrics like BLEU, which measure only lexical rather than semantic similarity, have also come under scrutiny. In response, a new trend has emerged to employ LLMs for automated evaluation, known as LLM-as-a-judge. These LLM-as-a-judge methods are claimed to better mimic human assessment than conventional metrics without relying on high-quality reference answers. Nevertheless, their exact human alignment in SE tasks remains unexplored. In this paper, we empirically explore LLM-as-a-judge methods for evaluating SE tasks, focusing on their alignment with human judgments. We select seven LLM-as-a-judge methods that utilize general-purpose LLMs, alongside two LLMs specifically fine-tuned for evaluation. After generating and manually scoring LLM responses on three recent SE datasets of code translation, code generation, and code summarization, we then prompt these methods to evaluate each response. Finally, we compare the scores generated by these methods with human evaluation. The results indicate that output-based methods reach the highest Pearson correlation of 81.32 and 68.51 with human scores in code translation and generation, achieving near-human evaluation, noticeably outperforming ChrF++, one of the best conventional metrics, at 34.23 and 64.92. Such output-based methods prompt LLMs to output judgments directly, and exhibit more balanced score distributions that resemble human score patterns. Finally, we provide...

Lixue Gong, Xiaoxia Hou, Fanshi Li et al.

Rapid advancement of diffusion models has catalyzed remarkable progress in the field of image generation. However, prevalent models such as Flux, SD3.5 and Midjourney, still grapple with issues like model bias, limited text rendering capabilities, and insufficient understanding of Chinese cultural nuances. To address these limitations, we present Seedream 2.0, a native Chinese-English bilingual image generation foundation model that excels across diverse dimensions, which adeptly manages text prompt in both Chinese and English, supporting bilingual image generation and text rendering. We develop a powerful data system that facilitates knowledge integration, and a caption system that balances the accuracy and richness for image description. Particularly, Seedream is integrated with a self-developed bilingual large language model as a text encoder, allowing it to learn native knowledge directly from massive data. This enable it to generate high-fidelity images with accurate cultural nuances and aesthetic expressions described in either Chinese or English. Beside, Glyph-Aligned ByT5 is applied for flexible character-level text rendering, while a Scaled ROPE generalizes well to untrained resolutions. Multi-phase post-training optimizations, including SFT and RLHF iterations, further improve the overall capability. Through extensive experimentation, we demonstrate that Seedream 2.0 achieves state-of-the-art performance across multiple aspects, including prompt-following, aesthetics, text rendering, and structural correctness. Furthermore, Seedream 2.0 has been optimized through multiple RLHF iterations to closely align its output with human preferences, as revealed by its outstanding ELO score. In addition, it can be readily adapted to an instruction-based image editing model, such as SeedEdit, with strong editing capability that balances instruction-following and image consistency.

Jiaxiang Cheng, Pan Xie, Xin Xia et al.

Recent advancement in text-to-image models (e.g., Stable Diffusion) and corresponding personalized technologies (e.g., DreamBooth and LoRA) enables individuals to generate high-quality and imaginative images. However, they often suffer from limitations when generating images with resolutions outside of their trained domain. To overcome this limitation, we present the Resolution Adapter (ResAdapter), a domain-consistent adapter designed for diffusion models to generate images with unrestricted resolutions and aspect ratios. Unlike other multi-resolution generation methods that process images of static resolution with complex post-process operations, ResAdapter directly generates images with the dynamical resolution. Especially, after learning a deep understanding of pure resolution priors, ResAdapter trained on the general dataset, generates resolution-free images with personalized diffusion models while preserving their original style domain. Comprehensive experiments demonstrate that ResAdapter with only 0.5M can process images with flexible resolutions for arbitrary diffusion models. More extended experiments demonstrate that ResAdapter is compatible with other modules (e.g., ControlNet, IP-Adapter and LCM-LoRA) for image generation across a broad range of resolutions, and can be integrated into other multi-resolution model (e.g., ElasticDiffusion) for efficiently generating higher-resolution images. Project link is https://res-adapter.github.io