Related papers: Synergizing Deconfounding and Temporal Generalizat…
In this study, we focus on estimating the heterogeneous treatment effect (HTE) for survival outcome. The outcome is subject to censoring and the number of covariates is high-dimensional. We utilize data from both the randomized controlled…
Treatment effects can be estimated from observational data as the difference in potential outcomes. In this paper, we address the challenge of estimating the potential outcome when treatment-dose levels can vary continuously over time.…
Time Series Alignment is a critical task in signal processing with numerous real-world applications. In practice, signals often exhibit temporal shifts and scaling, making classification on raw data prone to errors. This paper introduces a…
In the context of medical decision making, counterfactual prediction enables clinicians to predict treatment outcomes of interest under alternative courses of therapeutic actions given observed patient history. In this work, we present…
Video Temporal Grounding (VTG) faces a cross-modal semantic gap that often leads to background features being incorrectly aligned with the query, while directly matching the query to moments results in insufficient discriminability and…
The synthetic control method (SCM) estimates causal effects in panel data with a single-treated unit by constructing a counterfactual outcome as a weighted combination of untreated control units that matches the pre-treatment trajectory. In…
Radiology Report Generation (RRG) draws attention as a vision-and-language interaction of biomedical fields. Previous works inherited the ideology of traditional language generation tasks, aiming to generate paragraphs with high readability…
Temporal Sentence Grounding (TSG) aims to identify relevant moments in an untrimmed video that semantically correspond to a given textual query. Despite existing studies having made substantial progress, they often overlook the issue of…
Consider sensitivity analysis to assess the worst-case possible values of counterfactual outcome means and average treatment effects under sequential unmeasured confounding in a longitudinal study with time-varying treatments and…
Session-based recommendation (SR) models aim to recommend top-K items to a user, based on the user's behaviour during the current session. Several SR models are proposed in the literature, however,concerns have been raised about their…
Electronic records contain sequences of events, some of which take place all at once in a single visit, and others that are dispersed over multiple visits, each with a different timestamp. We postulate that fine temporal detail, e.g.,…
Time Series Foundation Models (TSFMs) advance generalization and data efficiency in time series forecasting by unified large-scale pretraining. But TSFMs remain lacking when adapting to specific downstream forecasting tasks for two reasons.…
Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video…
Spiking neural networks (SNNs) have received widespread attention as an ultra-low power computing paradigm. Recent studies have shown that SNNs suffer from severe overfitting, which limits their generalization performance. In this paper, we…
The rapid expansion of digital information and knowledge across structured and unstructured sources has heightened the importance of Information Retrieval (IR). While dense retrieval methods have substantially improved semantic matching for…
Time-parallel algorithms, such as Parareal, are well-understood for linear problems, but their convergence analysis for nonlinear, chaotic systems remains limited. This paper introduces a new theoretical framework for analysing…
Counterfactual reasoning is an important paradigm applicable in many fields, such as healthcare, economics, and education. In this work, we propose a novel method to address the issue of \textit{selection bias}. We learn two groups of…
Irregularly sampled multivariate event streams remain a stubbornly difficult modality for generative modeling: tokenization-based approaches break down when inter-event intervals vary by orders of magnitude, and neural temporal point…
We investigate two recently proposed multivariate time series analysis techniques that aim at detecting phase synchronization clusters in spatially extended, nonstationary systems with regard to field applications. The starting point of…
Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs) by providing access to external knowledge. However, current research primarily focuses on retrieval quality, often overlooking the critical…