Zobrazeno 1 - 10
of 5 110
pro vyhledávání: '"A. Ajinkya"'
Autor:
Deng, Shijian, Zhao, Wentian, Li, Yu-Jhe, Wan, Kun, Miranda, Daniel, Kale, Ajinkya, Tian, Yapeng
Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and potential pitfa
Externí odkaz:
http://arxiv.org/abs/2411.17760
The goal of this paper is to improve (upcycle) an existing large language model without the prohibitive requirements of continued pre-training of the full-model. The idea is to split the pre-training data into semantically relevant groups and train a
Externí odkaz:
http://arxiv.org/abs/2410.09687
Autor:
Zhang, Zeliang, Pham, Phu, Zhao, Wentian, Wan, Kun, Li, Yu-Jhe, Zhou, Jianing, Miranda, Daniel, Kale, Ajinkya, Xu, Chenliang
By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks, leveraging the robust architectures of Large Language Models (LLMs).
Externí odkaz:
http://arxiv.org/abs/2410.06169
Autor:
Sridhara, Shashank N., Pavez, Eduardo, Jayawant, Ajinkya, Ortega, Antonio, Watanabe, Ryosuke, Nonaka, Keisuke
3D Point clouds (PCs) are commonly used to represent 3D scenes. They can have millions of points, making subsequent downstream tasks such as compression and streaming computationally expensive. PC sampling (selecting a subset of points) can be used t
Externí odkaz:
http://arxiv.org/abs/2410.01027
Autor:
Murtunge, Yamuna, Punjal, Ajinkya, Puranik, Ruturaj, Pandey, Utkarsh, Kulkarni, S. B., Prabhu, S. S.
We employed sodium mesitylene sulfonate crystals to investigate angle-dependent phonon resonance and thickness-dependent splitting in THz time-domain polarimetry. This crystal possesses a C2 space group, leading to a repetition pattern after 180deg r
Externí odkaz:
http://arxiv.org/abs/2409.12497
Contrary to on-road autonomous navigation, off-road autonomy is complicated by various factors ranging from sensing challenges to terrain variability. In such a milieu, data-driven approaches have been commonly employed to capture intricate vehicle-e
Externí odkaz:
http://arxiv.org/abs/2409.10347
Autor:
Gibson, Jason B., Janicki, Tesia D., Hire, Ajinkya C., Bishop, Chris, Lane, J. Matthew D., Hennig, Richard G.
Machine-learned interatomic potentials (MLIPs) are becoming an essential tool in materials modeling. However, optimizing the generation of training data used to parameterize the MLIPs remains a significant challenge. This is because MLIPs can fail wh
Externí odkaz:
http://arxiv.org/abs/2409.07610
While recent zero-shot multispeaker text-to-speech (TTS) models achieve impressive results, they typically rely on extensive transcribed speech datasets from numerous speakers and intricate training pipelines. Meanwhile, self-supervised learning (SSL
Externí odkaz:
http://arxiv.org/abs/2408.10771
Autor:
Sharma, Anantha, Deshmukh, Ajinkya
With the increasing demand for data sharing across platforms and organizations, ensuring the privacy and security of sensitive information has become a critical challenge. This paper introduces "TableGuard". An innovative approach to data obfuscation
Externí odkaz:
http://arxiv.org/abs/2408.07045
Autor:
Drolet, Michael, Stepputtis, Simon, Kailas, Siva, Jain, Ajinkya, Peters, Jan, Schaal, Stefan, Amor, Heni Ben
Amidst the wide popularity of imitation learning algorithms in robotics, their properties regarding hyperparameter sensitivity, ease of training, data efficiency, and performance have not been well-studied in high-precision industry-inspired environm
Externí odkaz:
http://arxiv.org/abs/2408.06536