Related papers: Beyond Extrapolation: Knowledge Utilization Paradi…

Most research designing novel predictive models, or employing existing ones, assumes that training and testing data are independent and identically distributed. In practice, the data encountered at serving time often deviate from the…

Multi-object tracking (MOT) and trajectory prediction are two critical components in modern 3D perception systems that require accurate modeling of multi-agent interaction. We hypothesize that it is beneficial to unify both tasks under one…

Traffic forecasting plays a key role in Intelligent Transportation Systems, and significant strides have been made in this field. However, most existing methods can only predict up to four hours in the future, which doesn't quite meet…

Future trajectories of neighboring traffic agents have a significant influence on the path planning and decision-making of autonomous vehicles. While trajectory forecasting is a well-studied field, research mainly focuses on snapshot-based…

Downsampling-based methods for time series forecasting have attracted increasing attention due to their superiority in capturing sequence trends. However, this approaches mainly capture dependencies within subsequences but neglect…

The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This work address this gap by modeling knowledge retention, the…

Programming Knowledge Tracing (PKT) has recently advanced through hybrid approaches that integrate attention-based feature modeling for code representation with RNN-based sequential prediction. While these models report strong empirical…

Lateral predictive coding is a recurrent neural network which creates energy-efficient internal representations by exploiting statistical regularity in sensory inputs. Here we investigate the trade-off between information robustness and…

Inductive knowledge graph completion requires models to comprehend the underlying semantics and logic patterns of relations. With the advance of pretrained language models, recent research have designed transformers for link prediction…

Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets? This work provides positive evidence to this using a broad…

Predictive variability due to data ambiguities has typically been addressed via construction of dedicated models with built-in probabilistic capabilities that are trained to predict uncertainty estimates as variables of interest. These…

Drawing on infrastructure studies in HCI and CSCW, this paper introduces Protocol Futuring, a methodological framework that extends design futuring by foregrounding protocols -- rules, standards, and coordination mechanisms -- as the…

Predicting outcomes in external domains is challenging due to hidden confounders that potentially influence both predictors and outcomes. Well-established methods frequently rely on stringent assumptions, explicit knowledge about the…

Deep Learning models have become dominant in tackling financial time-series analysis problems, overturning conventional machine learning and statistical methods. Most often, a model trained for one market or security cannot be directly…

Reinforcement learning (RL) agents performing complex tasks must be able to remember observations and actions across sizable time intervals. This is especially true during the initial learning stages, when exploratory behaviour can increase…

Due to the concise and structured nature of tables, the knowledge contained therein may be incomplete or missing, posing a significant challenge for table question answering (TableQA) and data analysis systems. Most existing datasets either…

This paper utilizes well-designed item-item path modelling between consecutive items with attention mechanisms to sequentially model dynamic user-item evolutions on dynamic knowledge graph for explainable recommendations. Compared with…

Knowledge graph construction typically relies either on predefined ontologies or on schema-free extraction. Ontology-driven pipelines enforce consistent typing but require costly schema design and maintenance, whereas schema-free methods…

Delay embedding---a method for reconstructing dynamical systems by delay coordinates---is widely used to forecast nonlinear time series as a model-free approach. When multivariate time series are observed, several existing frameworks can be…

In highly interactive driving scenes, trajectory prediction is conditioned on information from surrounding traffic participants such as cars and pedestrians. Our main contribution is a comprehensive analysis of state-of-the-art trajectory…