Related papers: An Effective and Efficient Time-aware Entity Align…
Temporal Knowledge Graph (TKG) reasoning often involves completing missing factual elements along the timeline. Although existing methods can learn good embeddings for each factual element in quadruples by integrating temporal information,…
Spatio-temporal alignment is crucial for temporal modeling of end-to-end (E2E) perception in autonomous driving (AD), providing valuable structural and textural prior information. Existing methods typically rely on the attention mechanism…
The Efficient Adaptive Transformer (EAT) framework unifies three adaptive efficiency techniques - progressive token pruning, sparse attention, and dynamic early exiting - into a single, reproducible architecture for input-adaptive…
Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test…
The proliferation of generative video models has made detecting AI-generated and manipulated videos an urgent challenge. Existing detection approaches often fail to generalize across diverse manipulation types due to their reliance on…
Test-time adaptation with pre-trained vision-language models has attracted increasing attention for tackling distribution shifts during the test time. Though prior studies have achieved very promising performance, they involve intensive…
Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs). The core challenge of this task lies in understanding the complex semantic information regarding…
Temporal knowledge graph completion (TKGC) has become a popular approach for reasoning over the event and temporal knowledge graphs, targeting the completion of knowledge with accurate but missing information. In this context, tensor…
Multi-modal entity alignment (MMEA) is essential for enhancing knowledge graphs and improving information retrieval and question-answering systems. Existing methods often focus on integrating modalities through their complementarity but…
Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing large-scale KGs. Over the course of its development, supervision has been considered necessary for…
Recent advances in LLM-based agent systems have shown promise on complex, long-horizon tasks, but existing agent protocols (e.g., A2A and MCP) do not adequately support lifecycle-aware coordination across agents, tools, and environments. To…
Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is…
Temporal knowledge graphs (TKGs) support reasoning over time-evolving facts, yet state-of-the-art models are often computationally heavy and costly to deploy. Existing compression and distillation techniques are largely designed for static…
Reasoning on Temporal Knowledge Graphs (TKGs) is essential for predicting future events and time-aware facts. While existing methods are effective at capturing relational dynamics, their performance is limited by a closed-world assumption,…
Knowledge graphs contain rich knowledge about various entities and the relational information among them, while temporal knowledge graphs (TKGs) describe and model the interactions of the entities over time. In this context, automatic…
Temporal Knowledge Graph (TKG) representation learning embeds entities and event types into a continuous low-dimensional vector space by integrating the temporal information, which is essential for downstream tasks, e.g., event prediction…
Detecting and analyzing complex patterns in multivariate time-series data is crucial for decision-making in urban and environmental system operations. However, challenges arise from the high dimensionality, intricate complexity, and…
We propose Lite-STGNN, a lightweight spatial-temporal graph neural network for long-term multivariate forecasting that integrates decomposition-based temporal modeling with learnable sparse graph structure. The temporal module applies…
Entity alignment aims to use pre-aligned seed pairs to find other equivalent entities from different knowledge graphs (KGs) and is widely used in graph fusion-related fields. However, as the scale of KGs increases, manually annotating…
Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such as mislabel detection, data selection, and copyright…