视频时间基础（VTG）的目标是根据自然语言（NL）描述在未修剪视频中定位时间矩。由于现实世界的应用程序提供了永无止境的视频流，因此它提出了对长形视频的时间基础的需求，这导致了两个主要挑战：（1）长视频长度使得很难处理整个视频而不减少样本速率并导致高计算负担； （2）随着候选时间的增加数量，准确的多模式对准更具挑战性。为了应对这些挑战，我们提出了一个有效的以窗户为中心的粗略对齐框架，它可以灵活地处理具有较高推理速度的长格式视频输入，并通过我们的新颖的Choce-Fine Muly-Fine增强了时间基础模态对齐框架。具体来说，我们通过滑动窗口方法将长视频将长视频切成候选窗口。 Cone（1）以窗户为中心，通过对比度学习和通过对NL查询相关的候选窗口进行过滤来学习窗口间的（粗粒）语义差异，并且（2）执行内部（罚款） - 使用强大的对比视力文本预训练模型的强大多模式对齐能力对候选力矩进行排名。长期视频的两个大规模VTG基准测试的广泛实验始终显示出可观的性能增长（MAD的3.13％至6.87％，从10.46％到EGO4D-NLQ上的10.46％至13.46％），并且Cone在两个数据集上都可以达到SOTA结果。分析揭示了组件的有效性和长期视频接地的效率较高，因为我们的系统在EGO4D-NLQ上提高了2倍的推理速度，而在MAD上提高了15倍的速度，同时保持了锥体的SOTA性能。

跨模式表示学习已成为弥合文本和视觉数据之间语义差距的新常态。但是，在连续的潜在空间中学习模态不可知表示通常被视为黑盒数据驱动的训练过程。众所周知，表示学习的有效性在很大程度上取决于培训数据的质量和规模。对于视频表示学习，拥有一组完整的标签来注释全部视频内容进行培训，即使不是不可能，也很难。这些问题，即黑盒培训和数据集偏见，由于无法解释和无法预测的结果，代表学习实际上具有挑战性地用于视频理解。在本文中，我们提出了两个新颖的培训目标，即可能性和不可能的功能，以在嵌入背后的语义上展开语义，同时解决训练中的标签稀疏问题。可能性训练旨在解释培训标签以外的嵌入语义，而不可能的培训利用了正规化的先验知识，以确保语义上的一致性解释。通过这两个培训目标，提出了一个新的编码器 - 模型网络，该网络将学习可解释的跨模式表示形式，用于临时视频搜索。关于TrecVID和MSR-VTT数据集的广泛实验表明，所提出的网络的表现优于几个最新的检索模型，具有统计学意义的性能差。

Nowadays, time-stamped web documents related to a general news query floods spread throughout the Internet, and timeline summarization targets concisely summarizing the evolution trajectory of events along the timeline. Unlike traditional document summarization, timeline summarization needs to model the time series information of the input events and summarize important events in chronological order. To tackle this challenge, in this paper, we propose a Unified Timeline Summarizer (UTS) that can generate abstractive and extractive timeline summaries in time order. Concretely, in the encoder part, we propose a graph-based event encoder that relates multiple events according to their content dependency and learns a global representation of each event. In the decoder part, to ensure the chronological order of the abstractive summary, we propose to extract the feature of event-level attention in its generation process with sequential information remained and use it to simulate the evolutionary attention of the ground truth summary. The event-level attention can also be used to assist in extracting summary, where the extracted summary also comes in time sequence. We augment the previous Chinese large-scale timeline summarization dataset and collect a new English timeline dataset. Extensive experiments conducted on these datasets and on the out-of-domain Timeline 17 dataset show that UTS achieves state-of-the-art performance in terms of both automatic and human evaluations.

Brain midline shift (MLS) is one of the most critical factors to be considered for clinical diagnosis and treatment decision-making for intracranial hemorrhage. Existing computational methods on MLS quantification not only require intensive labeling in millimeter-level measurement but also suffer from poor performance due to their dependence on specific landmarks or simplified anatomical assumptions. In this paper, we propose a novel semi-supervised framework to accurately measure the scale of MLS from head CT scans. We formulate the MLS measurement task as a deformation estimation problem and solve it using a few MLS slices with sparse labels. Meanwhile, with the help of diffusion models, we are able to use a great number of unlabeled MLS data and 2793 non-MLS cases for representation learning and regularization. The extracted representation reflects how the image is different from a non-MLS image and regularization serves an important role in the sparse-to-dense refinement of the deformation field. Our experiment on a real clinical brain hemorrhage dataset has achieved state-of-the-art performance and can generate interpretable deformation fields.

Adversarial imitation learning (AIL) has become a popular alternative to supervised imitation learning that reduces the distribution shift suffered by the latter. However, AIL requires effective exploration during an online reinforcement learning phase. In this work, we show that the standard, naive approach to exploration can manifest as a suboptimal local maximum if a policy learned with AIL sufficiently matches the expert distribution without fully learning the desired task. This can be particularly catastrophic for manipulation tasks, where the difference between an expert and a non-expert state-action pair is often subtle. We present Learning from Guided Play (LfGP), a framework in which we leverage expert demonstrations of multiple exploratory, auxiliary tasks in addition to a main task. The addition of these auxiliary tasks forces the agent to explore states and actions that standard AIL may learn to ignore. Additionally, this particular formulation allows for the reusability of expert data between main tasks. Our experimental results in a challenging multitask robotic manipulation domain indicate that LfGP significantly outperforms both AIL and behaviour cloning, while also being more expert sample efficient than these baselines. To explain this performance gap, we provide further analysis of a toy problem that highlights the coupling between a local maximum and poor exploration, and also visualize the differences between the learned models from AIL and LfGP.

In this work, we introduce a hypergraph representation learning framework called Hypergraph Neural Networks (HNN) that jointly learns hyperedge embeddings along with a set of hyperedge-dependent embeddings for each node in the hypergraph. HNN derives multiple embeddings per node in the hypergraph where each embedding for a node is dependent on a specific hyperedge of that node. Notably, HNN is accurate, data-efficient, flexible with many interchangeable components, and useful for a wide range of hypergraph learning tasks. We evaluate the effectiveness of the HNN framework for hyperedge prediction and hypergraph node classification. We find that HNN achieves an overall mean gain of 7.72% and 11.37% across all baseline models and graphs for hyperedge prediction and hypergraph node classification, respectively.

Neural fields, also known as coordinate-based or implicit neural representations, have shown a remarkable capability of representing, generating, and manipulating various forms of signals. For video representations, however, mapping pixel-wise coordinates to RGB colors has shown relatively low compression performance and slow convergence and inference speed. Frame-wise video representation, which maps a temporal coordinate to its entire frame, has recently emerged as an alternative method to represent videos, improving compression rates and encoding speed. While promising, it has still failed to reach the performance of state-of-the-art video compression algorithms. In this work, we propose FFNeRV, a novel method for incorporating flow information into frame-wise representations to exploit the temporal redundancy across the frames in videos inspired by the standard video codecs. Furthermore, we introduce a fully convolutional architecture, enabled by one-dimensional temporal grids, improving the continuity of spatial features. Experimental results show that FFNeRV yields the best performance for video compression and frame interpolation among the methods using frame-wise representations or neural fields. To reduce the model size even further, we devise a more compact convolutional architecture using the group and pointwise convolutions. With model compression techniques, including quantization-aware training and entropy coding, FFNeRV outperforms widely-used standard video codecs (H.264 and HEVC) and performs on par with state-of-the-art video compression algorithms.

Learning fair graph representations for downstream applications is becoming increasingly important, but existing work has mostly focused on improving fairness at the global level by either modifying the graph structure or objective function without taking into account the local neighborhood of a node. In this work, we formally introduce the notion of neighborhood fairness and develop a computational framework for learning such locally fair embeddings. We argue that the notion of neighborhood fairness is more appropriate since GNN-based models operate at the local neighborhood level of a node. Our neighborhood fairness framework has two main components that are flexible for learning fair graph representations from arbitrary data: the first aims to construct fair neighborhoods for any arbitrary node in a graph and the second enables adaption of these fair neighborhoods to better capture certain application or data-dependent constraints, such as allowing neighborhoods to be more biased towards certain attributes or neighbors in the graph.Furthermore, while link prediction has been extensively studied, we are the first to investigate the graph representation learning task of fair link classification. We demonstrate the effectiveness of the proposed neighborhood fairness framework for a variety of graph machine learning tasks including fair link prediction, link classification, and learning fair graph embeddings. Notably, our approach achieves not only better fairness but also increases the accuracy in the majority of cases across a wide variety of graphs, problem settings, and metrics.

Quantum many-body problems are some of the most challenging problems in science and are central to demystifying some exotic quantum phenomena, e.g., high-temperature superconductors. The combination of neural networks (NN) for representing quantum states, coupled with the Variational Monte Carlo (VMC) algorithm, has been shown to be a promising method for solving such problems. However, the run-time of this approach scales quadratically with the number of simulated particles, constraining the practically usable NN to - in machine learning terms - minuscule sizes (<10M parameters). Considering the many breakthroughs brought by extreme NN in the +1B parameters scale to other domains, lifting this constraint could significantly expand the set of quantum systems we can accurately simulate on classical computers, both in size and complexity. We propose a NN architecture called Vector-Quantized Neural Quantum States (VQ-NQS) that utilizes vector-quantization techniques to leverage redundancies in the local-energy calculations of the VMC algorithm - the source of the quadratic scaling. In our preliminary experiments, we demonstrate VQ-NQS ability to reproduce the ground state of the 2D Heisenberg model across various system sizes, while reporting a significant reduction of about ${\times}10$ in the number of FLOPs in the local-energy calculation.

Current language models are considered to have sub-human capabilities at natural language tasks like question-answering or writing code. However, language models are not trained to perform well at these tasks, they are trained to accurately predict the next token given previous tokes in tokenized text. It is not clear whether language models are better or worse than humans at next token prediction. To try to answer this question, we performed two distinct experiments to directly compare humans and language models on this front: one measuring top-1 accuracy and the other measuring perplexity. In both experiments, we find humans to be consistently \emph{worse} than even relatively small language models like GPT3-Ada at next-token prediction.