AAAI 2025 Papers

Partially linear models (PLM) have attracted much attention in the field of statistical machine learning. Specially, the ability of variable selection of PLM has been studied extensively due to the high requirement of model interpretability. However, few of the existing works concerns the false discovery rate (FDR) controllability of variable selection associated with PLM. To address this issue, we formulate a new Knockoffs Inference scheme for Linear And Nonlinear Discoverer (called KI-LAND), where FDR is controlled with respect to both linear and nonlinear variables for automatic structure discovery. For the proposed KI-LAND, theoretical guarantees are established for both FDR controllability and power, and experimental evaluations are provided to validate its effectiveness.

Category-level object pose estimation is an important task in computer vision. Some prior methods based on assumptions often struggle with drastic changes in object appearance. To address this challenge, we propose a new method for object pose estimation based on object-adaptive keypoints. In this paper, we first introduce a transformer-based keypoint prediction method for adaptive forecasting of point cloud keypoints. This method calculates the similarity between keypoint features and point cloud features, allowing keypoints to represent object geometry more effectively. Furthermore, to enhance the geometric feature construction of keypoints, we propose a graph-based keypoint feature aggregation method, which considers both the structural relationships between keypoints and the point cloud, strengthening the network's understanding of geometric structures. At this stage, keypoints remain at the geometric spatial level of the object and have not been predicted in NOCS. To improve the accuracy of keypoint prediction in NOCS, we design a NOCS voxelization method that divides NOCS into multiple voxels and accurately predicts NOCS keypoints within these voxels. Experimental results on multiple benchmark datasets demonstrate that our proposed KeyPose method outperforms all existing methods, achieving over 20% improvement in pose accuracy on some critical datasets.

Reconstructing high-quality 3D models from sparse 2D images has garnered significant attention in computer vision. Recently, 3D Gaussian Splatting (3DGS) has gained prominence due to its explicit representation with efficient training speed and real-time rendering capabilities. However, existing methods still heavily depend on accurate camera poses for reconstruction. Although some recent approaches attempt to train 3DGS models without the Structure-from-Motion (SfM) preprocessing from monocular video datasets, these methods suffer from prolonged training times, making them impractical for many applications. In this paper, we present an efficient framework that operates without any depth or matching model. Our approach initially uses SfM to quickly obtain rough camera poses within seconds, and then refines these poses by leveraging the dense representation in 3DGS. This framework effectively addresses the issue of long training times. Additionally, we integrate the densification process with joint refinement and propose a coarse-to-fine frequency-aware densification to reconstruct different levels of details. This approach prevents camera pose estimation from being trapped in local minima or drifting due to high-frequency signals. Our method significantly reduces training time from hours to minutes while achieving more accurate novel view synthesis and camera pose estimation compared to previous methods.

Large language models have shown great potential in complex reasoning tasks, yet their performance is often hampered by the scarcity of high-quality and reasoning-focused training datasets. Addressing this challenge, we propose Key-PointDriven Data Synthesis (KPDDS), a novel data synthesis framework that synthesizes question-answer pairs by leveraging key points and exemplar practices from authentic data sources. KPDDS ensures the generation of novel questions with rigorous quality control and substantial scalability. As a result, we present KPMath, an extensive synthetic dataset tailored for mathematical reasoning, comprising over 800K questionanswer pairs. Utilizing KPMath and augmenting it with additional reasoning-intensive corpora, we create the comprehensive KPMath-Plus dataset. Our experiments demonstrate that this dataset can enhance the mathematical reasoning performance of models across various architectures and sizes. The Qwen1.5-72B model, fine-tuned on KPMath-Plus, achieves 87.0% accuracy on GSM8K and 58.3% on MATH, surpassing competitors in the 7B to 72B range and best commercial models like GPT-4 across multiple math reasoning datasets.

Time series forecasting requires reliable uncertainty estimates. Gaussian process regression provides a powerful framework for modelling this in a probabilistic fashion. However, its application to large time series is challenging, due to its cubic time complexity and quadratic memory requirement. In this work, we present KernelMatmul, a novel method that accelerates Gaussian process inference and thus facilitates scaling of Gaussian process regression to large, irregularly sampled and multi-output time series. Leveraging conjugate gradients in combination with sparsity approximation, KernelMatmul achieves time and memory complexity linear in the number of samples. We thoroughly benchmark our new method against multiple baselines to demonstrate its benefits and limitations, both in efficiency and accuracy.

Few-shot anomaly detection (FSAD) aims to detect unseen anomaly regions with the guidance of very few normal support images from the same class. Existing FSAD methods usually find anomalies by directly designing complex text prompts to align them with visual features under the prevailing large vision-language model paradigm. However, these methods, almost always, neglect intrinsic contextual information in visual features, e.g., the interaction relationships between different vision layers, which is an important clue for detecting anomalies comprehensively. To this end, we propose a kernel-aware graph prompt learning framework, termed as KAG-prompt, by reasoning the cross-layer relations among visual features for FSAD. Specifically, a kernel-aware hierarchical graph is built by taking the different layer features focusing on anomalous regions of different sizes as nodes, meanwhile, the relationships between arbitrary pairs of nodes stand for the edges of the graph. By message passing over this graph, KAG-prompt can capture cross-layer contextual information, thus leading to more accurate anomaly prediction. Moreover, to integrate the information of multiple important anomaly signals in the prediction map, we propose a novel image-level scoring method based on multi-level information fusion. Extensive experiments on MVTecAD and VisA datasets show that KAG-prompt achieves state-of-the-art FSAD results for image-level/pixel-level anomaly detection.

Time sequences are essential in fields such as finance, healthcare, and environmental science, where understanding temporal dependencies and making accurate predictions are crucial. These sequences often exhibit complexities like nonlinearity, noise, and concept drift. Traditional models struggle to capture the intricate dynamics of multivariate and co-evolving sequences, particularly in contexts where relationships between variables shift unpredictably. This thesis introduces a range of Kernel Representation Learning (KRL) methodologies to address these challenges. We develop kernel self-representation learning to capture the temporal dependencies and hidden structures, while identifying concept drift in co-evolving sequences. Additionally, we explore theoretical connections between KRL and advanced deep-learning models. The proposed methods are validated through real-world applications, showing improvements in predictive accuracy, interpretability, and robustness.

Black box optimization (BBO) focuses on optimizing unknown functions in high-dimensional spaces. In many applications, sampling the unknown function is expensive, imposing a tight sample budget.Ongoing work is making progress on reducing the sample budget by learning the shape/structure of the function, known as kernel learning. We propose a new method to learn the kernel of a Gaussian Process. Our idea is to create a continuous kernel space in the latent space of a variational autoencoder, and run an auxiliary optimization to identify the best kernel. Results show that the proposed method, Kernel Optimized Blackbox Optimization (KOBO), outperforms state of the art by estimating the optimal at considerably lower sample budgets. Results hold not only across synthetic benchmark functions but also in real applications. We show that a hearing aid may be personalized with fewer audio queries to the user, or a generative model could converge to desirable images from limited user ratings.

Visual Language Models such as CLIP excel in image recognition due to extensive image-text pre-training. However, applying the CLIP inference in zero-shot classification, particularly for medical image diagnosis, faces challenges due to: 1) the inadequacy of representing image classes solely with single category names; 2) the modal gap between the visual and text spaces generated by CLIP encoders. Despite attempts to enrich disease descriptions with large language models, the lack of class-specific knowledge often leads to poor performance. In addition, empirical evidence suggests that existing proxy learning methods for zero-shot image classification on natural image datasets exhibit instability when applied to medical datasets. To tackle these challenges, we introduce the Knowledge Proxy Learning (KPL) to mine knowledge from CLIP. KPL is designed to leverage CLIP's multimodal understandings for medical image classification through Text Proxy Optimization and Multimodal Proxy Learning. Specifically, KPL retrieves image-relevant knowledge descriptions from the constructed knowledge-enhanced base to enrich semantic text proxies. It then harnesses input images and these descriptions, encoded via CLIP, to stably generate multimodal proxies that boost the zero-shot classification performance. Extensive experiments conducted on both medical and natural image datasets demonstrate that KPL enables effective zero-shot image classification, outperforming all baselines. These findings highlight the great potential in this paradigm of mining knowledge from CLIP for medical image classification and broader areas.

Incomplete Multi-View Clustering (IMVC) has made significant progress by optimally merging multiple pre-specified incomplete views. Most existing IMVC algorithms operate under the assumption that view alignment is known, but in practice, the coupling information between views may be absent, thereby limiting the practical applicability of these methods. Being aware of this, we propose a novel IMVC method named Kernel cOupling And eLement imputAtion induced Multi-View Clustering (KOALA), which sufficiently explores the nonlinear relationship among features and optimally processes a group of kernels with missing and unaligned elements to simultaneously resolve multi-view clustering problem under both uncoupled and incomplete scenarios. Specifically, we first introduce a cross-kernel alignment learning strategy to reconstruct the coupling relationships among multiple kernels, which effectively captures high-order nonlinear relationships among samples and enhances alignment accuracy. Additionally, a low-rank tensor constraint is imposed on the optimizable alignment kernel tensor, facilitating the effective imputation of missing kernel elements by leveraging consistency information across views. Subsequently, we develop an alternative optimization approach with promising convergence to solve the resultant optimization problem. Extensive experimental results on various multi-view datasets demonstrate that the KOALA method achieves remarkable clustering performance.

Sensors are commonly deployed to perceive the environment. However, due to the high cost, sensors are usually sparsely deployed. Kriging is the tailored task to infer the unobserved nodes (without sensors) using the observed nodes (with sensors). The essence of kriging task is transferability. Recently, several inductive spatio-temporal kriging methods have been proposed based on graph neural networks, being trained based on a graph built on top of observed nodes via pretext tasks such as masking nodes out and reconstructing them. However, the graph in training is inevitably much sparser than the graph in inference that includes all the observed and unobserved nodes. The learned pattern cannot be well generalized for inference, denoted as graph gap. To address this issue, we first present a novel Increment training strategy: instead of masking nodes (and reconstructing them), we add virtual nodes into the training graph so as to mitigate the graph gap issue naturally. Nevertheless, the empty-shell virtual nodes without labels could have bad-learned features and lack supervision signals. To solve these issues, we pair each virtual node with its most similar observed node and fuse their features together; to enhance the supervision signal, we construct reliable pseudo labels for virtual nodes. As a result, the learned pattern of virtual nodes could be safely transferred to real unobserved nodes for reliable kriging. We name our new Kriging model with Increment Training Strategy as KITS. Extensive experiments demonstrate that KITS consistently outperforms existing methods by large margins, e.g., the improvement over MAE score could be as high as 18.33%.

Knowledge Graph Embedding (KGE) methods have achieved great success in predicting missing links in knowledge graphs, a task also known as Knowledge Graph Completion (KGC). Under this task, the Reciprocal Rank (RR) of ground-truth items serve as a key indicator for evaluating the method’s performance. However, most existing studies have overlooked the inconsistency between the ranking metric, RR, and the optimization objective functions, resulting in sub-optimal KGC performance. To address this issue, we propose a KGC framework called KGCRR by designing a novel upper bound function named CRR. By introducing the parameter-pressure ρ to shift the sigmoid function, CRR achieves a better approximation to RR compared with existing objective functions. We theoretically proved that by adjusting ρ, CRR can achieve a more effective approximation to RR. By narrowing the discrepancy with RR and alleviating the gradient vanishing issue associated with the direct optimization of RR loss, CRR demonstrates an advantage in optimizing RR. CRR serves as a plug-and-play objective, capable of seamless integration into various KGE methods. Through extensive experiments conducted on FB15k-237 and WN18RR datasets, we have obtained promising results, with an average improvement of 19.06% in MRR, indicating that CRR significantly enhances the performance of existing methods.

Adversarial patches pose a significant threat to computer vision models' integrity, decreasing the accuracy of various tasks, including object detection (OD). Most existing OD defenses exhibit a trade-off between enhancing the model's adversarial robustness and maintaining its performance on benign images. We propose KDAT (knowledge distillation with adversarial tuning), a novel mechanism that enhances the robustness of an OD model without compromising its performance on benign images or its inference time. Our method combines the knowledge distillation (KD) technique with the adversarial tuning concept to teach the model to match the predictions of adversarial images with those of their corresponding benign ones. To match these predictions, we designed four unique loss components, allowing the student model to effectively distill the knowledge of different features from various parts of the teacher model. Our extensive evaluation on the COCO and INRIA datasets demonstrates KDAT's ability to improve the performance of Faster R-CNN and DETR on benign images by 2-4 mAP% and adversarial examples by 10-15 mAP%, outperforming other state-of-the-art (SOTA) defenses. Furthermore, our additional physical evaluation on the Superstore dataset demonstrates KDAT's SOTA adversarial robustness against printed patches (improvement of 22 mAP% compared to the undefended model).

Artificial intelligence has achieved notable results in sign language recognition and translation. However, relatively few efforts have been made to significantly improve the quality of life for the 72 million hearing-impaired people worldwide. Sign language translation models, relying on video inputs, involves with large parameter sizes, making it time-consuming and computationally intensive to be deployed. This directly contributes to the scarcity of human-centered technology in this field. Additionally, the lack of datasets in sign language translation hampers research progress in this area. To address these, we first propose a cross-modal multi-knowledge distillation technique from 3D to 1D and a novel end-to-end pre-training text correction framework. Compared to other pre-trained models, our framework achieves significant advancements in correcting text output errors. Our model achieves a decrease in Word Error Rate (WER) of at least 1.4% on PHOENIX14 and PHOENIX14T datasets compared to the state-of-the-art CorrNet. Additionally, the TensorFlow Lite (TFLite) quantized model size is reduced to 12.93 MB, making it the smallest, fastest, and most accurate model to date. We have also collected and released extensive Chinese sign language datasets, and developed a specialized training vocabulary. To address the lack of research on data augmentation for landmark data, we have designed comparative experiments on various augmentation methods. Moreover, we performed a simulated deployment and prediction of our model on Intel platform CPUs and assessed the feasibility of deploying the model on other platforms.

Deep hashing has been widely used for large-scale approximate nearest neighbor search due to its storage and search efficiency. However, existing deep hashing methods predominantly rely on abundant training data, leaving the more challenging scenario of low-resource adaptation for deep hashing relatively underexplored. This setting involves adapting pre-trained models to downstream tasks with only an extremely small number of training samples available. Our preliminary benchmarks reveal that current methods suffer significant performance degradation due to the distribution shift caused by limited training samples. To address these challenges, we introduce Class-Calibration LoRA (CLoRA), a novel plug-and-play approach that dynamically constructs low-rank adaptation matrices by leveraging class-level textual knowledge embeddings. CLoRA effectively incorporates prior class knowledge as anchors, enabling parameter-efficient fine-tuning while maintaining the original data distribution. Furthermore, we propose Knowledge-Guided Discrete Optimization (KIDDO), a framework to utilize class knowledge to compensate for the scarcity of visual information and enhance the discriminability of hash codes. Extensive experiments demonstrate that our proposed method, Knowledge- Anchored Low-Resource Adaptation Hashing (KALAHash), significantly boosts retrieval performance and achieves a 4× data efficiency in low-resource scenarios.

Cross-prompt automated essay scoring (AES) aims to train models using essays from different source prompts and test them on new target prompt essays. A core challenge of the task is to learn as much shared knowledge as possible between essays from different prompts in order to better represent new prompt essays. Previous studies primarily focus on learning this knowledge on a general, coarse-grained level, ignoring that the shared knowledge among prompts is highly detailed and contains a more comprehensive range of information that is not fully investigated. In this paper, we propose a novel multi-aspect knowledge finding and aligning optimization strategy to better acquire this detailed various shared knowledge. We also introduce LLM to extract explicit, interpretable knowledge from implicit, multi-aspect shared knowledge and use this knowledge to improve the representation and evaluation performance of new prompt essays. We conduct extensive experiments on public datasets. The results show that our approach outperforms current state-of-the-art models and is effective on cross-prompt AES.

The powerful capability of HyperGraph Neural Networks (HGNNs) in modeling intricate, high-order relationships among multiple data samples stems primarily from their ability to aggregate both the direct neighborhood features of individual nodes and those associated with hyperedges. However, the limited scope of feature propagation in existing HGNNs significantly reduces the utilization of hypergraph information, exacerbating over-squashing and over-smoothing issues. To this end, we propose a novel K-hop HyperGraph Neural Network (KHGNN) to facilitate the interactions of distant nodes and hyperedges. Specifically, the bisection nested convolution based on HyperGINE is employed to extract features from nodes, hyperedges, and structures along all shortest paths between nodes or hyperedges, providing representations of long-distance relationships. With these comprehensive path features, nodes and hyperedges are guided to aggregate distant information while learning their complex relationships. The extensive experiments, particularly on long-range graph datasets, demonstrate that the proposed method achieves SOTA performance compared to existing HGNNs and graph neural networks.

Recent advancements in large language models (LLMs) have significantly improved various natural language processing (NLP) tasks. Typically, LLMs are trained to predict the next token, aligning well with many NLP tasks. However, in knowledge graph (KG) scenarios, entities are the fundamental units and identifying an entity requires at least several tokens. This leads to a granularity mismatch between KGs and natural languages. To address this issue, we propose K-ON, which integrates KG knowledge into the LLM by employing multiple head layers for next k-step prediction. K-ON can not only generate entity-level results in one step, but also enables contrastive loss against entities, which is the most powerful tool in KG representation learning. Experimental results show that K-ON outperforms state-of-the-art methods that incorporate text and even the other modalities.

To break through the limitations of pre-training models on fixed categories, Open-Set Object Detection (OSOD) and Open-Set Segmentation (OSS) have attracted a surge of interest from researchers. Inspired by large language models, mainstream OSOD and OSS methods generally utilize text as a prompt, achieving remarkable performance. Following SAM paradigm, some researchers use visual prompts, such as points, boxes, and masks that cover detection or segmentation targets. Despite these two prompt paradigms exhibit excellent performance, they also reveal inherent limitations. On the one hand, it is difficult to accurately describe characteristics of specialized category using textual description. On the other hand, existing visual prompt paradigms heavily rely on multi-round human interaction, which hinders them being applied to fully automated pipeline. To address the above issues, we propose a novel prompt paradigm in OSOD and OSS, that is, Image Prompt Paradigm. This brand new prompt paradigm enables to detect or segment specialized categories without multi-round human intervention. To achieve this goal, the proposed image prompt paradigm uses just a few image instances as prompts, and we propose a novel framework named MI Grounding for this new paradigm. In this framework, high-quality image prompts are automatically encoded, selected and fused, achieving the single-stage and non-interactive inference. We conduct extensive experiments on public datasets, showing that MI Grounding achieves competitive performance on OSOD and OSS benchmarks compared to text prompt paradigm methods and visual prompt paradigm methods. Moreover, MI Grounding can greatly outperform existing method on our constructed specialized ADR50K dataset.