Zobrazeno 1 - 10
of 8 425
pro vyhledávání: '"Savarese A"'
Autor:
Awadalla, Anas, Xue, Le, Shu, Manli, Yan, An, Wang, Jun, Purushwalkam, Senthil, Shen, Sheng, Lee, Hannah, Lo, Oscar, Park, Jae Sung, Guha, Etash, Savarese, Silvio, Schmidt, Ludwig, Choi, Yejin, Xiong, Caiming, Xu, Ran
We introduce BLIP3-KALE, a dataset of 218 million image-text pairs that bridges the gap between descriptive synthetic captions and factual web-scale alt-text. KALE augments synthetic dense image captions with web-scale alt-text to generate factually
Externí odkaz:
http://arxiv.org/abs/2411.07461
Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with capabiliti
Externí odkaz:
http://arxiv.org/abs/2411.04329
Autor:
Chen, Haolin, Feng, Yihao, Liu, Zuxin, Yao, Weiran, Prabhakar, Akshara, Heinecke, Shelby, Ho, Ricky, Mui, Phil, Savarese, Silvio, Xiong, Caiming, Wang, Huan
Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time, optimizing
Externí odkaz:
http://arxiv.org/abs/2411.04282
Autor:
Huang, Kung-Hsiang, Prabhakar, Akshara, Dhawan, Sidharth, Mao, Yixin, Wang, Huan, Savarese, Silvio, Xiong, Caiming, Laban, Philippe, Wu, Chien-Sheng
Customer Relationship Management (CRM) systems are vital for modern enterprises, providing a foundation for managing customer interactions and data. Integrating AI agents into CRM systems can automate routine processes and enhance personalized servic
Externí odkaz:
http://arxiv.org/abs/2411.02305
Autor:
Agnes, P., Berger, Q., Bomben, M., Campestrini, M., Caravati, M., Cortez, A. F. V., Franco, D., Galbiati, C., Giovanetti, G. K., Hessel, T., Hidalgo, C., Hoceini, S., Houriez, C., Kunzé, P., Machts, J., Nikoloudaki, E., Pailot, D., Pantic, E., Savarese, C., Stringari, P., Sung, A., Lavina, L. Scotto, Simon, J-M, de Souza, H. Vieira, Wada, M., Wang, Y., Zhang, Y.
The Xenon-Argon Technology (X-ArT) collaboration presents a study on the dynamics of pure and xenon-doped liquid argon (LAr) scintillation. Using two types of silicon photomultipliers sensitive to different wavelength ranges, we identify a long-lived
Externí odkaz:
http://arxiv.org/abs/2410.22863
Autor:
Ginart, Antonio A., Kodali, Naveen, Lee, Jason, Xiong, Caiming, Savarese, Silvio, Emmons, John
While frontier large language models (LLMs) are capable tool-using agents, current AI systems still operate in a strict turn-based fashion, oblivious to passage of time. This synchronous design forces user queries and tool-use to occur sequentially,
Externí odkaz:
http://arxiv.org/abs/2410.21620
Autor:
Liu, Zhiwei, Yao, Weiran, Zhang, Jianguo, Murthy, Rithesh, Yang, Liangwei, Liu, Zuxin, Lan, Tian, Zhu, Ming, Tan, Juntao, Kokane, Shirley, Hoang, Thai, Niebles, Juan Carlos, Heinecke, Shelby, Wang, Huan, Savarese, Silvio, Xiong, Caiming
We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data. Central to our approach is the use of text gradients from a reflection and optimization engine to de
Externí odkaz:
http://arxiv.org/abs/2410.18528
Autor:
Ryoo, Michael S., Zhou, Honglu, Kendre, Shrikant, Qin, Can, Xue, Le, Shu, Manli, Savarese, Silvio, Xu, Ran, Xiong, Caiming, Niebles, Juan Carlos
We present xGen-MM-Vid (BLIP-3-Video): a multimodal language model for videos, particularly designed to efficiently capture temporal information over multiple frames. BLIP-3-Video takes advantage of the 'temporal encoder' in addition to the conventio
Externí odkaz:
http://arxiv.org/abs/2410.16267
Autor:
Liu, Xu, Liu, Juncheng, Woo, Gerald, Aksu, Taha, Liang, Yuxuan, Zimmermann, Roger, Liu, Chenghao, Savarese, Silvio, Xiong, Caiming, Sahoo, Doyen
Time series foundation models have demonstrated impressive performance as zero-shot forecasters. However, achieving effectively unified training on time series remains an open challenge. Existing approaches introduce some level of model specializatio
Externí odkaz:
http://arxiv.org/abs/2410.10469
Autor:
Aksu, Taha, Woo, Gerald, Liu, Juncheng, Liu, Xu, Liu, Chenghao, Savarese, Silvio, Xiong, Caiming, Sahoo, Doyen
Time series foundation models excel in zero-shot forecasting, handling diverse tasks without explicit training. However, the advancement of these models has been hindered by the lack of comprehensive benchmarks. To address this gap, we introduce the
Externí odkaz:
http://arxiv.org/abs/2410.10393