相关论文: Latent Video Prediction Learns Better World Models

The video generation task can be formulated as a prediction of future video frames given some past frames. Recent generative models for videos face the problem of high computational requirements. Some models require up to 512 Tensor…

World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However, current world model research is often dominated by three partially…

Predicting high dimensional video sequences is a curiously difficult problem. The number of possible futures for a given video sequence grows exponentially over time due to uncertainty. This is especially evident when trying to predict…

Accurate face detection and facial landmark localization are crucial to any face recognition system. We present a series of three single-stage RCNNs with different sized backbones (MobileNetV2-25, MobileNetV2-100, and ResNet101) and a…

World models have become crucial for autonomous driving, as they learn how scenarios evolve over time to address the long-tail challenges of the real world. However, current approaches relegate world models to limited roles: they operate…

Generating fine-grained video descriptions is a fundamental challenge in video understanding. In this work, we introduce Tarsier, a family of large-scale video-language models designed to generate high-quality video descriptions. Tarsier…

Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model…

Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. World models have emerged as a linchpin…

Diffusion models have emerged as a powerful paradigm in video synthesis tasks including prediction, generation, and interpolation. Due to the limitation of the computational budget, existing methods usually implement conditional diffusion…

This paper introduces a Video Quality Assessment (VQA) problem that has received little attention in the literature, called the latent resolution prediction problem. The problem arises when images or videos are upscaled from their native…

Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they…

Continual learning for video--language understanding is increasingly important as models face non-stationary data, domains, and query styles, yet prevailing solutions blur what should stay stable versus what should adapt, rely on static…

End-to-end autonomous driving increasingly leverages self-supervised video pretraining to learn transferable planning representations. However, pretraining video world models for scene understanding has so far brought only limited…

Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use, we train them to…

The dissertation presents four key contributions toward fairness and robustness in vision learning. First, to address the problem of large-scale data requirements, the dissertation presents a novel Fairness Domain Adaptation approach…

Video representation learning is an increasingly important topic in machine learning research. We present Video JEPA with Variance-Covariance Regularization (VJ-VCR): a joint-embedding predictive architecture for self-supervised video…

Given the three dimensional complexity of a video signal, training a robust and diverse GAN based video generative model is onerous due to large stochasticity involved in data space. Learning disentangled representations of the data help to…

Large Vision Language Models (LVLMs) excel in various vision-language tasks. Yet, their robustness to visual variations in position, scale, orientation, and context that objects in natural scenes inevitably exhibit due to changes in…

Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, which underutilizes their powerful scene understanding and…

This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for…