D.3 Open source performance on mini test set . . . . . . . . . . . . . . . . . . . . . A.1 V ersion 2 We have fixed some bugs in the evaluation code, resulting in slight differences compared to the previous release. The issue was that 149 samples were not evaluated in the previous version, and these have now been included in the new update. A.2 V ersion 3 We have clarified certain statements and added experimental results to address the reviewer's questions. B.1 Limitations Despite these advancements, our dataset does exhibit certain limitations, largely stemming from inherited biases from the source datasets: Currently, we only address scenarios where both the question and the answer span a single time duration. Given a question, the annotated time span must be a single, continuous duration, which might be limiting for all scenes. The presence of noisy or inaccurate annotations in the source datasets, including captions and timestamps, poses a challenge. Despite our efforts, some of these errors could not be automatically filtered out. The extent of this issue is detailed in the qualitative visualization conducted by our human reviewers, as presented in supplementary. The average duration of ground truth events in our dataset is relatively long. This characteristic has the unintended consequence of hindering the models' ability to detect and analyze fine-grained actions within shorter video segments. These drawbacks highlight areas for potential improvement and indicate the necessity for ongoing refinement to ensure the creation of more accurate and unbiased video language models. B.2 Social Impact Though we provide an assessment of temporal reasoning and moment localization, the types and scene diversity are still limited. We inherit the video classes from the two source video datasets, which may not be sufficient for a comprehensive assessment of all kinds of temporal reasoning. This limitation could introduce a bias. For both curated data and video data, they do not contain any personally identifiable information. Besides, some of the video samples in the source datasets might be slightly uncomfortable depending on the viewer. For example, some videos discuss tattoos and piercings, and some of them present news about social events including demonstrations or war reports. However, we only release the data of curated question-answer and time span.

Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and interpretability, self-attention is gradually becoming a key component in event sequence models. However, like most other sequence models, self-attention does not account for the time span between events and thus captures sequential signals rather than temporal patterns. Without relying on recurrent network structures, self-attention recognizes event orderings via positional encoding. To bridge the gap between modelling time-independent and time-dependent event sequence, we introduce a functional feature map that embeds time span into high-dimensional spaces. By constructing the associated translation-invariant time kernel function, we reveal the functional forms of the feature map under classic functional function analysis results, namely Bochner's Theorem and Mercer's Theorem. We propose several models to learn the functional time representation and the interactions with event representation. These methods are evaluated on real-world datasets under various continuous-time event sequence prediction tasks. The experiments reveal that the proposed methods compare favorably to baseline models while also capture useful time-event interactions.

The performance of speaker verification systems is adversely affected by speaker aging. However, due to challenges in data collection, particularly the lack of sustained and large-scale longitudinal data for individuals, research on speaker aging remains difficult. In this paper, we present V oxAging, a large-scale longitudinal dataset collected from 293 speakers (226 English speakers and 67 Mandarin speakers) over several years, with the longest time span reaching 17 years (approximately 900 weeks). For each speaker, the data were recorded at weekly intervals. We studied the phenomenon of speaker aging and its effects on advanced speaker verification systems, analyzed individual speaker aging processes, and explored the impact of factors such as age group and gender on speaker aging research.

Click-through Rate (CTR) prediction in real-world recommender systems often deals with billions of user interactions every day. To improve the training efficiency, it is common to update the CTR prediction model incrementally using the new incremental data and a subset of historical data. However, the feature embeddings of a CTR prediction model often get stale when the corresponding features do not appear in current incremental data. In the next period, the model would have a performance degradation on samples containing stale features, which we call the feature staleness problem. To mitigate this problem, we propose a Feature Staleness Aware Incremental Learning method for CTR prediction (FeSAIL) which adaptively replays samples containing stale features. We first introduce a staleness aware sampling algorithm (SAS) to sample a fixed number of stale samples with high sampling efficiency. We then introduce a staleness aware regularization mechanism (SAR) for a fine-grained control of the feature embedding updating. We instantiate FeSAIL with a general deep learning-based CTR prediction model and the experimental results demonstrate FeSAIL outperforms various state-of-the-art methods on four benchmark datasets.

Current Hierarchical Reinforcement Learning (HRL) algorithms excel in long-horizon sequential decision-making tasks but still face two challenges: delay effects and spurious correlations. To address them, we propose a causal HRL approach called D3HRL. First, D3HRL models delayed effects as causal relationships across different time spans and employs distributed causal discovery to learn these relationships. Second, it employs conditional independence testing to eliminate spurious correlations. Finally, D3HRL constructs and trains hierarchical policies based on the identified true causal relationships. These three steps are iteratively executed, gradually exploring the complete causal chain of the task. Experiments conducted in 2D-MineCraft and MiniGrid show that D3HRL demonstrates superior sensitivity to delay effects and accurately identifies causal relationships, leading to reliable decision-making in complex environments.

Research on large language models (LLMs) has shown remarkable performance in domains such as mathematics, programming, and literary creation. However, most studies have focused on semantic memory-based question answering, neglecting LLMs' potential to handle episodic memory (EM)-related queries. This oversight has led to suboptimal performance in applications requiring EM, including emotional companionship, personal AI assistants, and AI teachers. To address this gap, we introduce Echo, a LLM enhanced with temporal episodic memory. We propose a Multi-Agent Data Generation Framework that guides the model in generating multi-turn, complex scenario episodic memory dialogue data (EM-Train). Temporal information is innovatively incorporated into the LLM training process, and Echo is trained using the EM-Train. Furthermore, We develop an EM-Test benchmark specifically designed to evaluate LLMs' episodic memory capabilities. The EM-Test assesses performance across various time spans and difficulty levels, providing a comprehensive evaluation of multi-turn episodic memory dialogues. Our experiments demonstrate that Echo significantly outperforms state-of-the-art LLMs on EM-Test. Additionally, a qualitative analysis reveals Echo's potential to exhibit human-like episodic memory capabilities. We will open-source all datasets, code, and model weights.

The estimation of uncertainties associated with predictions from quantitative structure-activity relationship (QSAR) models can accelerate the drug discovery process by identifying promising experiments and allowing an efficient allocation of resources. Several computational tools exist that estimate the predictive uncertainty in machine learning models. However, deviations from the i.i.d. setting have been shown to impair the performance of these uncertainty quantification methods. We use a real-world pharmaceutical dataset to address the pressing need for a comprehensive, large-scale evaluation of uncertainty estimation methods in the context of realistic distribution shifts over time. We investigate the performance of several uncertainty estimation methods, including ensemble-based and Bayesian approaches. Furthermore, we use this real-world setting to systematically assess the distribution shifts in label and descriptor space and their impact on the capability of the uncertainty estimation methods. Our study reveals significant shifts over time in both label and descriptor space and a clear connection between the magnitude of the shift and the nature of the assay. Moreover, we show that pronounced distribution shifts impair the performance of popular uncertainty estimation methods used in QSAR models. This work highlights the challenges of identifying uncertainty quantification methods that remain reliable under distribution shifts introduced by real-world data.

Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and interpretability, self-attention is gradually becoming a key component in event sequence models. However, like most other sequence models, self-attention does not account for the time span between events and thus captures sequential signals rather than temporal patterns. Without relying on recurrent network structures, self-attention recognizes event orderings via positional encoding. To bridge the gap between modelling time-independent and time-dependent event sequence, we introduce a functional feature map that embeds time span into high-dimensional spaces.

Large language models (LLMs) have captured significant interest from both academia and industry due to their impressive performance across various textual tasks. However, the potential of LLMs to analyze physiological time-series data remains an emerging research field. Particularly, there is a notable gap in the utilization of LLMs for analyzing wearable biosignals to achieve cuffless blood pressure (BP) measurement, which is critical for the management of cardiovascular diseases. This paper presents the first work to explore the capacity of LLMs to perform cuffless BP estimation based on wearable biosignals. We extracted physiological features from electrocardiogram (ECG) and photoplethysmogram (PPG) signals and designed context-enhanced prompts by combining these features with BP domain knowledge and user information. Subsequently, we adapted LLMs to BP estimation tasks through fine-tuning. To evaluate the proposed approach, we conducted assessments of ten advanced LLMs using a comprehensive public dataset of wearable biosignals from 1,272 participants. The experimental results demonstrate that the optimally fine-tuned LLM significantly surpasses conventional task-specific baselines, achieving an estimation error of 0.00 $\pm$ 9.25 mmHg for systolic BP and 1.29 $\pm$ 6.37 mmHg for diastolic BP. Notably, the ablation studies highlight the benefits of our context enhancement strategy, leading to an 8.9% reduction in mean absolute error for systolic BP estimation. This paper pioneers the exploration of LLMs for cuffless BP measurement, providing a potential solution to enhance the accuracy of cuffless BP measurement.