Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Tsai, Alicia Y."'
Autor:
Tsai, Alicia Y., Kraft, Adam, Jin, Long, Cai, Chenwei, Hosseini, Anahita, Xu, Taibai, Zhang, Zemin, Hong, Lichan, Chi, Ed H., Yi, Xinyang
Recent advancements have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. While tasks like arithmetic reasoning involve clear, definitive answers and l
Externí odkaz:
http://arxiv.org/abs/2408.00802
In this paper, we investigate the extrapolation capabilities of implicit deep learning models in handling unobserved data, where traditional deep neural networks may falter. Implicit models, distinguished by their adaptability in layer depth and inco
Externí odkaz:
http://arxiv.org/abs/2407.14430
Implicit models are a general class of learning models that forgo the hierarchical layer structure typical in neural networks and instead define the internal states based on an ``equilibrium'' equation, offering competitive performance and reduced me
Externí odkaz:
http://arxiv.org/abs/2209.09389
Autor:
Tsai, Alicia Y., Ghaoui, Laurent El
We address the problem of unsupervised extractive document summarization, especially for long documents. We model the unsupervised problem as a sparse auto-regression one and approximate the resulting combinatorial problem via a convex, norm-constrai
Externí odkaz:
http://arxiv.org/abs/2208.09454
Autor:
Tsai, Alicia Y., Oraby, Shereen, Perera, Vittorio, Kao, Jiun-Yu, Du, Yuheng, Narayan-Chen, Anjali, Chung, Tagyoung, Hakkani-Tur, Dilek
Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to simultaneously
Externí odkaz:
http://arxiv.org/abs/2109.12211
Autor:
Tsai, Alicia Y., Gunay, Selim, Hwang, Minjune, Zhai, Pengyuan, Li, Chenglong, Ghaoui, Laurent El, Mosalam, Khalid M.
Post-hazard reconnaissance for natural disasters (e.g., earthquakes) is important for understanding the performance of the built environment, speeding up the recovery, enhancing resilience and making informed decisions related to current and future h
Externí odkaz:
http://arxiv.org/abs/2011.13087
Implicit deep learning prediction rules generalize the recursive rules of feedforward neural networks. Such rules are based on the solution of a fixed-point equation involving a single vector of hidden features, which is thus only implicitly defined.
Externí odkaz:
http://arxiv.org/abs/1908.06315