Related papers: PRISM: Iterative Cross-Modal Posterior Refinement …

Accurate multistep forecasting of node-level attributes on dynamic graphs is critical for applications ranging from financial trust networks to biological networks. Existing spatiotemporal graph neural networks typically assume a static…

In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters. While large language models have demonstrated this ability, how…

Semantic map models visualize systematic relations among semantic functions through graph structures and are widely used in linguistic typology. However, existing construction methods either depend on labor-intensive expert reasoning or on…

Variational methods that rely on a recognition network to approximate the posterior of directed graphical models offer better inference and learning than previous methods. Recent advances that exploit the capacity and flexibility in this…

Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks(GNNs) have emerged as a powerful tool for graph…

Group activities usually involve spatiotemporal dynamics among many interactive individuals, while only a few participants at several key frames essentially define the activity. Therefore, effectively modeling the group-relevant and…

Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal…

Remarkable gains in deep learning usually rely on tremendous supervised data. Ensuring the modality diversity for one object in training set is critical for the generalization of cutting-edge deep models, but it burdens human with heavy…

Causal representation learning algorithms discover lower-dimensional representations of data that admit a decipherable interpretation of cause and effect; as achieving such interpretable representations is challenging, many causal learning…

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes. Two prevalent approaches for TR are single-step retrieval, which…

Explaining the outcome of deep learning decisions based on affect is challenging but necessary if we expect social companion robots to interact with users on an emotional level. In this paper, we present a commonsense approach that utilizes…

Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. However, its application to the downstream Image-Text Retrieval…

Action recognition is a fundamental task in video understanding. Existing methods typically extract unified features to process all actions in one video, which makes it challenging to model the interactions between different objects in…

Despite the recent success of large language models (LLMs) in time-series forecasting, most existing methods still adopt a Deep Synchronous Fusion strategy, where dense interactions between textual and temporal features are enforced at…

Multimodal Attributed Graphs (MAGs) have been widely adopted for modeling complex systems by integrating multi-modal information, such as text and images, on nodes. However, we identify a discrepancy between the implicit semantic structure…

While modern text-to-image (T2I) models excel at generating images from intricate prompts, they struggle to capture the key details when the inputs are descriptive paragraphs. This limitation stems from the prevalence of concise captions…

With the rapid development of the new energy vehicle industry, the efficient disassembly and recycling of power batteries have become a critical challenge for the circular economy. In current unstructured disassembly scenarios, the dynamic…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli, essentially images, from functional Magnetic Resonance Imaging (fMRI)…