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.

Xiaoqing Zhang, Ang Lv, Yuhan Liu, Flood Sung, Wei Liu, Jian Luan, Shuo Shang, Xiuying Chen, Rui Yan. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

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.

In today's digital environment, the rapid propagation of fake news via social networks poses significant social challenges. Most existing detection methods either employ traditional classification models, which suffer from low interpretability and limited generalization capabilities, or craft specific prompts for large language models (LLMs) to produce explanations and results directly, failing to leverage LLMs' reasoning abilities fully. Inspired by the saying that ''truth becomes clearer through debate,'' our study introduces a novel multi-agent system with LLMs named TruEDebate (TED) to enhance the interpretability and effectiveness of fake news detection. TED employs a rigorous debate process inspired by formal debate settings. Central to our approach are two innovative components: the DebateFlow Agents and the InsightFlow Agents. The DebateFlow Agents organize agents into two teams, where one supports and the other challenges the truth of the news. These agents engage in opening statements, cross-examination, rebuttal, and closing statements, simulating a rigorous debate process akin to human discourse analysis, allowing for a thorough evaluation of news content. Concurrently, the InsightFlow Agents consist of two specialized sub-agents: the Synthesis Agent and the Analysis Agent. The Synthesis Agent summarizes the debates and provides an overarching viewpoint, ensuring a coherent and comprehensive evaluation. The Analysis Agent, which includes a role-aware encoder and a debate graph, integrates role embeddings and models the interactions between debate roles and arguments using an attention mechanism, providing the final judgment.Our extensive experiments on two datasets, ARG-EN and ARG-CN, demonstrate that the TED framework surpasses traditional methods across various metrics and, more importantly, enhances interpretable fake news detection by illuminating logical reasoning and structured debate processes leading to accurate conclusions.We release our code to support Information systems that use structured debate within responsible information systems for improved decision-making.

Influencer marketing campaign success heavily depends on identifying key opinion leaders who can effectively leverage their credibility and reach to promote products or services.The selection of influencers is vital for boosting brand visibility, fostering consumer trust, and driving sales.While traditional research often simplifies complex factors like user attitudes, interaction frequency, and advertising content, into simple numerical values.However, this reductionist approach fails to capture the dynamic nature of influencer marketing effectiveness.To bridge this gap, we present SAGraph, a novel comprehensive dataset from Weibo that captures multi-dimensional marketing campaign data across six product domains.The dataset encompasses 345,039 user profiles with their complete interaction histories, including 1.3M comments and 554K reposts across 44K posts, providing unprecedented granularity in influencer marketing dynamics.SAGraph uniquely integrates user profiles, content features, and temporal interaction patterns, enabling in-depth analysis of influencer marketing mechanisms.Experimental results using both traditional baselines and state-of-the-art large language models (LLMs) demonstrate the crucial role of content analysis in predicting advertising effectiveness.Our findings reveal that LLM-based approaches achieve superior performance in understanding and predicting campaign success, opening new avenues for data-driven influencer marketing strategies.We hope that this dataset will inspire further research: https

With the outbreak of COVID-19, it is urgent and necessary to design a system that can access to information from COVID-19 related documents. Current methods fail to do so since the knowledge about COVID-19, an emerging disease, keeps changing and growing. In this study, we design a dynamic document-based question answering system, namely Web Understanding and Learning with AI (WULAI-QA). WULAI-QA employs feature engineering and online learning to adapt to the non-stationary environment and maintains good and steady performance. We evaluate WULAI-QA's performance on a public question answering (https://www.datafountain.cn/competitions/424) and rank first. We demonstrate that WULAI-QA can learn from user feedback and is easy to use. We believe that WULAI-QA will definitely help people understand COVID-19 and play an important role to fight against the pandemic.