Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing methods rely heavily on costly human-annotated training datasets, which limits their generalization and causes them to struggle in out-of-domain (OOD) scenarios, reducing real-world adaptability. To address these challenges, we propose ManipLVM-R1, a novel reinforcement learning framework that replaces traditional supervision with Reinforcement Learning using Verifiable Rewards (RLVR). By directly optimizing for task-aligned outcomes, our method enhances generalization and physical reasoning while removing the dependence on costly annotations. Specifically, we design two rule-based reward functions targeting key robotic manipulation subtasks: an Affordance Perception Reward to enhance localization of interaction regions, and a Trajectory Match Reward to ensure the physical plausibility of action paths. These rewards provide immediate feedback and impose spatial-logical constraints, encouraging the model to go beyond shallow pattern matching and instead learn deeper, more systematic reasoning about physical interactions. Experimental results show that ManipLVM-R1 achieves substantial performance gains across multiple manipulation tasks, using only 50% of the training data while achieving strong generalization to OOD scenarios. We further analyze the benefits of our reward design and its impact on task success and efficiency.

Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Fengxian Ji, Jingpu Yang, Zirui Song, Lang Gao, Junhong Liang, Zhenhao Chen, Jinghui Zhang, Xiuying Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zirui Song, Qian Jiang, Mingxuan Cui, Mingzhe Li, Lang Gao, Zeyu Zhang, Zixiang Xu, Yanbo Wang, Guangxian Ouyang, Zhenhao Chen, Xiuying Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

BACKGROUND: Small nucleolar RNAs (snoRNAs) are increasingly recognized for their involvement in human diseases. Accurate and robust prediction of disease-associated snoRNAs is crucial for accelerating drug discovery and disease treatment. However, the limited availability of biomedical data in this domain poses a significant challenge to the generalization ability of machine learning models. While existing computational methods have made progress, their performance is often constrained by data scarcity. RESULTS: To overcome these limitations, we introduce SPGA, a novel graph representation learning framework designed to enhance snoRNA-disease association prediction. SPGA leverages intrinsic structural features of snoRNAs and diseases to construct interaction-aware graph representations. It then employs residual graph convolutional networks augmented with a hierarchical attention mechanism to learn robust node embeddings for association predictions. Comprehensive experiments demonstrate that SPGA effectively alleviates the data scarcity problem for model generalization and significantly improves state-of-the-art methods in terms of prediction accuracy, achieving an AUC of 0.9812 and an AUPR of 0.9749 under five-fold cross-validation setting. Case studies further validate its efficacy in identifying novel snoRNA-disease associations. CONCLUSIONS: Our study provides a potent computational tool for prioritizing candidate disease-related snoRNAs, thereby facilitating the discovery of potential diagnostic biomarkers and therapeutic targets.

Pedestrian detection in intelligent transportation systems has made significant progress but faces two critical challenges: (1) insufficient fusion of complementary information between visible and infrared spectra, particularly in complex scenarios, and (2) sensitivity to illumination changes, such as low-light or overexposed conditions, leading to degraded performance. To address these issues, we propose PedDet, an adaptive spectral optimization complementarity framework which specifically enhanced and optimized for multispectral pedestrian detection. PedDet introduces the Multi-scale Spectral Feature Perception Module (MSFPM) to adaptively fuse visible and infrared features, enhancing robustness and flexibility in feature extraction. Additionally, the Illumination Robustness Feature Decoupling Module (IRFDM) improves detection stability under varying lighting by decoupling pedestrian and background features. We further design a contrastive alignment to enhance intermodal feature discrimination. Experiments on LLVIP and MSDS datasets demonstrate that PedDet achieves state-of-the-art performance, improving the mAP by 6.6 % with superior detection accuracy even in low-light conditions, marking a significant step forward for road safety.

With the growing spread of misinformation online, understanding how true news evolves into fake news has become crucial for early detection and prevention.However, previous research has often assumed fake news inherently exists rather than exploring its gradual formation.To address this gap, we propose FUSE (Fake news evolUtion Simulation framEwork), a novel Large Language Model (LLM)-based simulation approach explicitly focusing on fake news evolution from real news.Our framework model a social network with four distinct types of LLM agents commonly observed in daily interactions: spreaders who propagate information, commentators who provide interpretations, verifiers who fact-check, and bystanders who observe passively to simulate realistic daily interactions that progressively distort true news.To quantify these gradual distortions, we develop FUSE-EVAL, a comprehensive evaluation framework measuring truth deviation along multiple linguistic and semantic dimensions.Results show that FUSE effectively captures fake news evolution patterns and accurately reproduces known fake news, aligning closely with human evaluations.Experiments demonstrate that FUSE accurately reproduces known fake news evolution scenarios, aligns closely with human judgment, and highlights the importance of timely intervention at early stages.Our framework is extensible, enabling future research on broader scenarios of fake news: FUSE.

Zirui Song, Guangxian Ouyang, Meng Fang, Hongbin Na, Zijing Shi, Zhenhao Chen, Fu Yujie, Zeyu Zhang, Shiyu Jiang, Miao Fang, Ling Chen, Xiuying Chen. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Agent systems based on large language models (LLMs) have shown great potential in complex reasoning tasks, but building efficient and generalizable workflows remains a major challenge. Most existing approaches rely on manually designed processes, which limits their adaptability across different tasks. While a few methods attempt automated workflow generation, they are often tied to specific datasets or query types and make limited use of intermediate feedback, reducing system robustness and reasoning depth. Moreover, their operations are typically predefined and inflexible. To address these limitations, we propose **DyFlow**, a dynamic workflow generation framework that adaptively constructs and adjusts reasoning procedures based on task requirements and real-time intermediate feedback, thereby enhancing cross-task generalization. DyFlow consists of two core components: a designer and an executor. The designer decomposes complex problems into a sequence of sub-goals defined by high-level objectives and dynamically plans the next steps based on intermediate outputs and feedback. These plans are then carried out by the executor, which executes each operation using dynamic operators with context-aware parameterization, enabling flexible and semantically grounded reasoning. We systematically evaluate DyFlow across diverse domains, including social reasoning, biomedical tasks, mathematical problem solving, and code generation. Results demonstrate that DyFlow significantly outperforms existing baselines, achieving substantial Pass@k improvements and exhibiting robust generalization across diverse domains.

Analyzing binary code is vital for software engineering and security research, particularly when the source code is unavailable. However, understanding, modifying, and retargeting binary code can be complex tasks. To counter these difficulties, binary lifters have been introduced. These tools translate binary code into Intermediate Representations (IRs), providing several advantages, such as enabling modifications to executables without source code and facilitating code retargetability. So far, accurately developing binary lifters for modern ISAs is universally acknowledged as challenging and error-prone. Existing validation methods mainly concentrate on isolated instructions, overlooking interactions among instructions. In this paper, we introduce LiftFuzz, a novel framework that leverages instruction context-aware fuzzing to validate binary lifters. LiftFuzz harnesses an assembly language model to learn interactions among instructions and generates test cases with the knowledge. LiftFuzz greatly outperforms the baseline, requiring only 1/1000 of the test cases used by the baseline to identify 26 inconsistencies, including a previously uncovered category. LiftFuzz significantly contributes to enhancing the performance of binary lifters, which are frequently employed in binary security applications.

Type recovery in stripped binaries is a critical and challenging task in reverse engineering, as it is the basis for many security applications (e.g., vulnerability detection). Traditional analysis methods are limited by software complexity and emerging types in real-world projects. To address these limitations, machine learning methods have been explored. However, the existing supervised learning approaches struggle with analyzing complicated and uncommon types due to the limited availability of samples. Additionally, none of the existing works can capture fine-grained and inter-procedural features in the binaries. In this paper, we present TypeFSL, a framework that addresses the challenge of imbalanced type distributions by incorporating few-shot learning and captures inter-procedural semantics through program slicing. Moreover, based on a dataset with 3,003,117 functions, TypeFSL achieves an average of 77.9% and 84.6% accuracy across all architecture and optimizations in 20-way 5-shot and 10-shot classification tasks. Our prototype outperforms existing techniques in prediction accuracy and obfuscation resistance. Finally, the case studies demonstrate how TypeFSL predicts uncommon and complicated types in practical analysis.

The capability mechanism in Linux-based systems is designed for dispersing the root privileges into a set of more refined capabilities, making programs gain no-more-necessary privileges. However, it is challenging to check the necessity and sufficiency of capabilities assigned to programs due to the highly complicated call chains invoked in practice. Inappropriate capability assignment brings threats to the systems. For example, over-privileged programs could allow an attacker to misuse root privileges, while under-privileged programs may incur runtime errors.