Zobrazeno 1 - 10
of 6 302
pro vyhledávání: '"Khosla, P. P."'
We present RELOCATE, a simple training-free baseline designed to perform the challenging task of visual query localization in long videos. To eliminate the need for task-specific training and efficiently handle long videos, RELOCATE leverages a regio
Externí odkaz:
http://arxiv.org/abs/2412.01826
Neuroscience and artificial intelligence (AI) both face the challenge of interpreting high-dimensional neural data, where the comparative analysis of such data is crucial for revealing shared mechanisms and differences between these complex systems.
Externí odkaz:
http://arxiv.org/abs/2411.14633
Autor:
Zhao, Tianqi, Khosla, Megha
Graph neural networks (GNNs) have emerged as powerful models for learning representations of graph data showing state of the art results in various tasks. Nevertheless, the superiority of these methods is usually supported by either evaluating their
Externí odkaz:
http://arxiv.org/abs/2411.14094
Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining graph model de
Externí odkaz:
http://arxiv.org/abs/2410.21043
Over the past decade, predictive modeling of neural responses in the primate visual system has advanced significantly, largely driven by various DNN approaches. These include models optimized directly for visual recognition, cross-modal alignment thr
Externí odkaz:
http://arxiv.org/abs/2410.14031
Publikováno v:
Published in Data-centric Machine Learning Research Worshop @ ICML 2024
Graph Neural Networks (GNNs) have achieved state-of-the-art results in node classification tasks. However, most improvements are in multi-class classification, with less focus on the cases where each node could have multiple labels. The first challen
Externí odkaz:
http://arxiv.org/abs/2406.12439
In recent years, continual learning (CL) techniques have made significant progress in learning from streaming data while preserving knowledge across sequential tasks, particularly in the realm of euclidean data. To foster fair evaluation and recogniz
Externí odkaz:
http://arxiv.org/abs/2406.01229
Pre-trained deep learning (DL) models are increasingly accessible in public repositories, i.e., model zoos. Given a new prediction task, finding the best model to fine-tune can be computationally intensive and costly, especially when the number of pr
Externí odkaz:
http://arxiv.org/abs/2404.03988
Autor:
Lu, Jiasen, Clark, Christopher, Lee, Sangho, Zhang, Zichen, Khosla, Savya, Marten, Ryan, Hoiem, Derek, Kembhavi, Aniruddha
We present Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating image, text, audio, and action. To unify different modalities, we tokenize inputs and outputs -- images, text, audio, action, bounding
Externí odkaz:
http://arxiv.org/abs/2312.17172
Autor:
Kohli, Guneet Singh, Parida, Shantipriya, Sekhar, Sambit, Saha, Samirit, Nair, Nipun B, Agarwal, Parul, Khosla, Sonal, Patiyal, Kusumlata, Dhal, Debasish
Building LLMs for languages other than English is in great demand due to the unavailability and performance of multilingual LLMs, such as understanding the local context. The problem is critical for low-resource languages due to the need for instruct
Externí odkaz:
http://arxiv.org/abs/2312.12624