With the rapidly increasing application of large language models (LLMs), their abuse has caused many undesirable societal problems such as fake news, academic dishonesty, and information pollution. This makes AI-generated text (AIGT) detection of great importance. Among existing methods, white-box methods are generally superior to black-box methods in terms of performance and generalizability, but they require access to LLMs' internal states and are not applicable to black-box settings. In this paper, we propose to estimate word generation probabilities as pseudo white-box features via multiple re-sampling to help improve AIGT detection under the black-box setting. Specifically, we design POGER, a proxy-guided efficient re-sampling method, which selects a small subset of representative words (e.g., 10 words) for performing multiple re-sampling in black-box AIGT detection. Experiments on datasets containing texts from humans and seven LLMs show that POGER outperforms all baselines in macro F1 under black-box, partial white-box, and out-of-distribution settings and maintains lower re-sampling costs than its existing counterparts.
The competition focuses on Multiparty Multiobjective Optimization Problems (MPMOPs), where multiple decision makers have conflicting objectives, as seen in applications like UAV path planning. Despite their importance, MPMOPs remain understudied in comparison to conventional multiobjective optimization. The competition aims to address this gap by encouraging researchers to explore tailored modeling approaches. The test suite comprises two parts: problems with common Pareto optimal solutions and Biparty Multiobjective UAV Path Planning (BPMO-UAVPP) problems with unknown solutions. Optimization algorithms for the first part are evaluated using Multiparty Inverted Generational Distance (MPIGD), and the second part is evaluated using Multiparty Hypervolume (MPHV) metrics. The average algorithm ranking across all problems serves as a performance benchmark.
Federated recommender systems (FedRecs) have gained significant attention for their potential to protect user's privacy by keeping user privacy data locally and only communicating model parameters/gradients to the server. Nevertheless, the currently existing architecture of FedRecs assumes that all users have the same 0-privacy budget, i.e., they do not upload any data to the server, thus overlooking those users who are less concerned about privacy and are willing to upload data to get a better recommendation service. To bridge this gap, this paper explores a user-governed data contribution federated recommendation architecture where users are free to take control of whether they share data and the proportion of data they share to the server. To this end, this paper presents a cloud-device collaborative graph neural network federated recommendation model, named CDCGNNFed. It trains user-centric ego graphs locally, and high-order graphs based on user-shared data in the server in a collaborative manner via contrastive learning. Furthermore, a graph mending strategy is utilized to predict missing links in the graph on the server, thus leveraging the capabilities of graph neural networks over high-order graphs. Extensive experiments were conducted on two public datasets, and the results demonstrate the effectiveness of the proposed method.
In Location-based Social Networks, Point-of-Interest (POI) recommendation helps users discover interesting places. There is a trend to move from the cloud-based model to on-device recommendations for privacy protection and reduced server reliance. Due to the scarcity of local user-item interactions on individual devices, solely relying on local instances is not adequate. Collaborative Learning (CL) emerges to promote model sharing among users, where reference data is an intermediary that allows users to exchange their soft decisions without directly sharing their private data or parameters, ensuring privacy and benefiting from collaboration. However, existing CL-based recommendations typically use a single reference for all users. Reference data valuable for one user might be harmful to another, given diverse user preferences. Users may not offer meaningful soft decisions on items outside their interest scope. Consequently, using the same reference data for all collaborations can impede knowledge exchange and lead to sub-optimal performance. To address this gap, we introduce the Decentralized Collaborative Learning with Adaptive Reference Data (DARD) framework, which crafts adaptive reference data for effective user collaboration. It first generates a desensitized public reference data pool with transformation and probability data generation methods. For each user, the selection of adaptive reference data is executed in parallel by training loss tracking and influence function. Local models are trained with individual private data and collaboratively with the geographical and semantic neighbors. During the collaboration between two users, they exchange soft decisions based on a combined set of their adaptive reference data. Our evaluations across two real-world datasets highlight DARD's superiority in recommendation performance and addressing the scarcity of available reference data.
Recommender systems have been widely deployed in various real-world applications to help users identify content of interest from massive amounts of information. Traditional recommender systems work by collecting user-item interaction data in a cloud-based data center and training a centralized model to perform the recommendation service. However, such cloud-based recommender systems (CloudRSs) inevitably suffer from excessive resource consumption, response latency, as well as privacy and security risks concerning both data and models. Recently, driven by the advances in storage, communication, and computation capabilities of edge devices, there has been a shift of focus from CloudRSs to on-device recommender systems (DeviceRSs), which leverage the capabilities of edge devices to minimize centralized data storage requirements, reduce the response latency caused by communication overheads, and enhance user privacy and security by localizing data processing and model training. Despite the rapid rise of DeviceRSs, there is a clear absence of timely literature reviews that systematically introduce, categorize and contrast these methods. To bridge this gap, we aim to provide a comprehensive survey of DeviceRSs, covering three main aspects: (1) the deployment and inference of DeviceRSs (2) the training and update of DeviceRSs (3) the security and privacy of DeviceRSs. Furthermore, we provide a fine-grained and systematic taxonomy of the methods involved in each aspect, followed by a discussion regarding challenges and future research directions. This is the first comprehensive survey on DeviceRSs that covers a spectrum of tasks to fit various needs. We believe this survey will help readers effectively grasp the current research status in this field, equip them with relevant technical foundations, and stimulate new research ideas for developing DeviceRSs.
While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals. Although vision-language models (VLMs) integrate LLM modules (1) aligned with static image features, and (2) may possess prior knowledge of world dynamics (as demonstrated in the text world), they have not been trained in an embodied visual world and thus cannot align with its dynamics. On the other hand, training an embodied agent in a noisy visual world without expert guidance is often challenging and inefficient. In this paper, we train a VLM agent living in a visual world using an LLM agent excelling in a parallel text world (but inapplicable to the visual world). Specifically, we distill LLM's reflection outcomes (improved actions by analyzing mistakes) in a text world's tasks to finetune the VLM on the same tasks of the visual world, resulting in an Embodied Multi-Modal Agent (EMMA) quickly adapting to the visual world dynamics. Such cross-modality imitation learning between the two parallel worlds enables EMMA to generalize to a broad scope of new tasks without any further guidance from the LLM expert. Extensive evaluations on the ALFWorld benchmark highlight EMMA's superior performance to SOTA VLM-based agents across diverse tasks, e.g., 20%-70% improvement in the success rate.
In the post-Moore era, the main performance gains of black-box optimizers are increasingly depending upon parallelism, especially for large-scale optimization (LSO). In this paper, we propose to parallelize the well-established covariance matrix adaptation evolution strategy (CMA-ES) and in particular its one latest variant called limited-memory CMA (LM-CMA) for LSO. To achieve scalability while maintaining the invariance property as much as possible, we present a multilevel learning-based meta-framework. Owing to its hierarchically organized structure, Meta-ES is well-suited to implement our distributed meta-framework, wherein the outer-ES controls strategy parameters while all parallel inner-ESs run the serial LM-CMA with different settings. For the distribution mean update of the outer-ES, both the elitist and multi-recombination strategy are used in parallel to avoid stagnation and regression, respectively. To exploit spatiotemporal information, the global step-size adaptation combines Meta-ES with the parallel cumulative step-size adaptation. After each isolation time, our meta-framework employs both the structure and parameter learning strategy to combine aligned evolution paths for CMA reconstruction. Experiments on a set of large-scale benchmarking functions with memory-intensive evaluations, arguably reflecting many data-driven optimization problems, validate the benefits (e.g., scalability w.r.t. CPU cores, effectiveness w.r.t. solution quality, and adaptability w.r.t. second-order learning) and costs of our meta-framework.
Target-oriented grasping in unstructured scenes with language control is essential for intelligent robot arm grasping. The ability for the robot arm to understand the human language and execute corresponding grasping actions is a pivotal challenge. In this paper, we propose a combination model called QwenGrasp which combines a large vision-language model with a 6-DoF grasp neural network. QwenGrasp is able to conduct a 6-DoF grasping task on the target object with textual language instruction. We design a complete experiment with six-dimension instructions to test the QwenGrasp when facing with different cases. The results show that QwenGrasp has a superior ability to comprehend the human intention. Even in the face of vague instructions with descriptive words or instructions with direction information, the target object can be grasped accurately. When QwenGrasp accepts the instruction which is not feasible or not relevant to the grasping task, our approach has the ability to suspend the task execution and provide a proper feedback to humans, improving the safety. In conclusion, with the great power of large vision-language model, QwenGrasp can be applied in the open language environment to conduct the target-oriented grasping task with freely input instructions.
The ability for robotic systems to understand human language and execute grasping actions is a pivotal challenge in the field of robotics. In target-oriented grasping, prior researches achieve matching human textual commands with images of target objects. However, these works are hard to understand complex or flexible instructions. Moreover, these works lack the capability to autonomously assess the feasibility of instructions, leading to blindly execute grasping tasks even there is no target object. In this paper, we introduce a combination model called QwenGrasp, which combines a large vision language model with a 6-DoF grasp network. By leveraging a pre-trained large vision language model, our approach is capable of working in open-world with natural human language environments, accepting complex and flexible instructions. Furthermore, the specialized grasp network ensures the effectiveness of the generated grasp pose. A series of experiments conducted in real world environment show that our method exhibits a superior ability to comprehend human intent. Additionally, when accepting erroneous instructions, our approach has the capability to suspend task execution and provide feedback to humans, improving safety.
Detecting fake news requires both a delicate sense of diverse clues and a profound understanding of the real-world background, which remains challenging for detectors based on small language models (SLMs) due to their knowledge and capability limitations. Recent advances in large language models (LLMs) have shown remarkable performance in various tasks, but whether and how LLMs could help with fake news detection remains underexplored. In this paper, we investigate the potential of LLMs in fake news detection. First, we conduct an empirical study and find that a sophisticated LLM such as GPT 3.5 could generally expose fake news and provide desirable multi-perspective rationales but still underperforms the basic SLM, fine-tuned BERT. Our subsequent analysis attributes such a gap to the LLM's inability to select and integrate rationales properly to conclude. Based on these findings, we propose that current LLMs may not substitute fine-tuned SLMs in fake news detection but can be a good advisor for SLMs by providing multi-perspective instructive rationales. To instantiate this proposal, we design an adaptive rationale guidance network for fake news detection (ARG), in which SLMs selectively acquire insights on news analysis from the LLMs' rationales. We further derive a rationale-free version of ARG by distillation, namely ARG-D, which services cost-sensitive scenarios without inquiring LLMs. Experiments on two real-world datasets demonstrate that ARG and ARG-D outperform three types of baseline methods, including SLM-based, LLM-based, and combinations of small and large language models.