Zobrazeno 1 - 10
of 2 087
pro vyhledávání: '"Doyen, P."'
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
Time series forecasting aids decision-making, especially for stakeholders who rely on accurate predictions, making it very important to understand and explain these models to ensure informed decisions. Traditional explainable AI (XAI) methods, which
Externí odkaz:
http://arxiv.org/abs/2410.14180
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
Hallucinations (i.e., generating plausible but inaccurate content) and laziness (i.e. excessive refusals or defaulting to "I don't know") persist as major challenges in LLM reasoning. Current efforts to reduce hallucinations primarily focus on factua
Externí odkaz:
http://arxiv.org/abs/2410.07627
Autor:
Wang, Lei, Dong, Shan, Xu, Yuhui, Dong, Hanze, Wang, Yalu, Saha, Amrita, Lim, Ee-Peng, Xiong, Caiming, Sahoo, Doyen
Recent large language models (LLMs) have demonstrated versatile capabilities in long-context scenarios. Although some recent benchmarks have been developed to evaluate the long-context capabilities of LLMs, there is a lack of benchmarks evaluating th
Externí odkaz:
http://arxiv.org/abs/2410.04698
Autor:
Xu, Yuhui, Jie, Zhanming, Dong, Hanze, Wang, Lei, Lu, Xudong, Zhou, Aojun, Saha, Amrita, Xiong, Caiming, Sahoo, Doyen
Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant challenges,
Externí odkaz:
http://arxiv.org/abs/2407.21018
Large language models (LLMs) for code are typically trained to align with natural language instructions to closely follow their intentions and requirements. However, in many practical scenarios, it becomes increasingly challenging for these models to
Externí odkaz:
http://arxiv.org/abs/2407.02518
Autor:
Liu, Juncheng, Liu, Chenghao, Woo, Gerald, Wang, Yiwei, Hooi, Bryan, Xiong, Caiming, Sahoo, Doyen
Transformer-based models have emerged as powerful tools for multivariate time series forecasting (MTSF). However, existing Transformer models often fall short of capturing both intricate dependencies across variate and temporal dimensions in MTS data
Externí odkaz:
http://arxiv.org/abs/2406.04975
Stochastic two-player games model systems with an environment that is both adversarial and stochastic. In this paper, we study the expected value of quantitative prefix-independent objectives in stochastic games. We show a generic reduction from the
Externí odkaz:
http://arxiv.org/abs/2405.18048