Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Vasiljevic, Igor"'
Autor:
Li, Jeffrey, Fang, Alex, Smyrnis, Georgios, Ivgi, Maor, Jordan, Matt, Gadre, Samir, Bansal, Hritik, Guha, Etash, Keh, Sedrick, Arora, Kushal, Garg, Saurabh, Xin, Rui, Muennighoff, Niklas, Heckel, Reinhard, Mercat, Jean, Chen, Mayee, Gururangan, Suchin, Wortsman, Mitchell, Albalak, Alon, Bitton, Yonatan, Nezhurina, Marianna, Abbas, Amro, Hsieh, Cheng-Yu, Ghosh, Dhruba, Gardner, Josh, Kilian, Maciej, Zhang, Hanlin, Shao, Rulin, Pratt, Sarah, Sanyal, Sunny, Ilharco, Gabriel, Daras, Giannis, Marathe, Kalyani, Gokaslan, Aaron, Zhang, Jieyu, Chandu, Khyathi, Nguyen, Thao, Vasiljevic, Igor, Kakade, Sham, Song, Shuran, Sanghavi, Sujay, Faghri, Fartash, Oh, Sewoong, Zettlemoyer, Luke, Lo, Kyle, El-Nouby, Alaaeldin, Pouransari, Hadi, Toshev, Alexander, Wang, Stephanie, Groeneveld, Dirk, Soldaini, Luca, Koh, Pang Wei, Jitsev, Jenia, Kollar, Thomas, Dimakis, Alexandros G., Carmon, Yair, Dave, Achal, Schmidt, Ludwig, Shankar, Vaishaal
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardized corpus of 240T tokens extracted from Common Crawl, effective pretrai
Externí odkaz:
http://arxiv.org/abs/2406.11794
Monocular visual odometry is a key technology in a wide variety of autonomous systems. Relative to traditional feature-based methods, that suffer from failures due to poor lighting, insufficient texture, large motions, etc., recent learning-based SLA
Externí odkaz:
http://arxiv.org/abs/2406.00929
Autor:
Mercat, Jean, Vasiljevic, Igor, Keh, Sedrick, Arora, Kushal, Dave, Achal, Gaidon, Adrien, Kollar, Thomas
Linear transformers have emerged as a subquadratic-time alternative to softmax attention and have garnered significant interest due to their fixed-size recurrent state that lowers inference cost. However, their original formulation suffers from poor
Externí odkaz:
http://arxiv.org/abs/2405.06640
Autor:
Fang, Jiading, Tan, Xiangshan, Lin, Shengjie, Vasiljevic, Igor, Guizilini, Vitor, Mei, Hongyuan, Ambrus, Rares, Shakhnarovich, Gregory, Walter, Matthew R
If robots are to work effectively alongside people, they must be able to interpret natural language references to objects in their 3D environment. Understanding 3D referring expressions is challenging -- it requires the ability to both parse the 3D s
Externí odkaz:
http://arxiv.org/abs/2404.19221
Autor:
Gadre, Samir Yitzhak, Smyrnis, Georgios, Shankar, Vaishaal, Gururangan, Suchin, Wortsman, Mitchell, Shao, Rulin, Mercat, Jean, Fang, Alex, Li, Jeffrey, Keh, Sedrick, Xin, Rui, Nezhurina, Marianna, Vasiljevic, Igor, Jitsev, Jenia, Soldaini, Luca, Dimakis, Alexandros G., Ilharco, Gabriel, Koh, Pang Wei, Song, Shuran, Kollar, Thomas, Carmon, Yair, Dave, Achal, Heckel, Reinhard, Muennighoff, Niklas, Schmidt, Ludwig
Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are ultimatel
Externí odkaz:
http://arxiv.org/abs/2403.08540
Publikováno v:
The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
Autonomous vehicles and robots need to operate over a wide variety of scenarios in order to complete tasks efficiently and safely. Multi-camera self-supervised monocular depth estimation from videos is a promising way to reason about the environment,
Externí odkaz:
http://arxiv.org/abs/2308.02153
Monocular depth estimation is scale-ambiguous, and thus requires scale supervision to produce metric predictions. Even so, the resulting models will be geometry-specific, with learned scales that cannot be directly transferred across domains. Because
Externí odkaz:
http://arxiv.org/abs/2306.17253
Autor:
Fang, Jiading, Lin, Shengjie, Vasiljevic, Igor, Guizilini, Vitor, Ambrus, Rares, Gaidon, Adrien, Shakhnarovich, Gregory, Walter, Matthew R.
A practical benefit of implicit visual representations like Neural Radiance Fields (NeRFs) is their memory efficiency: large scenes can be efficiently stored and shared as small neural nets instead of collections of images. However, operating on thes
Externí odkaz:
http://arxiv.org/abs/2305.13307
Autor:
Guizilini, Vitor, Vasiljevic, Igor, Fang, Jiading, Ambrus, Rares, Zakharov, Sergey, Sitzmann, Vincent, Gaidon, Adrien
Differentiable volumetric rendering is a powerful paradigm for 3D reconstruction and novel view synthesis. However, standard volume rendering approaches struggle with degenerate geometries in the case of limited viewpoint diversity, a common scenario
Externí odkaz:
http://arxiv.org/abs/2304.02797
Autor:
Vasiljevic, Igor
Modern computer vision has moved beyond the domain of internet photo collections and into the physical world, guiding camera-equipped robots and autonomous cars through unstructured environments. To enable these embodied agents to interact with real-
Externí odkaz:
http://arxiv.org/abs/2208.12903