Author name cluster

Xinran Li

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.

17 papers

2 author rows

AAAI Conference 2026 Conference Paper

Do LLMs Feel? Teaching Emotion Recognition with Prompts, Retrieval, and Curriculum Learning

Xinran Li
Yu Liu
Jiaqi Qiao
Xiujuan Xu

Emotion Recognition in Conversation (ERC) is a crucial task for understanding human emotions and enabling natural human-computer interaction. Although Large Language Models (LLMs) have recently shown great potential in this field, their ability to capture the intrinsic connections between explicit and implicit emotions remains limited. We propose a novel ERC training framework, PRC-Emo, which integrates Prompt engineering, demonstration Retrieval, and Curriculum learning, with the goal of exploring whether LLMs can effectively perceive emotions in conversational contexts. Specifically, we design emotion-sensitive prompt templates based on both explicit and implicit emotional cues to better guide the model in understanding the speaker’s psychological states. We construct the first dedicated demonstration retrieval repository for ERC, which includes training samples from widely used datasets, as well as high-quality dialogue examples generated by LLMs and manually verified. Moreover, we introduce a curriculum learning strategy into the LoRA fine-tuning process, incorporating weighted emotional shifts between same-speaker and different-speaker utterances to assign difficulty levels to dialogue samples, which are then organized in an easy-to-hard training sequence. Experimental results on two benchmark datasets—IEMOCAP and MELD—show that our method achieves new state-of-the-art (SOTA) performance, demonstrating the effectiveness and generalizability of our approach in improving LLM-based emotional understanding.

PDF Details DOI

AAMAS Conference 2026 Conference Paper

Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning

Sijia Li
Xinran Li
Shibo Chen
Jun Zhang

Offline multi-agent reinforcement learning (MARL) aims to solve cooperative decision-making problems in multi-agent systems using pre-collected datasets. Existing offline MARL methods primarily constrain training within the dataset distribution, resulting in overly conservative policies that struggle to generalize beyond the support of the data. While model-based approaches offer a promising solution by expanding the original dataset with synthetic data generated from a learned world model, the high dimensionality, non-stationarity, and complexity of multi-agent systems make it challenging to accurately estimate the transitions and reward functions in offline MARL. Given the difficulty of directly modeling joint dynamics, we propose a local-to-global (LOGO) world model, a novel framework that leverages local predictions—which are easier to estimate—to infer global state dynamics, thus improving prediction accuracy while implicitly capturing agent-wise dependencies. Using the trained world model, we generate synthetic data toaugmenttheoriginaldataset, expandingtheeffectivestate-action space. To ensure reliable policy learning, we further introduce an uncertainty-aware sampling mechanism that adaptively weights synthetic data by prediction uncertainty, reducing approximation error propagation to policies. In contrast to conventional ensemblebased methods, our approach requires only an additional encoder for uncertainty estimation, significantly reducing computational overheadwhilemaintainingaccuracy. Extensiveexperimentsacross 8 scenarios against 8 baselines demonstrate that our method surpasses state-of-the-art baselines on standard offline MARL benchmarks, establishing a new model-based baseline for generalizable offline multi-agent learning.

PDF

EAAI Journal 2025 Journal Article

A multi-topology quantum convolutional neural network with qubit-measurement attention for image classification

QingShan Wu
Wenjie Liu
Xinran Li
Zhaofeng Su
Jian Lei

With the increasing scale of data and complexity of problems, some researchers have explored the integration of parameterized quantum circuits (PQCs) within convolutional neural networks (CNNs) as a means to enhance algorithmic performance. However, in most current quantum convolutional neural networks (QCNN) models, a single topological structure for quantum kernels (qkernels) is adopted and only one qubit of qkernels is measured, both of which may limit the model’s performance. To solve these problems, a novel multi-topology quantum convolutional neural networks with qubit-measurement attention for image classification is proposed. In order to enhance the capability of feature extraction, a multi-topology PQCs strategy is proposed, i. e. , we adopt the different topology PQCs to construct quantum convolutional layers. In addition, a qubit-measurement attention mechanism is designed to mitigate the significant loss of entanglement information during the measurement phase. Specifically, each qubit in the qkernel is measured to generate a local feature map, and the weight of each local feature map is then calculated, resulting in the final feature map. Nine image classification experiments conducted on CIFAR-10 demonstrate that our model outperforms the state-of-the-art QCNN model, achieving an improvement of 11. 7% on ten categories classification. Our model not only introduces a new approach for constructing QCNNs but also provides valuable reference for designing attention mechanisms tailored to quantum computing.

Details DOI

NeurIPS Conference 2025 Conference Paper

Are Pixel-Wise Metrics Reliable for Computerized Tomography Reconstruction?

Tianyu Lin
Xinran Li
Chuntung Zhuang
Qi Chen
Yuanhao Cai
Kai Ding
Alan Yuille
Zongwei Zhou

Widely adopted evaluation metrics for sparse-view CT reconstruction, such as Structural Similarity Index Measure and Peak Signal-to-Noise Ratio, prioritize pixel-wise fidelity but often fail to capture the completeness of critical anatomical structures, particularly small or thin regions that are easily missed. To address this limitation, we propose a suite of novel anatomy-aware evaluation metrics designed to assess structural completeness across anatomical structures, including large organs, small organs, intestines, and vessels. Building on these metrics, we introduce CARE, a Completeness-Aware Reconstruction Enhancement framework that incorporates structural penalties during training to encourage anatomical preservation of significant structures. CARE is model-agnostic and can be seamlessly integrated into analytical, implicit, and generative methods. When applied to these methods, CARE substantially improves structural completeness in CT reconstructions, achieving up to 32% improvement for large organs, 22% for small organs, 40% for intestines, and 36% for vessels.

PDF Details

ICML Conference 2025 Conference Paper

C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning

Zifan Liu
Xinran Li
Jun Zhang 0004

Safe offline reinforcement learning aims to develop policies that maximize cumulative rewards while satisfying safety constraints without the need for risky online interaction. However, existing methods often struggle with the out-of-distribution (OOD) problem, leading to potentially unsafe and suboptimal policies. To address this issue, we first propose Constrained Implicit Q-learning (CIQL), a novel algorithm designed to avoid the OOD problem. In particular, CIQL expands the implicit update of reward value functions to constrained settings and then estimates cost value functions under the same implicit policy. Despite its advantages, the further performance improvement of CIQL is still hindered by the inaccurate discounted approximations of constraints. Thus, we further propose Constraint-Conditioned Implicit Q-learning (C2IQL). Building upon CIQL, C2IQL employs a cost reconstruction model to derive non-discounted cumulative costs from discounted values and incorporates a flexible, constraint-conditioned mechanism to accommodate dynamic safety constraints. Experiment results on DSRL benchmarks demonstrate the superiority of C2IQL compared to baseline methods in achieving higher rewards while guaranteeing safety constraints under different threshold conditions.

Details

ICLR Conference 2025 Conference Paper

Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning

Xinran Li
Xiaolu Wang
Chenjia Bai
Jun Zhang 0004

In cooperative multi-agent reinforcement learning (MARL), well-designed communication protocols can effectively facilitate consensus among agents, thereby enhancing task performance. Moreover, in large-scale multi-agent systems commonly found in real-world applications, effective communication plays an even more critical role due to the escalated challenge of partial observability compared to smaller-scale setups. In this work, we endeavor to develop a scalable communication protocol for MARL. Unlike previous methods that focus on selecting optimal pairwise communication links—a task that becomes increasingly complex as the number of agents grows—we adopt a global perspective on communication topology design. Specifically, we propose utilizing the exponential topology to enable rapid information dissemination among agents by leveraging its small-diameter and small-size properties. This approach leads to a scalable communication protocol, named ExpoComm. To fully unlock the potential of exponential graphs as communication topologies, we employ memory-based message processors and auxiliary tasks to ground messages, ensuring that they reflect global information and benefit decision-making. Extensive experiments on large-scale cooperative benchmarks, including MAgent and Infrastructure Management Planning, demonstrate the superior performance and robust zero-shot transferability of ExpoComm compared to existing communication strategies. The code is publicly available at [https://github.com/LXXXXR/ExpoComm](https://github.com/LXXXXR/ExpoComm).

Details

AAAI Conference 2025 Conference Paper

Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language Model

Weilin Sun
Xinran Li
Manyi Li
Kai Xu
Xiangxu Meng
Lei Meng

Indoor scene synthesis aims to automatically produce plausible, realistic, and diverse 3D indoor scenes, especially given arbitrary user requirements. Recently, the promising generalization ability of pre-trained large language models (LLM) assist in open-vocabulary indoor scene synthesis. However, the challenge lies in converting the LLM-generated outputs into reasonable and physically feasible scene layouts. In this paper, we propose to generate hierarchically structured scene descriptions with LLM and then compute the scene layouts. Specifically, we train a hierarchy-aware network to infer the fine-grained relative positions between objects and design a divide-and-conquer optimization to solve for scene layouts. The advantages of using hierarchically structured scene representation are two-fold. First, the hierarchical structure provides a rough grounding for object arrangement, which alleviates contradictory placements with dense relations and enhances the generalization ability of the network to infer fine-grained placements. Second, it naturally supports the divide-and-conquer optimization, by first arranging the sub-scenes and then the entire scene, to more effectively solve for a feasible layout. We conduct extensive comparison experiments and ablation studies with both qualitative and quantitative evaluations to validate the effectiveness of our key designs with the hierarchically structured scene representation. Our approach can generate more reasonable scene layouts while better aligned with the user requirements and LLM descriptions. We also present open-vocabulary scene synthesis and interactive scene design results to show the strength of our approach in the applications.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Learn How to Query from Unlabeled Data Streams in Federated Learning

Yuchang Sun
Xinran Li
Tao Lin
Jun Zhang

Federated learning (FL) enables collaborative learning among decentralized clients while safeguarding the privacy of their local data. Existing studies on FL typically assume offline labeled data available at each client when the training starts. Nevertheless, the training data in practice often arrive at clients in a streaming fashion without ground-truth labels. Given the expensive annotation cost, it is critical to identify a subset of informative samples for labeling on clients. However, selecting samples locally while accommodating the global training objective presents a challenge unique to FL. In this work, we tackle this conundrum by framing the data querying process in FL as a collaborative decentralized decision-making problem and proposing an effective solution named LeaDQ, which leverages multi-agent reinforcement learning algorithms. In particular, under the implicit guidance from global information, LeaDQ effectively learns the local policies for distributed clients and steers them towards selecting samples that can enhance the global model's accuracy. Extensive simulations on image and text tasks show that LeaDQ advances the model performance in various FL scenarios, outperforming the benchmarking algorithms.

PDF Details DOI

ECAI Conference 2025 Conference Paper

Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation

Xinran Li
Xiujuan Xu
Jiaqi Qiao

Emotion Recognition in Conversation (ERC) is a practical and challenging task. This paper proposes a novel multimodal approach, the Long-Short Distance Graph Neural Network (LSDGNN). Based on the Directed Acyclic Graph (DAG), it constructs a long-distance graph neural network and a short-distance graph neural network to obtain multimodal features of distant and nearby utterances, respectively. To ensure that long- and short-distance features are as distinct as possible in representation while enabling mutual influence between the two modules, we employ a Differential Regularizer and incorporate a BiAffine Module to facilitate feature interaction. In addition, we propose an Improved Curriculum Learning (ICL) to address the challenge of data imbalance. By computing the similarity between different emotions to emphasize the shifts in similar emotions, we design a “weighted emotional shift” metric and develop a difficulty measurer, enabling a training process that prioritizes learning easy samples before harder ones. Experimental results on the IEMOCAP and MELD datasets demonstrate that our model outperforms existing benchmarks.

Details

NeurIPS Conference 2025 Conference Paper

Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective

Yang Zhang
Xinran Li
Jianing Ye
Shuang Qiu
Delin Qu
Xiu Li
Chongjie Zhang
Chenjia Bai

World models have recently attracted growing interest in Multi-Agent Reinforcement Learning (MARL) due to their ability to improve sample efficiency for policy learning. However, accurately modeling environments in MARL is challenging due to the exponentially large joint action space and highly uncertain dynamics inherent in multi-agent systems. To address this, we reduce modeling complexity by shifting from jointly modeling the entire state-action transition dynamics to focusing on the state space alone at each timestep through sequential agent modeling. Specifically, our approach enables the model to progressively resolve uncertainty while capturing the structured dependencies among agents, providing a more accurate representation of how agents influence the state. Interestingly, this sequential revelation of agents' actions in a multi-agent system aligns with the reverse process in diffusion models—a class of powerful generative models known for their expressiveness and training stability compared to autoregressive or latent variable models. Leveraging this insight, we develop a flexible and robust world model for MARL using diffusion models. Our method, \textbf{D}iffusion-\textbf{I}nspired \textbf{M}ulti-\textbf{A}gent world model (DIMA), achieves state-of-the-art performance across multiple multi-agent control benchmarks, significantly outperforming prior world models in terms of final return and sample efficiency, including MAMuJoCo and Bi-DexHands. DIMA establishes a new paradigm for constructing multi-agent world models, advancing the frontier of MARL research. Codes are open-sourced at \url{https: //github. com/breez3young/DIMA}.

PDF Details

IROS Conference 2025 Conference Paper

TEM 3 -Learning: Time-Efficient Multimodal Multi-Task Learning for Advanced Assistive Driving

Wenzhuo Liu
Yicheng Qiao
Zhen Wang
Qiannan Guo
Zilong Chen
Meihua Zhou
Xinran Li
Letian Wang

Multi-task learning (MTL) can advance assistive driving by exploring inter-task correlations through shared representations. However, existing methods face two critical limitations: single-modality constraints limiting comprehensive scene understanding and inefficient architectures impeding real-time deployment. This paper proposes TEM 3 -Learning (Time-Efficient Multimodal Multi-task Learning), a novel framework that jointly optimizes driver emotion recognition, driver behavior recognition, traffic context recognition, and vehicle behavior recognition through a two-stage architecture. The first component, the mamba-based multi-view temporal-spatial feature extraction subnetwork (MTS-Mamba), introduces a forward-backward temporal scanning mechanism and global-local spatial attention to efficiently extract low-cost temporal-spatial features from multi-view sequential images. The second component, the MTL-based gated multimodal feature integrator (MGMI), employs task-specific multi-gating modules to adaptively highlight the most relevant modality features for each task, effectively alleviating the negative transfer problem in MTL. Evaluation on the AIDE dataset, our proposed model achieves state-of-the-art accuracy across all four tasks, maintaining a lightweight architecture with fewer than 6 million parameters and delivering an impressive 142. 32 FPS inference speed. Rigorous ablation studies further validate the effectiveness of the proposed framework and the independent contributions of each module. The code is available on https://github.com/Wenzhuo-Liu/TEM3-Learning.

Details

AIIM Journal 2025 Journal Article

TSFNet: A Temporal–Spectral Fusion Network for advanced speech emotion recognition in medical applications

Xinran Li
Peilin Huang
Xiaojiang Peng
Feng Sha
Xiaomao Fan
Ye Li

Speech emotion recognition (SER) is a critical component in enhancing communication systems and human–machine interaction, with significant potential for applications in the medical field. Although existing SER methods that combine temporal and spectral features have achieved notable advancements, they still encounter a big challenge in capturing emotional nuances, which are vital in medical diagnostics and patient care. In this study, we introduce a straightforward yet highly efficient network called TSFNet, which is the Temporal–Spectral Fusion Network via a Large-scale Pre-trained Model. This network is specifically designed to effectively process intricate emotional nuances by seamlessly integrating temporal and spectral information present in speech signals. By leveraging the capabilities of a large-scale pre-trained model, which serves as a powerful plug-and-play component for extracting and learning the temporal characteristics of speech, TSFNet enables a more accurate capture of complex emotional details crucial for medical applications. Extensive experiments are conducted on publicly available datasets, to evaluate the performance of TSFNet. Extensive experiments conducted on six public datasets demonstrate that TSFNet significantly outperforms existing baselines, achieving unweighted accuracies of 95. 57% for Savee, 92. 67% for Crema-D, 85. 71% for IEMOCAP, 100. 00% for Tess, 95. 86% for Emovo, and 80. 43% for Meld. It means that TSFNet has the potential in advancing medical diagnostic tools and patient monitoring systems.

Details DOI

AAMAS Conference 2024 Conference Paper

Context-aware Communication for Multi-agent Reinforcement Learning

Xinran Li
Jun Zhang

Effective communication protocols in multi-agent reinforcement learning (MARL) are critical to fostering cooperation and enhancing team performance. To leverage communication, many previous works have proposed to compress local information into a single message and broadcast it to all reachable agents. This simplistic messaging mechanism, however, may fail to provide adequate, critical, and relevant information to individual agents, especially in severely bandwidth-limited scenarios. This motivates us to develop contextaware communication schemes for MARL, aiming to deliver personalized messages to different agents. Our communication protocol, named CACOM, consists of two stages. In the first stage, agents exchange coarse representations in a broadcast fashion, providing context for the second stage. Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers. Furthermore, we employ the learned step size quantization (LSQ) technique for message quantization to reduce the communication overhead. To evaluate the effectiveness of CACOM, we integrate it with both actor-critic and value-based MARL algorithms. Empirical results on cooperative benchmark tasks demonstrate that CACOM provides evident performance gains over baselines under communication-constrained scenarios. The code is publicly available at https: //github. com/LXXXXR/CACOM.

PDF

AILAW Journal 2024 Journal Article

Graph contrastive learning networks with augmentation for legal judgment prediction

Yao Dong
Xinran Li
Jin Shi
Yongfeng Dong
Chen Chen

Abstract Legal Judgment Prediction (LJP) is a typical application of Artificial Intelligence in the intelligent judiciary. Current research primarily focuses on automatically predicting law articles, charges, and terms of penalty based on the fact description of cases. However, existing methods for LJP have limitations, such as neglecting document structure and ignoring case similarities. We propose a novel framework called Graph Contrastive Learning with Augmentation (GCLA) for legal judgment prediction to address these issues. GCLA constructs trainable document-level graphs for fact description, capturing local and global context through sentence-level subgraphs. Graph augmentation enhances robustness. We introduce a comparison case relation perspective, using graph contrastive learning to model case-text label relationships effectively. Experimental results on real-world datasets demonstrate the competitive performance of GCLA.

Details DOI

ICML Conference 2024 Conference Paper

Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning

Xinran Li
Zifan Liu
Shibo Chen 0002
Jun Zhang 0004

In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster exploration in such settings, it often complicates credit assignment among agents. To address this difficulty, we propose Individual Contributions as intrinsic Exploration Scaffolds (ICES), a novel approach to motivate exploration by assessing each agent’s contribution from a global view. In particular, ICES constructs exploration scaffolds with Bayesian surprise, leveraging global transition information during centralized training. These scaffolds, used only in training, help to guide individual agents towards actions that significantly impact the global latent state transitions. Additionally, ICES separates exploration policies from exploitation policies, enabling the former to utilize privileged global information during training. Extensive experiments on cooperative benchmark tasks with sparse rewards, including Google Research Football (GRF) and StarCraft Multi-agent Challenge (SMAC), demonstrate that ICES exhibits superior exploration capabilities compared with baselines. The code is publicly available at https: //github. com/LXXXXR/ICES.

Details

NeurIPS Conference 2024 Conference Paper

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

Xinran Li
Ling Pan
Jun Zhang

In multi-agent reinforcement learning (MARL), parameter sharing is commonly employed to enhance sample efficiency. However, the popular approach of full parameter sharing often leads to homogeneous policies among agents, potentially limiting the performance benefits that could be derived from policy diversity. To address this critical limitation, we introduce \emph{Kaleidoscope}, a novel adaptive partial parameter sharing scheme that fosters policy heterogeneity while still maintaining high sample efficiency. Specifically, Kaleidoscope maintains one set of common parameters alongside multiple sets of distinct, learnable masks for different agents, dictating the sharing of parameters. It promotes diversity among policy networks by encouraging discrepancy among these masks, without sacrificing the efficiencies of parameter sharing. This design allows Kaleidoscope to dynamically balance high sample efficiency with a broad policy representational capacity, effectively bridging the gap between full parameter sharing and non-parameter sharing across various environments. We further extend Kaleidoscope to critic ensembles in the context of actor-critic algorithms, which could help improve value estimations. Our empirical evaluations across extensive environments, including multi-agent particle environment, multi-agent MuJoCo and StarCraft multi-agent challenge v2, demonstrate the superior performance of Kaleidoscope compared with existing parameter sharing approaches, showcasing its potential for performance enhancement in MARL. The code is publicly available at \url{https: //github. com/LXXXXR/Kaleidoscope}.

PDF Details DOI

AAMAS Conference 2023 Conference Paper

AC2C: Adaptively Controlled Two-Hop Communication for Multi-Agent Reinforcement Learning

Xuefeng Wang
Xinran Li
Jiawei Shao
Jun Zhang

Learning communication strategies in cooperative multi-agent reinforcement learning (MARL) has recently attracted intensive attention. Early studies typically assumed a fully-connected communication topology among agents, which induces high communication costs and may not be feasible. Some recent works have developed adaptive communication strategies to reduce communication overhead, but these methods cannot effectively obtain valuable information from agents that are beyond the communication range. In this paper, we consider a realistic communication model where each agent has a limited communication range, and the communication topology dynamically changes. To facilitate effective agent communication, we propose a novel communication protocol called Adaptively Controlled Two-Hop Communication (AC2C). After an initial local communication round, AC2C employs an adaptive twohop communication strategy to enable long-range information exchange among agents to boost performance, which is implemented by a communication controller. This controller determines whether each agent should ask for two-hop messages and thus helps to reduce the communication overhead during distributed execution. We evaluate AC2C on three cooperative multi-agent tasks, and the experimental results show that it outperforms relevant baselines with lower communication costs.

PDF