Zobrazeno 1 - 10
of 118 380
pro vyhledávání: '"Computer Science - Computation and Language"'
Autor:
Lambert, Nathan, Morrison, Jacob, Pyatkin, Valentina, Huang, Shengyi, Ivison, Hamish, Brahman, Faeze, Miranda, Lester James V., Liu, Alisa, Dziri, Nouha, Lyu, Shane, Gu, Yuling, Malik, Saumya, Graf, Victoria, Hwang, Jena D., Yang, Jiangjiang, Bras, Ronan Le, Tafjord, Oyvind, Wilhelm, Chris, Soldaini, Luca, Smith, Noah A., Wang, Yizhong, Dasigi, Pradeep, Hajishirzi, Hannaneh
Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag behind proprietary ones. The underlying training data and recipes for
Externí odkaz:
http://arxiv.org/abs/2411.15124
Generative large language models (LLMs), which create text without direct correspondence to truth value, are widely understood to resemble the uses of language described in Frankfurt's popular monograph On Bullshit. In this paper, we offer a rigorous
Externí odkaz:
http://arxiv.org/abs/2411.15129
Autor:
Zhang, Xiaoman, Zhou, Hong-Yu, Yang, Xiaoli, Banerjee, Oishi, Acosta, Julián N., Miller, Josh, Huang, Ouwen, Rajpurkar, Pranav
AI-driven models have demonstrated significant potential in automating radiology report generation for chest X-rays. However, there is no standardized benchmark for objectively evaluating their performance. To address this, we present ReXrank, https:
Externí odkaz:
http://arxiv.org/abs/2411.15122
Autor:
Ramesh, Samarth N, Zhao, Zhixue
As text-to-image models grow increasingly powerful and complex, their burgeoning size presents a significant obstacle to widespread adoption, especially on resource-constrained devices. This paper presents a pioneering study on post-training pruning
Externí odkaz:
http://arxiv.org/abs/2411.15113
VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement
Recent text-to-video (T2V) diffusion models have demonstrated impressive generation capabilities across various domains. However, these models often generate videos that have misalignments with text prompts, especially when the prompts describe compl
Externí odkaz:
http://arxiv.org/abs/2411.15115
Autor:
Dong, Yixin, Ruan, Charlie F., Cai, Yaxing, Lai, Ruihang, Xu, Ziyi, Zhao, Yilong, Chen, Tianqi
The applications of LLM Agents are becoming increasingly complex and diverse, leading to a high demand for structured outputs that can be parsed into code, structured function calls, and embodied agent commands. These developments bring significant d
Externí odkaz:
http://arxiv.org/abs/2411.15100
Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time. Yet the standard pretraining paradigm (contrastive learning on large amounts of image-text data) does not explicitly encourage representations
Externí odkaz:
http://arxiv.org/abs/2411.15099
Recent works on Generalized Referring Expression Segmentation (GRES) struggle with handling complex expressions referring to multiple distinct objects. This is because these methods typically employ an end-to-end foreground-background segmentation an
Externí odkaz:
http://arxiv.org/abs/2411.15087
Autor:
Griebel, Sarah, Cohen, Becca, Li, Lucian, Park, Jaihyun, Liu, Jiayu, Perkins, Jana, Underwood, Ted
Measures of textual similarity and divergence are increasingly used to study cultural change. But which measures align, in practice, with social evidence about change? We apply three different representations of text (topic models, document embedding
Externí odkaz:
http://arxiv.org/abs/2411.15068
Autor:
Barriere, Valentin
Publikováno v:
Bits de Ciencias 26 (2024), 02-13
Deep Learning models tend to learn correlations of patterns on huge datasets. The bigger these systems are, the more complex are the phenomena they can detect, and the more data they need for this. The use of Artificial Intelligence (AI) is becoming
Externí odkaz:
http://arxiv.org/abs/2411.15051