25 accepted papers
Text-to-LiDAR generation can customize 3D data with rich structures and diverse scenes for downstream tasks. However, the scarcity of Text-LiDAR pairs often causes insufficient training priors, generating overly smooth 3D scenes. Moreover, low-quality text descriptions may degrade generation quality
Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fusion: textual descriptions express temporal impacts implicitly and qualitatively, whereas forecasting models rely on expl…
In-context learning-based medical segmentation (ICLM) enables foundation models to generalize to unseen cases without retraining. To enhance performance on test queries, existing methods typically follow a two-stage process: (1) using a retrieval encoder (RE) to map both queries and training samples
Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically integrating a probability-flow ODE. We propose Riemannian MeanFlow (RMF), extending MeanFlow to manifold-valued generation where velocities lie in location-…
Pretraining on large-scale data followed by fine-tuning has become a standard paradigm for visual models. However, noise in the pretraining data can be absorbed by the model and carried into downstream tasks, causing catastrophic inheritance. Prior studies mainly link this issue to changes in the fe
Existing conditional Denoising Diffusion Probabilistic Models (DDPMs) with a Noise-Conditional Framework (NCF) remain challenging for 3D scene understanding tasks, as the complex geometric details in scenes increase the difficulty of fitting the gradients of the data distribution (the scores) from s…
Spatio-temporal data mining is crucial for decision-making and planning in diverse domains. However, in real-world scenarios, training and testing data are often not independent or identically distributed due to rapid changes in data distributions over time and space, resulting in spatio-temporal ou
Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks. GitHub issue resolving is a key challenge among these tasks. While recent approaches have made progress on this task, they focus on te…
Due to the superior ability of global dependency, transformer and its variants have become the primary choice in Masked Time-series Modeling (MTM) towards time-series classification task. In this paper, we experimentally analyze that existing transformer-based MTM methods encounter with two under-ex…
Although transformer-based methods excel in stereo image super-resolution, the full potential of the distinctive, complementary information inherent in stereo images has not been fully utilized. We propose a Disparity-Guided Cross-View Transformer (DCT) to extract features across dimensions and view…
The discriminative feature is crucial for point cloud registration. Recent methods improve the feature discriminative by distinguishing between non-overlapping and overlapping region points. However, they still face challenges in distinguishing the ambiguous structures in the overlapping regions. Th…
Multi-view representation learning integrates multiple observable views of an entity into a unified representation to facilitate downstream tasks. Current methods predominantly focus on distinguishing compatible components across views, followed by a single-step parallel fusion process. However, thi…
Origin-Destination (OD) demand prediction is a pivotal yet highly challenging task in intelligent transportation systems, aiming to accurately forecast cross-region ridership flows within urban networks. While previous studies have focused on modeling node-to-node relationships, most of them neglect
Current feature fusion strategies often fail to adequately account for the influence of activation intensity across different scales on small object features, which impedes the effective detection of small objects. To address this limitation, we propose the Region-Adaptive Feature Disentanglement an
Evaluating the performance of Multi-modal Large Language Models (MLLMs), integrating both point cloud and language, presents significant challenges. The lack of a comprehensive assessment hampers determining whether these models truly represent advancements, thereby impeding further progress in the…
In the era of code large language models (code LLMs), data engineering plays a pivotal role during the instruction fine-tuning phase. To train a versatile model, previous efforts devote tremendous efforts into crafting instruction data covering all the downstream scenarios. Nonetheless, this will in…
Detecting out-of-distribution (OOD) data is essential to ensure the reliability of machine learning models when deployed in real-world scenarios. Different from most previous test-time OOD detection methods that focus on designing OOD scores, we delve into the challenges in OOD detection from the pe…
Semantic annotation for points of interest (POIs) is the process of annotating a POI with a category label, which facilitates many services related to POIs, such as POI search and recommendation. Most of the existing solutions extract features related to POIs from abundant user-generated content dat…
Points of interest (POIs) carry a wealth of semantic information of varying locations in cities and thus have been widely used to enable various location-based services. To understand POI semantics, existing methods usually model contextual correlations of POI categories in users' check-in sequences…
Pre-training a model and then fine-tuning it on downstream tasks has demonstrated significant success in the 2D image and NLP domains. However due to the unordered and non-uniform density characteristics of point clouds it is non-trivial to explore the prior knowledge of point clouds and pre-train a…
Document AI, or Document Intelligence pertains to the technology used for document comprehension and analysis. Given the multimodality of documents, the importance of multimodal learning cannot be overstated in the field of document intelligence research. Multimodal data augmentation, as a crucial a…
Recently, learning urban region representations utilizing multi-modal data (information views) has become increasingly popular, for deep understanding of the distributions of various socioeconomic features in cities. However, previous methods usually blend multi-view information in a posteriors stag…
Source-free domain adaptation (SFDA) newly emerges to transfer the relevant knowledge of a well-trained source model to an unlabeled target domain, which is critical in various privacy-preserving scenarios. Most existing methods focus on learning the domain-invariant representations depending solely…
Large volumes of urban statistical data with multiple views imply rich knowledge about the development degree of cities. These data present crucial statistics which play an irreplaceable role in the regional analysis and urban computing. In reality, however, the statistical data divided into fine-gr…
We propose a new method for learning with multi-field categorical data. Multi-field categorical data are usually collected over many heterogeneous groups. These groups can reflect in the categories under a field. The existing methods try to learn a universal model that fits all data, which is challe…