AAAI 2025 Papers

Reservoir Computing (RC) models, a subclass of recurrent neural networks, are distinguished by their fixed, non-trainable input layer and dynamically coupled reservoir, with only the static readout layer being trained. This design circumvents the issues associated with backpropagating error signals through time, thereby enhancing both stability and training efficiency. RC models have been successfully applied across a broad range of application domains. Crucially, they have been demonstrated to be universal approximators of time-invariant dynamic filters with fading memory, under various settings of approximation norms and input driving sources. Simple Cycle Reservoirs (SCR) represent a specialized class of RC models with a highly constrained reservoir architecture, characterized by uniform ring connectivity and binary input-to-reservoir weights with an aperiodic sign pattern. For linear reservoirs, given the reservoir size, the reservoir construction has only one degree of freedom -- the reservoir cycle weight. Such architectures are particularly amenable to hardware implementations without significant performance degradation in many practical tasks. In this study we endow these observations with solid theoretical foundations by proving that SCRs operating in real domain are universal approximators of time-invariant dynamic filters with fading memory. Our results supplement recent research showing that SCRs in the complex domain can approximate, to arbitrary precision, any unrestricted linear reservoir with a non-linear readout. We furthermore introduce a novel method to drastically reduce the number of SCR units, making such highly constrained architectures natural candidates for low-complexity hardware implementations. Our findings are supported by empirical studies on real-world time series datasets.

Post-processing networks (PPNs) are components that modify the outputs of arbitrary modules in task-oriented dialogue systems and are optimized using reinforcement learning (RL) to improve the overall task completion capability of the system. However, previous PPN-based approaches have been limited to handling only a subset of modules within a system, which poses a significant limitation in improving the system performance. In this study, we propose a joint optimization method for post-processing the outputs of all modules using universal post-processing networks (UniPPNs), which are language-model-based networks that can modify the outputs of arbitrary modules in a system as a sequence-transformation task. Moreover, our RL algorithm, which employs a module-level Markov decision process, enables fine-grained value and advantage estimation for each module, thereby stabilizing joint learning for post-processing the outputs of all modules. Through both simulation-based and human evaluation experiments using the MultiWOZ dataset, we demonstrated that UniPPN outperforms conventional PPNs in the task completion capability of task-oriented dialogue systems.

Object pose estimation, crucial in computer vision and robotics applications, faces challenges with the diversity of unseen categories. We propose a zero-shot method to achieve category-level 6-DOF object pose estimation, which exploits both 2D and 3D universal features of input RGB-D image to establish semantic similarity-based correspondences and can be extended to unseen categories without additional model fine-tuning. Our method begins with combining efficient 2D universal features to find sparse correspondences between intra-category objects and gets initial coarse pose. To handle the correspondence degradation of 2D universal features if the pose deviates much from the target pose, we use an iterative strategy to optimize the pose. Subsequently, to resolve pose ambiguities due to shape differences between intra-category objects, the coarse pose is refined by optimizing with dense alignment constraint of 3D universal features. Our method outperforms previous methods on the REAL275 and Wild6D benchmarks for unseen categories.

Domain Adaptive Object Detection (DAOD) transfers knowledge from a labeled source domain to an unannotated target domain under closed-set assumption. Universal DAOD (UniDAOD) extends DAOD to handle open-set, partial-set, and closed-set domain adaptation. In this paper, we first unveil two issues: domain-private category alignment is crucial for global-level features, and the domain probability heterogeneity of features across different levels. To address these issues, we propose a novel Dual Probabilistic Alignment (DPA) framework to model domain probability as Gaussian distribution, enabling the heterogeneity domain distribution sampling and measurement. The DPA consists of three tailored modules: the Global-level Domain Private Alignment (GDPA), the Instance-level Domain Shared Alignment (IDSA), and the Private Class Constraint (PCC). GDPA utilizes the global-level sampling to mine domain-private category samples and calculate alignment weight through a cumulative distribution function to address the global-level private category alignment. IDSA utilizes instance-level sampling to mine domain-shared category samples and calculates alignment weight through Gaussian distribution to conduct the domain-shared category domain alignment to address the feature heterogeneity. The PCC aggregates domain-private category centroids between feature and probability spaces to mitigate negative transfer. Extensive experiments demonstrate that our DPA outperforms state-of-the-art UniDAOD and DAOD methods across various datasets and scenarios, including open, partial, and closed sets.

Chart Question Answering (CQA) requires models to perform chart perception and reasoning. Recent studies driven by Large Language Models (LLMs) have dominated CQA. These include employing more cognitively capable LLMs for indirectly reasoning over transformed charts, i.e., tables, and directly perceiving charts utilizing Multimodal Large Language Models (MLLMs) with a wider perceptual range. Yet, they often encounter bottlenecks due to the limitation of the receptive field of LLMs and the fragility of the complex reasoning of some MLLMs. To unite the strengths of LLMs and MLLMs to complement each other's limitations, we propose Synergy, a framework that unites the power of both models for CQA. Synergy first unites the chart with a table as the augmented perceptual signal. Next, it unites LLMs and MLLMs, scheduling the former to decompose a question into subquestions and the latter to answer these by perceiving the chart. Lastly, it operates LLMs to summarize the subquestion-answer pairs to refine the final answer. Extensive experimental results on popular CharQA and PlotQA benchmarks reveal that, with the power of union, Synergy outperforms strong competitors and achieves superior boosts over naive MLLMs by uniting them with a smaller LLM.

Large Vision-Language Model (LVLM), leveraging Large Language Model (LLM) as the cognitive core, has recently become one of the most representative multimodal model paradigms. However, with the expansion of unimodal branches, \emph{i.e.} visual encoder and LLM, the storage and computational burdens intensify, posing challenges for deployment. Structured pruning has proved promising in compressing large models by trimming a large portion of insignificant network structures. Nevertheless, most of them are predominantly designed for LLMs, either relying on unitary importance metrics that fail to deal with modality-wise imbalances or adopting generic pruning and recovery paradigms that overlook the unique calibration status and capability requirements of large models, leading to substantial performance degradation. To address these issues, we propose a novel structured pruning approach for LVLMs, dubbed Unified Knowledge Maintenance Pruning and Progressive Recovery with Weight Recalling (UKMP). Specifically, we design a Unified Knowledge Maintenance Importance (UKMI) metric, which simultaneously considers balancing the block-wise and modality-wise importance by adaptive normalization, optimizing the importance estimation by refining gradient-based criteria, and maintaining the knowledge capacity of LVLMs by using the angle distribution information entropy. Moreover, we develop a LoRA-based Progressive Distillation (LPD) method that recalls the pruned weights and performs progressive distillation for comprehensive recovery. Extensive experimental results across various vision-language tasks demonstrate the effectiveness of our approach, comparing to the state-of-the-art structured pruning methods.

Graph Neural Networks (GNNs) have proven effective and typically benefit from pre-training on accessible graphs to enhance performance on tasks with limited labeled data. However, existing GNNs are constrained by the ``one-domain-one-model'' limitation, which restricts their effectiveness across diverse graph domains. In this paper, we tackle this problem by developing a method called Multi-Domain Pre-training for a Unified GNN Model (MDP-GNN). This method is based on the philosophical notion that everything is interconnected, suggesting that a latent meta-domain exists to encompass the diverse graph domains and their interconnections. MDP-GNN seeks to identify and utilize this meta-domain to train a unified GNN model through three core strategies. Firstly, it integrates node feature semantics from different domains to create unified representations. Secondly, it employs a bi-level learning strategy to build a domain-synthesized network that identifies latent connections to facilitate cross-domain knowledge transfer. Thirdly, it uses Wasserstein distance to map diverse domains into the common meta-domain for graph distribution alignment. We validate the effectiveness of MDP-GNN through theoretical analysis and extensive experiments on four real-world graph datasets, showing its superiority in enhancing GNN performance across diverse domains.

The image compression model has long struggled with adaptability and generalization, as the decoded bitstream typically serves only human or machine needs and fails to preserve information for unseen visual tasks. Therefore, this paper innovatively introduces supervision obtained from multimodal pre-training models and incorporates adaptive multi-objective optimization tailored to support both human visual perception and machine vision simultaneously with a single bitstream, denoted as Unified and Generalized Image Coding for Machine (UG-ICM). Specifically, to get rid of the reliance between compression models with downstream task supervision, we introduce Contrastive Language-Image Pre-training (CLIP) models into the training constraint for improved generalization. Global-to-instance-wise CLIP supervision is applied to help obtain hierarchical semantics that make models more generalizable for the tasks relying on the information of different granularity. Furthermore, for supporting both human and machine visions with only a unifying bitstream, we incorporate a conditional decoding strategy that takes as conditions human or machine preferences, enabling the bitstream to be decoded into different versions for corresponding preferences. As such, our proposed UG-ICM is fully trained in a self-supervised manner, i.e., without awareness of any specific downstream models and tasks. The extensive experiments have shown that the proposed UG-ICM is capable of achieving remarkable improvements in various unseen machine analytics tasks, while simultaneously providing perceptually satisfying images.

Representation learning of urban spatial-temporal data is fundamental and critical, serving a wide range of intelligent applications. Given that road networks and trajectories are inherently interrelated, their joint representation learning can significantly enhance the accuracy and utility of these applications. However, effectively learning joint representations for these two types of data remains challenging, particularly due to the complexities of interaction modeling and cross-scale optimization. To this end, we propose a unified framework, named UniTR, for joint representation learning of road networks and trajectories. Specifically, we first design a hierarchical propagation mechanism to model the complex many-to-many interactions between road networks and trajectories, thereby generating informative embeddings. Then, a triple-level contrastive optimization module is incorporated to systematically select valid positive and negative samples, further refining the embeddings. Experiments conducted on real-world datasets from two cities clearly demonstrate the effectiveness and superiority of UniTR.

Learning-based point cloud compression methods have made significant progress in terms of performance. However, these methods still encounter challenges including high complexity, limited compression modes, and a lack of support for variable rate, which restrict the practical application of these methods. In order to promote the development of practical point cloud compression, we propose an efficient unified point cloud geometry compression framework, dubbed as UniPCGC. It is a lightweight framework that supports lossy compression, lossless compression, variable rate and variable complexity. First, we introduce the Uneven 8-Stage Lossless Coder (UELC) in the lossless mode, which allocates more computational complexity to groups with higher coding difficulty, and merges groups with lower coding difficulty. Second, Variable Rate and Complexity Module (VRCM) is achieved in the lossy mode through joint adoption of a rate modulation module and dynamic sparse convolution. Finally, through the dynamic combination of UELC and VRCM, we achieve lossy compression, lossless compression, variable rate and complexity within a unified framework. Compared to the previous state-of-the-art method, our method achieves a compression ratio (CR) gain of 8.1% on lossless compression, and a Bjontegaard Delta Rate (BD-Rate) gain of 14.02% on lossy compression, while also supporting variable rate and variable complexity.

We introduce UniMuMo, a unified multimodal model capable of taking arbitrary text, music, and motion data as input conditions to generate outputs across all three modalities. To address the lack of time-synchronized data, we align unpaired music and motion data based on rhythmic patterns to leverage existing large-scale music-only and motion-only datasets. By converting music, motion, and text into token-based representation, our model bridges these modalities through a unified encoder-decoder transformer architecture. To support multiple generation tasks within a single framework, we introduce several architectural improvements. We propose encoding motion with a music codebook, mapping motion into the same feature space as music. We introduce a music-motion parallel generation scheme that unifies all music and motion generation tasks into a single transformer decoder architecture with a single training task of music-motion joint generation. Moreover, the model is designed by fine-tuning existing pre-trained single-modality models, significantly reducing computational demands. Extensive experiments demonstrate that UniMuMo achieves competitive results on all unidirectional generation benchmarks across music, motion, and text modalities.

Graph anomaly detection has attracted significant attention due to its critical applications, such as identifying money laundering in financial systems and detecting fake reviews on social networks. However, two major challenges persist: (1) anomaly detection at the node, edge, and graph levels is often addressed in isolation, hindering the integration of complementary information to identify anomalies arising from collective behaviors; and (2) the inherent label sparsity in graph data, coupled with the difficulty of obtaining high-quality annotations, exacerbates bias in detection. To address these challenges, we propose UniFORM, a unified self-supervised anomaly detection framework comprising two modules: UIO and UMC. UIO unifies node-, edge-, and graph-level tasks from a subgraph perspective, leveraging an energy-based GNN for iterative multi-granular anomaly detection. UMC enhances meta-learning through contrastive learning and employs Langevin dynamics to generate phantom samples as substitutes for anomalous data, reducing reliance on labeled data. Extensive experiments on real-world datasets demonstrate that UniFORM significantly outperforms state-of-the-art methods across multiple granularities.

Growing customer demand for smart solutions in robotics and augmented reality has attracted considerable attention to 3D object detection from point clouds. Yet, existing indoor datasets taken individually are too small and insufficiently diverse to train a powerful and general 3D object detection model. In the meantime, more general approaches utilizing foundation models are still inferior in quality to those based on supervised training for a specific task. In this work, we propose UniDet3D, a simple yet effective 3D object detection model, which is trained on a mixture of indoor datasets and is capable to work in various indoor environments. By unifying different label spaces, UniDet3D enables learning a strong representation across multiple datasets through a supervised joint training scheme. The proposed network architecture is built upon a vanilla transformer encoder, making it easy to run, customize and extend the prediction pipeline for practical use. Extensive experiments demonstrate that UniDet3D obtains significant gains over existing 3D object detection methods in 6 indoor benchmarks: ScanNet (+1.1 mAP50), S3DIS (+9.1 mAP50), ARKitScenes (+19.4 mAP25), MultiScan (+14.3 mAP50), 3RScan (+3.2 mAP50), and ScanNet++ (+2.7 mAP50).

Image demoiréing poses one of the most formidable challenges in image restoration, primarily due to the unpredictable and anisotropic nature of moiré patterns. Limited by the quantity and diversity of training data, current methods tend to overfit to a single moiré domain, resulting in performance degradation for new domains, and restricting their robustness in real-world applications. In this paper, we propose a universal image demoiréing solution, UniDemoiré, which has superior generalization capability. Notably, we propose innovative and effective data generation and synthesis methods that can automatically provide vast high-quality moiré images to train a universal demoiréing model. Our extensive experiments demonstrate the cutting-edge performance and broad potential of our approach for generalized image demoiréing.

Data-driven analysis has shown promising results in identifying subtle patterns in the behavior of individuals with Autism Spectrum Disorder (ASD) for diagnosis and intervention. However, most existing methods primarily focus on a single behavioral modality (e.g., eye movements) instead of capturing the intricate multimodal behavior of humans. We propose a multimodal approach that investigates the underlying connections between eye movements and hand motions through eye-to-hand prediction. To tackle the highly noisy and irregular behavioral data, we propose a novel approach that defines the prediction as a machine translation problem and leverages a sequence-to-sequence machine learning model for the prediction. An experimental study on a dataset collected from a VR system has demonstrated high prediction accuracy. The significant difference in the prediction accuracy between the autistic group and their typically developing (TD) peers serves as quantitative evidence to objectively understand the restricted and repetitive behaviors (RRBs) in autistic children. The source code can be accessed here: https://github.com/mathjams/AAAI_2024.

We now live in a world where we can reach people directly through social media, without relying on traditional media such as television and radio. On the other hand, social media platforms collect vast amounts of data and create very specific profiles of different users through targeted advertising. Various interest groups, including politicians, advertisers, and stakeholders, utilize these platforms to target potential users to advance their interests by adapting their messaging. This process, known as microtargeting, relies on data-driven techniques that exploit the rich information collected by social networks about their users. Microtargeting is a double-edged sword. It enhances the relevance and efficiency of targeted content, can influence people to take action based on personal beliefs. This could be great, increasing the relevance based on users to help guide people in making better health decisions and offering them opportunities for career growth. On the other hand, it can influence people to make decisions against their own interests, foster echo chambers, and increase polarization. My research is motivated by the fact that some of these risks can be mitigated by providing transparency, identifying conflicting or harmful messaging choices, and indicating bias introduced in messaging in a nuanced way. I provide computational frameworks to analyze microtargeting patterns, which will help policymakers make better decisions. This is crucial for promoting healthy public discourse in the digital age and maintaining a cohesive society.

With the rapid rise of AI technologies such as ChatGPT, understanding and integrating AI into K-12 education has become increasingly important. However, teachers often lack the AI literacy necessary to navigate these tools, which can lead to the perpetuation of misconceptions and biases in the classroom. This study seeks to identify K-12 teachers’ self-identified needs regarding AI education and compare them with existing research on professional development (PD) for AI integration. We surveyed 34 K-12 teachers to assess their knowledge of AI, identify areas where they require further support, and evaluate the relevance of current PD offerings. Our findings reveal a significant disconnect between the top-down assumptions of expert-driven PD initiatives and the practical needs articulated by teachers. Key themes emerged, including a diverse range of AI understanding among educators, a strong preference for hands-on, practical training, and a demand for ongoing institutional support. Additionally, teachers expressed a desire for collaborative learning environments to share strategies and experiences related to AI. This study underscores the importance of tailoring PD programs to address the unique contexts and challenges faced by educators, advocating for a more personalized approach that fosters confidence and competence in AI integration. By aligning PD offerings with teachers’ needs, we aim to enhance their ability to effectively utilize AI tools in the classroom, ultimately enriching the educational experience for students.

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the blackboxed agent’s importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent’s importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the masking agents to identify important agents. Specifically, we define the optimization function to minimize the reward difference before and after action randomization and introduce sparsity constraints to encourage the exploration of more action randomization of agents during training. The experimental results in seven multi-agent tasks demonstrate that EMAI achieves higher fidelity in explanations compared to baselines and provides more effective guidance in practical applications concerning understanding policies, launching attacks, and patching policies.

Large Language Models (LLMs) and Generative AI (GenAI) have markedly changed the landscape of many fields, including education. While these tools have significant capabilities, they also require understanding to effectively and responsibly use them. Additionally, little work has been done to evaluate how these tools can best benefit education at the secondary level, with design insights from instructors. My work focuses on informing secondary instructors of these tools, receiving their input on how to make these tools work best for them, and finally using this input to create and evaluate an in-class Retrieval-Augmented Generation (RAG)-based chatbot for their students to use to improve learning outcomes. This work aims to bridge the gap between the latest in computing technology and secondary education classrooms.