Author name cluster

Zhenghua Xu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

1 author row

AAAI Conference 2026 Conference Paper

Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation

Bo Li
Zhenghua Xu
Rui Xie

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved evidence differs in language from the user query and in-context exemplars, the model often exhibits language drift by generating responses in an unintended language. This phenomenon is especially pronounced during reasoning-intensive decoding, such as Chain-of-Thought (CoT) generation, where intermediate steps introduce further language instability. In this paper, we systematically study output language drift in multilingual RAG across multiple datasets, languages, and LLM backbones. Our controlled experiments reveal that the drift results not from comprehension failure but from decoder-level collapse, where dominant token distributions and high-frequency English patterns dominate the intended generation language. We further observe that English serves as a semantic attractor under cross-lingual conditions, emerging as both the strongest interference source and the most frequent fallback language. To mitigate this, we propose Soft Constrained Decoding (SCD), a lightweight, training-free decoding strategy that gently steers generation toward the target language by penalizing non-target-language tokens. SCD is model-agnostic and can be applied to any generation algorithm without modifying the architecture or requiring additional data. Experiments across three multilingual datasets and multiple typologically diverse languages show that SCD consistently improves language alignment and task performance, providing an effective and generalizable solution in multilingual RAG.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG

Bo Li
Tian Tian
Zhenghua Xu
Hao Cheng
Shikun Zhang
Wei Ye

Dynamic retrieval-augmented generation (RAG) allows large language models (LLMs) to fetch external knowledge on demand, offering greater adaptability than static RAG. A central challenge in this setting lies in determining the optimal timing for retrieval. Existing methods often trigger retrieval based on low token-level confidence, which may lead to delayed intervention after errors have already propagated. We introduce Entropy-Trend Constraint (ETC), a training-free method that determines optimal retrieval timing by modeling the dynamics of token-level uncertainty. Specifically, ETC utilizes first- and second-order differences of the entropy sequence to detect emerging uncertainty trends, enabling earlier and more precise retrieval. Experiments on six QA benchmarks with three LLM backbones demonstrate that ETC consistently outperforms strong baselines while reducing retrieval frequency. ETC is particularly effective in domain-specific scenarios, exhibiting robust generalization capabilities. Ablation studies and qualitative analyses further confirm that trend-aware uncertainty modeling yields more effective retrieval timing. The method is plug-and-play, model-agnostic, and readily integrable into existing decoding pipelines. Implementation code is included in the supplementary materials.

PDF Details DOI

JBHI Journal 2026 Journal Article

You Need Glimpse Before Segmentation: Stochastic Detector-Actor-Critic for Medical Image Segmentation

Zhenghua Xu
Yunxin Liu
Di Yuan
Bo Li
Weipeng Liu
Thomas Lukasiewicz

Medical images often contain more redundant background areas than natural images, potentially introducing noise and degrading image segmentation performance. Inspired by doctors' diagnostic processes, where they identify the lesion area before conducting a detailed analysis, we introduce a novel S tochastic D etector- A ctor- C ritic (SDAC) framework to tackle this challenge. SDAC initially glimpses the entire image using a detector network and policy gradient algorithms to filter out irrelevant background regions and focus on crucial, smaller areas for segmentation. The Actor-Critic algorithm then dynamically creates segmentation masks pixel by pixel without user intervention or coarse masks, forming a robust segmentation module. Both processes are trained jointly to reduce error propagation and ensure stability and ease of implementation. Our experiments on two commonly used medical image segmentation datasets demonstrate that SDAC achieves competitive results comparable to state-of-the-art methods while using 10x fewer parameters than the best-performing baseline in terms of DICE and IoU metrics. We also conduct detailed ablation studies to enhance understanding and facilitate practical use. Furthermore, SDAC performs well in low-resource settings (i. e. , 50-shot or 100-shot), making it ideal for real-world scenarios. Its lightweight design make SDAC an excellent baseline for medical image segmentation tasks.

Details DOI

AAAI Conference 2022 Conference Paper

Reverse Differentiation via Predictive Coding

Tommaso Salvatori
Yuhang Song
Zhenghua Xu
Thomas Lukasiewicz
Rafal Bogacz

Deep learning has redefined AI thanks to the rise of artificial neural networks, which are inspired by neuronal networks in the brain. Through the years, these interactions between AI and neuroscience have brought immense benefits to both fields, allowing neural networks to be used in a plethora of applications. Neural networks use an efficient implementation of reverse differentiation, called backpropagation (BP). This algorithm, however, is often criticized for its biological implausibility (e. g. , lack of local update rules for the parameters). Therefore, biologically plausible learning methods that rely on predictive coding (PC), a framework for describing information processing in the brain, are increasingly studied. Recent works prove that these methods can approximate BP up to a certain margin on multilayer perceptrons (MLPs), and asymptotically on any other complex model, and that zerodivergence inference learning (Z-IL), a variant of PC, is able to exactly implement BP on MLPs. However, the recent literature shows also that there is no biologically plausible method yet that can exactly replicate the weight update of BP on complex models. To fill this gap, in this paper, we generalize (PC and) Z-IL by directly defining it on computational graphs, and show that it can perform exact reverse differentiation. What results is the first PC (and so biologically plausible) algorithm that is equivalent to BP in the way of updating parameters on any neural network, providing a bridge between the interdisciplinary research of neuroscience and deep learning. Furthermore, the above results in particular also immediately provide a novel local and parallel implementation of BP.

PDF Details

NeurIPS Conference 2021 Conference Paper

Associative Memories via Predictive Coding

Tommaso Salvatori
Yuhang Song
Yujian Hong
Lei Sha
Simon Frieder
Zhenghua Xu
Rafal Bogacz
Thomas Lukasiewicz

Associative memories in the brain receive and store patterns of activity registered by the sensory neurons, and are able to retrieve them when necessary. Due to their importance in human intelligence, computational models of associative memories have been developed for several decades now. In this paper, we present a novel neural model for realizing associative memories, which is based on a hierarchical generative network that receives external stimuli via sensory neurons. It is trained using predictive coding, an error-based learning algorithm inspired by information processing in the cortex. To test the model's capabilities, we perform multiple retrieval experiments from both corrupted and incomplete data points. In an extensive comparison, we show that this new model outperforms in retrieval accuracy and robustness popular associative memory models, such as autoencoders trained via backpropagation, and modern Hopfield networks. In particular, in completing partial data points, our model achieves remarkable results on natural image datasets, such as ImageNet, with a surprisingly high accuracy, even when only a tiny fraction of pixels of the original images is presented. Our model provides a plausible framework to study learning and retrieval of memories in the brain, as it closely mimics the behavior of the hippocampus as a memory index and generative model.

PDF Details

AAAI Conference 2021 Conference Paper

Detecting Beneficial Feature Interactions for Recommender Systems

Yixin Su
Rui Zhang
Sarah Erfani
Zhenghua Xu

Feature interactions are essential for achieving high accuracy in recommender systems. Many studies take into account the interaction between every pair of features. However, this is suboptimal because some feature interactions may not be that relevant to the recommendation result, and taking them into account may introduce noise and decrease recommendation accuracy. To make the best out of feature interactions, we propose a graph neural network approach to effectively model them, together with a novel technique to automatically detect those feature interactions that are beneficial in terms of recommendation accuracy. The automatic feature interaction detection is achieved via edge prediction with an L0 activation regularization. Our proposed model is proved to be effective through the information bottleneck principle and statistical interaction theory. Experimental results show that our model (i) outperforms existing baselines in terms of accuracy, and (ii) automatically identifies beneficial feature interactions.

PDF Details

AAAI Conference 2020 Conference Paper

Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence

Yuhang Song
Andrzej Wojcicki
Thomas Lukasiewicz
Jianyi Wang
Abi Aryan
Zhenghua Xu
Mai Xu
Zihan Ding

Learning agents that are not only capable of taking tests, but also innovating is becoming a hot topic in AI. One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other, and improving each agent means proposing new problems for others. However, existing evaluation platforms are either not compatible with multi-agent settings, or limited to a speciﬁc game. That is, there is not yet a general evaluation platform for research on multi-agent intelligence. To this end, we introduce Arena, a general evaluation platform for multi-agent intelligence with 35 games of diverse logics and representations. Furthermore, multi-agent intelligence is still at the stage where many problems remain unexplored. Therefore, we provide a building toolkit for researchers to easily invent and build novel multi-agent problems from the provided game set based on a GUI-conﬁgurable social tree and ﬁve basic multi-agent reward schemes. Finally, we provide Python implementations of ﬁve state-of-the-art deep multi-agent reinforcement learning baselines. Along with the baseline implementations, we release a set of 100 best agents/teams that we can train with different training schemes for each game, as the base for evaluating agents with population performance. As such, the research community can perform comparisons under a stable and uniform standard. All the implementations and accompanied tutorials have been open-sourced for the community at https: //sites. google. com/view/arena-unity/.

PDF Details

NeurIPS Conference 2020 Conference Paper

Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks

Yuhang Song
Thomas Lukasiewicz
Zhenghua Xu
Rafal Bogacz

Backpropagation (BP) has been the most successful algorithm used to train artificial neural networks. However, there are several gaps between BP and learning in biologically plausible neuronal networks of the brain (learning in the brain, or simply BL, for short), in particular, (1) it has been unclear to date, if BP can be implemented exactly via BL, (2) there is a lack of local plasticity in BP, i. e. , weight updates require information that is not locally available, while BL utilizes only locally available information, and (3)~there is a lack of autonomy in BP, i. e. , some external control over the neural network is required (e. g. , switching between prediction and learning stages requires changes to dynamics and synaptic plasticity rules), while BL works fully autonomously. Bridging such gaps, i. e. , understanding how BP can be approximated by BL, has been of major interest in both neuroscience and machine learning. Despite tremendous efforts, however, no previous model has bridged the gaps at a degree of demonstrating an equivalence to BP, instead, only approximations to BP have been shown. Here, we present for the first time a framework within BL that bridges the above crucial gaps. We propose a BL model that (1) produces \emph{exactly the same} updates of the neural weights as~BP, while (2)~employing local plasticity, i. e. , all neurons perform only local computations, done simultaneously. We then modify it to an alternative BL model that (3) also works fully autonomously. Overall, our work provides important evidence for the debate on the long-disputed question whether the brain can perform~BP.

PDF Details

AAAI Conference 2020 Conference Paper

Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards

Yuhang Song
Jianyi Wang
Thomas Lukasiewicz
Zhenghua Xu
Shangtong Zhang
Andrzej Wojcicki
Mai Xu

Intrinsic rewards were introduced to simulate how human intelligence works; they are usually evaluated by intrinsicallymotivated play, i. e. , playing games without extrinsic rewards but evaluated with extrinsic rewards. However, none of the existing intrinsic reward approaches can achieve humanlevel performance under this very challenging setting of intrinsically-motivated play. In this work, we propose a novel megalomania-driven intrinsic reward (called mega-reward), which, to our knowledge, is the ﬁrst approach that achieves human-level performance in intrinsically-motivated play. Intuitively, mega-reward comes from the observation that infants’ intelligence develops when they try to gain more control on entities in an environment; therefore, mega-reward aims to maximize the control capabilities of agents on given entities in a given environment. To formalize mega-reward, a relational transition model is proposed to bridge the gaps between direct and latent control. Experimental studies show that mega-reward (i) can greatly outperform all state-ofthe-art intrinsic reward approaches, (ii) generally achieves the same level of performance as Ex-PPO and professional human-level scores, and (iii) has also a superior performance when it is incorporated with extrinsic rewards.

PDF Details

AAAI Conference 2019 Conference Paper

Diversity-Driven Extensible Hierarchical Reinforcement Learning

Yuhang Song
Jianyi Wang
Thomas Lukasiewicz
Zhenghua Xu
Mai Xu

Hierarchical reinforcement learning (HRL) has recently shown promising advances on speeding up learning, improving the exploration, and discovering intertask transferable skills. Most recent works focus on HRL with two levels, i. e. , a master policy manipulates subpolicies, which in turn manipulate primitive actions. However, HRL with multiple levels is usually needed in many real-world scenarios, whose ultimate goals are highly abstract, while their actions are very primitive. Therefore, in this paper, we propose a diversitydriven extensible HRL (DEHRL), where an extensible and scalable framework is built and learned levelwise to realize HRL with multiple levels. DEHRL follows a popular assumption: diverse subpolicies are useful, i. e. , subpolicies are believed to be more useful if they are more diverse. However, existing implementations of this diversity assumption usually have their own drawbacks, which makes them inapplicable to HRL with multiple levels. Consequently, we further propose a novel diversity-driven solution to achieve this assumption in DEHRL. Experimental studies evaluate DEHRL with nine baselines from four perspectives in two domains; the results show that DEHRL outperforms the state-of-the-art baselines in all four aspects.

PDF Details

IJCAI Conference 2017 Conference Paper

Tag-Aware Personalized Recommendation Using a Hybrid Deep Model

Zhenghua Xu
Thomas Lukasiewicz
Cheng Chen
Yishu Miao
Xiangwu Meng

Recently, many efforts have been put into tag-aware personalized recommendation. However, due to uncontrolled vocabularies, social tags are usually redundant, sparse, and ambiguous. In this paper, we propose a deep neural network approach to solve this problem by mapping the tag-based user and item profiles to an abstract deep feature space, where the deep-semantic similarities between users and their target items (resp. , irrelevant items) are maximized (resp. , minimized). To ensure the scalability in practice, we further propose to improve this model's training efficiency by using hybrid deep learning and negative sampling. Experimental results show that our approach can significantly outperform the state-of-the-art baselines in tag-aware personalized recommendation (3. 8 times better than the best baseline), and that using hybrid deep learning and negative sampling can dramatically enhance the model's training efficiency (hundreds of times quicker), while maintaining similar (and sometimes even better) training quality and recommendation performance.

PDF Details