Tian Wang

Lei Huang, Yi Zhou, Tian Wang et al.

Batch normalization (BN) is a milestone technique in deep learning. It normalizes the activation using mini-batch statistics during training but the estimated population statistics during inference. This paper focuses on investigating the estimation of population statistics. We define the estimation shift magnitude of BN to quantitatively measure the difference between its estimated population statistics and expected ones. Our primary observation is that the estimation shift can be accumulated due to the stack of BN in a network, which has detriment effects for the test performance. We further find a batch-free normalization (BFN) can block such an accumulation of estimation shift. These observations motivate our design of XBNBlock that replace one BN with BFN in the bottleneck block of residual-style networks. Experiments on the ImageNet and COCO benchmarks show that XBNBlock consistently improves the performance of different architectures, including ResNet and ResNeXt, by a significant margin and seems to be more robust to distribution shift.

Jianheng Tang, Kejia Fan, Wenxuan Xie et al.

The recruitment of trustworthy and high-quality workers is an important research issue for MCS. Previous studies either assume that the qualities of workers are known in advance, or assume that the platform knows the qualities of workers once it receives their collected data. In reality, to reduce costs and thus maximize revenue, many strategic workers do not perform their sensing tasks honestly and report fake data to the platform, which is called False data attacks. And it is very hard for the platform to evaluate the authenticity of the received data. In this paper, an incentive mechanism named Semi-supervision based Combinatorial Multi-Armed Bandit reverse Auction (SCMABA) is proposed to solve the recruitment problem of multiple unknown and strategic workers in MCS. First, we model the worker recruitment as a multi-armed bandit reverse auction problem and design an UCB-based algorithm to separate the exploration and exploitation, regarding the Sensing Rates (SRs) of recruited workers as the gain of the bandit. Next, a Semi-supervised Sensing Rate Learning (SSRL) approach is proposed to quickly and accurately obtain the workers' SRs, which consists of two phases, supervision and self-supervision. Last, SCMABA is designed organically combining the SRs acquisition mechanism with multi-armed bandit reverse auction, where supervised SR learning is used in the exploration, and the self-supervised one is used in the exploitation. We theoretically prove that our SCMABA achieves truthfulness and individual rationality and exhibits outstanding performances of the SCMABA mechanism through in-depth simulations of real-world data traces.

Jianqiu Wu, Zhongyi Yu, Jianxiong Guo et al.

Terahertz communication networks and intelligent reflecting surfaces exhibit significant potential in advancing wireless networks, particularly within the domain of aerial-based multi-access edge computing systems. These technologies enable efficient offloading of computational tasks from user electronic devices to Unmanned Aerial Vehicles or local execution. For the generation of high-quality task-offloading allocations, conventional numerical optimization methods often struggle to solve challenging combinatorial optimization problems within the limited channel coherence time, thereby failing to respond quickly to dynamic changes in system conditions. To address this challenge, we propose a deep learning-based optimization framework called Iterative Order-Preserving policy Optimization (IOPO), which enables the generation of energy-efficient task-offloading decisions within milliseconds. Unlike exhaustive search methods, IOPO provides continuous updates to the offloading decisions without resorting to exhaustive search, resulting in accelerated convergence and reduced computational complexity, particularly when dealing with complex problems characterized by extensive solution spaces. Experimental results demonstrate that the proposed framework can generate energy-efficient task-offloading decisions within a very short time period, outperforming other benchmark methods.

Changfu Xu, Jianxiong Guo, Wanyu Lin et al.

Artificial Intelligence Generated Content (AIGC) has gained significant popularity for creating diverse content. Current AIGC models primarily focus on content quality within a centralized framework, resulting in a high service delay and negative user experiences. However, not only does the workload of an AIGC task depend on the AIGC model's complexity rather than the amount of data, but the large model and its multi-layer encoder structure also result in a huge demand for computational and memory resources. These unique characteristics pose new challenges in its modeling, deployment, and scheduling at edge networks. Thus, we model an offloading problem among edges for providing real AIGC services and propose LAD-TS, a novel Latent Action Diffusion-based Task Scheduling method that orchestrates multiple edge servers for expedited AIGC services. The LAD-TS generates a near-optimal offloading decision by leveraging the diffusion model's conditional generation capability and the reinforcement learning's environment interaction ability, thereby minimizing the service delays under multiple resource constraints. Meanwhile, a latent action diffusion strategy is designed to guide decision generation by utilizing historical action probability, enabling rapid achievement of near-optimal decisions. Furthermore, we develop DEdgeAI, a prototype edge system with a refined AIGC model deployment to implement and evaluate our LAD-TS method. DEdgeAI provides a real AIGC service for users, demonstrating up to 29.18% shorter service delays than the current five representative AIGC platforms. We release our open-source code at https://github.com/ChangfuXu/DEdgeAI/.

Changfu Xu, Jianxiong Guo, Yuzhu Liang et al.

Diffusion Models (DMs), as a leading class of generative models, offer key advantages for reinforcement learning (RL), including multi-modal expressiveness, stable training, and trajectory-level planning. This survey delivers a comprehensive and up-to-date synthesis of diffusion-based RL. We first provide an overview of RL, highlighting its challenges, and then introduce the fundamental concepts of DMs, investigating how they are integrated into RL frameworks to address key challenges in this research field. We establish a dual-axis taxonomy that organizes the field along two orthogonal dimensions: a function-oriented taxonomy that clarifies the roles DMs play within the RL pipeline, and a technique-oriented taxonomy that situates implementations across online versus offline learning regimes. We also provide a comprehensive examination of this progression from single-agent to multi-agent domains, thereby forming several frameworks for DM-RL integration and highlighting their practical utility. Furthermore, we outline several categories of successful applications of diffusion-based RL across diverse domains, discuss open research issues of current methodologies, and highlight key directions for future research to advance the field. Finally, we summarize the survey to identify promising future development directions. We are actively maintaining a GitHub repository (https://github.com/ChangfuXu/D4RL-FTD) for papers and other related resources to apply DMs for RL.

Xubin Wang, Zhiqing Tang, Jianxiong Guo et al.

The rapid advancement of artificial intelligence (AI) technologies has led to an increasing deployment of AI models on edge and terminal devices, driven by the proliferation of the Internet of Things (IoT) and the need for real-time data processing. This survey comprehensively explores the current state, technical challenges, and future trends of on-device AI models. We define on-device AI models as those designed to perform local data processing and inference, emphasizing their characteristics such as real-time performance, resource constraints, and enhanced data privacy. The survey is structured around key themes, including the fundamental concepts of AI models, application scenarios across various domains, and the technical challenges faced in edge environments. We also discuss optimization and implementation strategies, such as data preprocessing, model compression, and hardware acceleration, which are essential for effective deployment. Furthermore, we examine the impact of emerging technologies, including edge computing and foundation models, on the evolution of on-device AI models. By providing a structured overview of the challenges, solutions, and future directions, this survey aims to facilitate further research and application of on-device AI, ultimately contributing to the advancement of intelligent systems in everyday life.

Yongding Tao, Tian Wang, Yihong Dong et al. · pku

Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance. While detection methods have been developed for the pre-training and Supervised Fine-Tuning stages, a critical research gap exists for the increasingly significant phase of Reinforcement Learning (RL) post-training. As RL post-training becomes pivotal for advancing LLM reasoning, the absence of specialized contamination detection methods in this paradigm presents a critical vulnerability. To address this, we conduct the first systematic study of data detection within RL post-training scenario and propose Self-Critique. Our method is motivated by a key observation: after RL phase, the output entropy distribution of LLMs tends to collapse into highly specific and sparse modes. Self-Critique probes for the underlying policy collapse, i.e., the model's convergence to a narrow reasoning path, which causes this entropy reduction. To facilitate this research, we also introduce RL-MIA, a benchmark constructed to simulate this specific contamination scenario. Extensive experiments show that Self-Critique significantly outperforms baseline methods across multiple models and contamination tasks, achieving an AUC improvement of up to 30%. Whereas existing methods are close to a random guess for RL-phase contamination, our method makes detection possible.

Jiacheng Lin, Zhongruo Wang, Kun Qian et al.

Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their general capabilities. In this work, we revisit this trade-off and present both empirical and theoretical insights. First, we show that SFT does not always hurt: using a smaller learning rate can substantially mitigate general performance degradation while preserving comparable target-domain performance. We then provide a theoretical analysis that explains these phenomena and further motivates a new method, Token-Adaptive Loss Reweighting (TALR). Building on this, and recognizing that smaller learning rates alone do not fully eliminate general-performance degradation in all cases, we evaluate a range of strategies for reducing general capability loss, including L2 regularization, LoRA, model averaging, FLOW, and our proposed TALR. Experimental results demonstrate that while no method completely eliminates the trade-off, TALR consistently outperforms these baselines in balancing domain-specific gains and general capabilities. Finally, we distill our findings into practical guidelines for adapting LLMs to new domains: (i) using a small learning rate to achieve a favorable trade-off, and (ii) when a stronger balance is further desired, adopt TALR as an effective strategy.

Xingdan Wang, Jiayi He, Zhiqing Tang et al.

The rise of LLMs such as ChatGPT and Claude fuels the need for AI agents capable of real-time task handling. However, migrating data-intensive, multi-modal edge workloads to cloud data centers, traditionally used for agent deployment, introduces significant latency. Deploying AI agents at the edge improves efficiency and reduces latency. However, edge environments present challenges due to limited and heterogeneous resources. Maintaining QoS for mobile users necessitates agent migration, which is complicated by the complexity of AI agents coordinating LLMs, task planning, memory, and external tools. This paper presents the first systematic deployment and management solution for LLM-based AI agents in dynamic edge environments. We propose a novel adaptive framework for AI agent placement and migration in edge intelligence systems. Our approach models resource constraints and latency/cost, leveraging ant colony algorithms and LLM-based optimization for efficient decision-making. It autonomously places agents to optimize resource utilization and QoS and enables lightweight agent migration by transferring only essential state. Implemented on a distributed system using AgentScope and validated across globally distributed edge servers, our solution significantly reduces deployment latency and migration costs.

Jianheng Tang, Huiping Zhuang, Jingyu He et al.

Federated Continual Learning (FCL) enables distributed clients to collaboratively train a global model from online task streams in dynamic real-world scenarios. However, existing FCL methods face challenges of both spatial data heterogeneity among distributed clients and temporal data heterogeneity across online tasks. Such data heterogeneity significantly degrades the model performance with severe spatial-temporal catastrophic forgetting of local and past knowledge. In this paper, we identify that the root cause of this issue lies in the inherent vulnerability and sensitivity of gradients to non-IID data. To fundamentally address this issue, we propose a gradient-free method, named Analytic Federated Continual Learning (AFCL), by deriving analytical (i.e., closed-form) solutions from frozen extracted features. In local training, our AFCL enables single-epoch learning with only a lightweight forward-propagation process for each client. In global aggregation, the server can recursively and efficiently update the global model with single-round aggregation. Theoretical analyses validate that our AFCL achieves spatio-temporal invariance of non-IID data. This ideal property implies that, regardless of how heterogeneous the data are distributed across local clients and online tasks, the aggregated model of our AFCL remains invariant and identical to that of centralized joint learning. Extensive experiments show the consistent superiority of our AFCL over state-of-the-art baselines across various benchmark datasets and settings.

Yimeng Zhang, Jiri Gesi, Ran Xue et al.

LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generated rationales, and by leveraging RL to further enhance reasoning capabilities. Despite these advances, current approaches rely on text-based inputs and overlook the essential role of visual perception in shaping human decision-making during web GUI interactions. In this paper, we investigate the integration of visual information, specifically webpage screenshots, into behavior simulation via VLMs, leveraging OPeRA dataset. By grounding agent decision-making in both textual and visual modalities, we aim to narrow the gap between synthetic agents and real-world users, thereby enabling more cognitively aligned simulations of online shopping behavior. Specifically, we employ SFT for joint action prediction and rationale generation, conditioning on the full interaction context, which comprises action history, past HTML observations, and the current webpage screenshot. To further enhance reasoning capabilities, we integrate RL with a hierarchical reward structure, scaled by a difficulty-aware factor that prioritizes challenging decision points. Empirically, our studies show that incorporating visual grounding yields substantial gains: the combination of text and image inputs improves exact match accuracy by more than 6% over text-only inputs. These results indicate that multi-modal grounding not only boosts predictive accuracy but also enhances simulation fidelity in visually complex environments, which captures nuances of human attention and decision-making that text-only agents often miss. Finally, we revisit the design space of behavior simulation frameworks, identify key methodological limitations, and propose future research directions toward building efficient and effective human behavior simulators.

Tian Wang, Yuri M. Brovman, Sriganesh Madhvanath

Recommender systems are an essential component of e-commerce marketplaces, helping consumers navigate massive amounts of inventory and find what they need or love. In this paper, we present an approach for generating personalized item recommendations in an e-commerce marketplace by learning to embed items and users in the same vector space. In order to alleviate the considerable cold-start problem present in large marketplaces, item and user embeddings are computed using content features and multi-modal onsite user activity respectively. Data ablation is incorporated into the offline model training process to improve the robustness of the production system. In offline evaluation using a dataset collected from eBay traffic, our approach was able to improve the Recall@k metric over the Recently-Viewed-Item (RVI) method. This approach to generating personalized recommendations has been launched to serve production traffic, and the corresponding scalable engineering architecture is also presented. Initial A/B test results show that compared to the current personalized recommendation module in production, the proposed method increases the surface rate by $\sim$6\% to generate recommendations for 90\% of listing page impressions.

Tian Wang, Anastasios Bezerianos, Andrzej Cichocki et al.

Objective: Schizophrenia seriously affects the quality of life. To date, both simple (linear discriminant analysis) and complex (deep neural network) machine learning methods have been utilized to identify schizophrenia based on functional connectivity features. The existing simple methods need two separate steps (i.e., feature extraction and classification) to achieve the identification, which disables simultaneous tuning for the best feature extraction and classifier training. The complex methods integrate two steps and can be simultaneously tuned to achieve optimal performance, but these methods require a much larger amount of data for model training. Methods: To overcome the aforementioned drawbacks, we proposed a multi-kernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure. Kernels were set to match with partition sizes of brain anatomical structure in order to capture interregional connectivities at the varying scales. With the inspiration of widely-used dropout strategy in deep learning, we developed vector dropout in the capsule layer to prevent overfitting of the model. Results: The comparison results showed that the proposed method outperformed the state-of-the-art methods. Besides, we compared performances using different parameters and illustrated the routing process to reveal characteristics of the proposed method. Conclusion: MKCapsnet is promising for schizophrenia identification. Significance: Our study not only proposed a multi-kernel capsule network but also provided useful information in the parameter setting, which is informative for further studies using a capsule network for neurophysiological signal classification.

Tian Wang, Kyunghyun Cho

The goal of personalized history-based recommendation is to automatically output a distribution over all the items given a sequence of previous purchases of a user. In this work, we present a novel approach that uses a recurrent network for summarizing the history of purchases, continuous vectors representing items for scalability, and a novel attention-based recurrent mixture density network, which outputs each component in a mixture sequentially, for modelling a multi-modal conditional distribution. We evaluate the proposed approach on two publicly available datasets, MovieLens-20M and RecSys15. The experiments show that the proposed approach, which explicitly models the multi-modal nature of the predictive distribution, is able to improve the performance over various baselines in terms of precision, recall and nDCG.

Tian Wang, Kyunghyun Cho

In this work, we propose a novel method to incorporate corpus-level discourse information into language modelling. We call this larger-context language model. We introduce a late fusion approach to a recurrent language model based on long short-term memory units (LSTM), which helps the LSTM unit keep intra-sentence dependencies and inter-sentence dependencies separate from each other. Through the evaluation on three corpora (IMDB, BBC, and PennTree Bank), we demon- strate that the proposed model improves perplexity significantly. In the experi- ments, we evaluate the proposed approach while varying the number of context sentences and observe that the proposed late fusion is superior to the usual way of incorporating additional inputs to the LSTM. By analyzing the trained larger- context language model, we discover that content words, including nouns, adjec- tives and verbs, benefit most from an increasing number of context sentences. This analysis suggests that larger-context language model improves the unconditional language model by capturing the theme of a document better and more easily.