Current datasets for long-form video understanding often fall short of providing genuine long-form comprehension challenges, as many tasks derived from these datasets can be successfully tackled by analyzing just one or a few random frames from a video. To address this issue, we present a novel dataset and benchmark, CinePile, specifically designed for authentic long-form video understanding. This paper details our innovative approach for creating a question-answer dataset, utilizing advanced LLMs with human-in-the-loop and building upon human-generated raw data. Our comprehensive dataset comprises 305,000 multiple-choice questions (MCQs), covering various visual and multimodal aspects, including temporal comprehension, understanding human-object interactions, and reasoning about events or actions within a scene. Additionally, we evaluate recent video-centric LLMs, both open-source and proprietary, on the test split of our dataset. The findings reveal that even state-of-the-art video-centric LLMs significantly lag behind human performance in these tasks, highlighting the complexity and challenge inherent in video understanding.

The Kohn-Sham equations underlie many important applications such as the discovery of new catalysts. Recent machine learning work on catalyst modeling has focused on prediction of the energy, but has so far not yet demonstrated significant out-of-distribution generalization. Here we investigate another approach based on the pointwise learning of the Kohn-Sham charge-density. On a new dataset of bulk catalysts with charge densities, we show density models can generalize to new structures with combinations of elements not seen at train time, a form of combinatorial generalization. We show that over 80% of binary and ternary test cases achieve faster convergence than standard baselines in Density Functional Theory, amounting to an average reduction of 13% in the number of iterations required to reach convergence, which may be of independent interest. Our results suggest that density learning is a viable alternative, trading greater inference costs for a step towards combinatorial generalization, a key property for applications.

Despite tremendous progress in generating high-quality images using diffusion models, synthesizing a sequence of animated frames that are both photorealistic and temporally coherent is still in its infancy. While off-the-shelf billion-scale datasets for image generation are available, collecting similar video data of the same scale is still challenging. Also, training a video diffusion model is computationally much more expensive than its image counterpart. In this work, we explore finetuning a pretrained image diffusion model with video data as a practical solution for the video synthesis task. We find that naively extending the image noise prior to video noise prior in video diffusion leads to sub-optimal performance. Our carefully designed video noise prior leads to substantially better performance. Extensive experimental validation shows that our model, Preserve Your Own Correlation (PYoCo), attains SOTA zero-shot text-to-video results on the UCF-101 and MSR-VTT benchmarks. It also achieves SOTA video generation quality on the small-scale UCF-101 benchmark with a $10\times$ smaller model using significantly less computation than the prior art.

A core component of the recent success of self-supervised learning is cropping data augmentation, which selects sub-regions of an image to be used as positive views in the self-supervised loss. The underlying assumption is that randomly cropped and resized regions of a given image share information about the objects of interest, which the learned representation will capture. This assumption is mostly satisfied in datasets such as ImageNet where there is a large, centered object, which is highly likely to be present in random crops of the full image. However, in other datasets such as OpenImages or COCO, which are more representative of real world uncurated data, there are typically multiple small objects in an image. In this work, we show that self-supervised learning based on the usual random cropping performs poorly on such datasets. We propose replacing one or both of the random crops with crops obtained from an object proposal algorithm. This encourages the model to learn both object and scene level semantic representations. Using this approach, which we call object-aware cropping, results in significant improvements over scene cropping on classification and object detection benchmarks. For example, on OpenImages, our approach achieves an improvement of 8.8% mAP over random scene-level cropping using MoCo-v2 based pre-training. We also show significant improvements on COCO and PASCAL-VOC object detection and segmentation tasks over the state-of-the-art self-supervised learning approaches. Our approach is efficient, simple and general, and can be used in most existing contrastive and non-contrastive self-supervised learning frameworks.

Recent literature has shown that features obtained from supervised training of CNNs may over-emphasize texture rather than encoding high-level information. In self-supervised learning in particular, texture as a low-level cue may provide shortcuts that prevent the network from learning higher level representations. To address these problems we propose to use classic methods based on anisotropic diffusion to augment training using images with suppressed texture. This simple method helps retain important edge information and suppress texture at the same time. We empirically show that our method achieves state-of-the-art results on object detection and image classification with eight diverse datasets in either supervised or self-supervised learning tasks such as MoCoV2 and Jigsaw. Our method is particularly effective for transfer learning tasks and we observed improved performance on five standard transfer learning datasets. The large improvements (up to 11.49\%) on the Sketch-ImageNet dataset, DTD dataset and additional visual analyses with saliency maps suggest that our approach helps in learning better representations that better transfer.

Although self-/un-supervised methods have led to rapid progress in visual representation learning, these methods generally treat objects and scenes using the same lens. In this paper, we focus on learning representations for objects and scenes that preserve the structure among them. Motivated by the observation that visually similar objects are close in the representation space, we argue that the scenes and objects should instead follow a hierarchical structure based on their compositionality. To exploit such a structure, we propose a contrastive learning framework where a Euclidean loss is used to learn object representations and a hyperbolic loss is used to encourage representations of scenes to lie close to representations of their constituent objects in a hyperbolic space. This novel hyperbolic objective encourages the scene-object hypernymy among the representations by optimizing the magnitude of their norms. We show that when pretraining on the COCO and OpenImages datasets, the hyperbolic loss improves downstream performance of several baselines across multiple datasets and tasks, including image classification, object detection, and semantic segmentation. We also show that the properties of the learned representations allow us to solve various vision tasks that involve the interaction between scenes and objects in a zero-shot fashion. Our code can be found at \url{https://github.com/shlokk/HCL/tree/main/HCL}.

We introduce CAN, a simple, efficient and scalable method for self-supervised learning of visual representations. Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise prediction approach used in diffusion models. The learning mechanisms are complementary to one another: contrastive learning shapes the embedding space across a batch of image samples; masked autoencoders focus on reconstruction of the low-frequency spatial correlations in a single image sample; and noise prediction encourages the reconstruction of the high-frequency components of an image. The combined approach results in a robust, scalable and simple-to-implement algorithm. The training process is symmetric, with 50% of patches in both views being masked at random, yielding a considerable efficiency improvement over prior contrastive learning methods. Extensive empirical studies demonstrate that CAN achieves strong downstream performance under both linear and finetuning evaluations on transfer learning and robustness tasks. CAN outperforms MAE and SimCLR when pre-training on ImageNet, but is especially useful for pre-training on larger uncurated datasets such as JFT-300M: for linear probe on ImageNet, CAN achieves 75.4% compared to 73.4% for SimCLR and 64.1% for MAE. The finetuned performance on ImageNet of our ViT-L model is 86.1%, compared to 85.5% for SimCLR, and 85.4% for MAE. The overall FLOPs load of SimCLR is 70% higher than CAN for ViT-L models.

AI algorithms that identify maneuvers from trajectory data could play an important role in improving flight safety and pilot training. AI challenges allow diverse teams to work together to solve hard problems and are an effective tool for developing AI solutions. AI challenges are also a key driver of AI computational requirements. The Maneuver Identification Challenge hosted at maneuver-id.mit.edu provides thousands of trajectories collected from pilots practicing in flight simulators, descriptions of maneuvers, and examples of these maneuvers performed by experienced pilots. Each trajectory consists of positions, velocities, and aircraft orientations normalized to a common coordinate system. Construction of the data set required significant data architecture to transform flight simulator logs into AI ready data, which included using a supercomputer for deduplication and data conditioning. There are three proposed challenges. The first challenge is separating physically plausible (good) trajectories from unfeasible (bad) trajectories. Human labeled good and bad trajectories are provided to aid in this task. Subsequent challenges are to label trajectories with their intended maneuvers and to assess the quality of those maneuvers.

Recent theoretical work has shown that massively overparameterized neural networks are equivalent to kernel regressors that use Neural Tangent Kernels (NTKs). Experiments show that these kernel methods perform similarly to real neural networks. Here we show that NTK for fully connected networks with ReLU activation is closely related to the standard Laplace kernel. We show theoretically that for normalized data on the hypersphere both kernels have the same eigenfunctions and their eigenvalues decay polynomially at the same rate, implying that their Reproducing Kernel Hilbert Spaces (RKHS) include the same sets of functions. This means that both kernels give rise to classes of functions with the same smoothness properties. The two kernels differ for data off the hypersphere, but experiments indicate that when data is properly normalized these differences are not significant. Finally, we provide experiments on real data comparing NTK and the Laplace kernel, along with a larger class of γ-exponential kernels. We show that these perform almost identically. Our results suggest that much insight about neural networks can be obtained from analysis of the well-known Laplace kernel, which has a simple closed form.

We study the relationship between the speed at which a neural network learns a function and the frequency of the function. We build on recent results that show that the dynamics of overparameterized neural networks trained with gradient descent can be well approximated by a linear system. When normalized training data is uniformly distributed on a hypersphere, the eigenfunctions of this linear system are spherical harmonic functions. We derive the corresponding eigenvalues for each frequency after introducing a bias term in the model. This bias term had been omitted from the linear network model without significantly affecting previous theoretical results. However, we show theoretically and experimentally that a shallow neural network without bias cannot learn simple, low frequency functions with odd frequencies, in the limit of large amounts of data. Our results enable us to make specific predictions of the time it will take a network with bias to learn functions of varying frequency. These predictions match the behavior of real shallow and deep networks.