Výsledky vyhledávání - "Dubey, Kumar"

Report

Linear Transformer Topological Masking with Graph Random Features

Autor: Reid, Isaac, Dubey, Kumar Avinava, Jain, Deepali, Whitney, Will, Ahmed, Amr, Ainslie, Joshua, Bewley, Alex, Jacob, Mithun, Mehta, Aranyak, Rendleman, David, Schenck, Connor, Turner, Richard E., Wagner, René, Weller, Adrian, Choromanski, Krzysztof

When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance. Topological masking, a type of relative position encoding, achieves this by upweighting or downweighting att

Externí odkaz: http://arxiv.org/abs/2410.03462

Zobrazit plný text záznamu

Report

Auctions with LLM Summaries

Autor: Dubey, Kumar Avinava, Feng, Zhe, Kidambi, Rahul, Mehta, Aranyak, Wang, Di

We study an auction setting in which bidders bid for placement of their content within a summary generated by a large language model (LLM), e.g., an ad auction in which the display is a summary paragraph of multiple ads. This generalizes the classic

Externí odkaz: http://arxiv.org/abs/2404.08126

Zobrazit plný text záznamu

Report

Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers

Autor: Choromanski, Krzysztof Marcin, Li, Shanda, Likhosherstov, Valerii, Dubey, Kumar Avinava, Luo, Shengjie, He, Di, Yang, Yiming, Sarlos, Tamas, Weingarten, Thomas, Weller, Adrian

We propose a new class of linear Transformers called FourierLearner-Transformers (FLTs), which incorporate a wide range of relative positional encoding mechanisms (RPEs). These include regular RPE techniques applied for sequential data, as well as no

Externí odkaz: http://arxiv.org/abs/2302.01925

Zobrazit plný text záznamu

Report

Discourse in Multimedia: A Case Study in Information Extraction

Autor: Sachan, Mrinmaya, Dubey, Kumar Avinava, Hovy, Eduard H., Mitchell, Tom M., Roth, Dan, Xing, Eric P.

To ensure readability, text is often written and presented with due formatting. These text formatting devices help the writer to effectively convey the narrative. At the same time, these help the readers pick up the structure of the discourse and com

Externí odkaz: http://arxiv.org/abs/1811.05546

Zobrazit plný text záznamu

Report

Recurrent Estimation of Distributions

Autor: Oliva, Junier B., Dubey, Kumar Avinava, Poczos, Barnabas, Xing, Eric, Schneider, Jeff

This paper presents the recurrent estimation of distributions (RED) for modeling real-valued data in a semiparametric fashion. RED models make two novel uses of recurrent neural networks (RNNs) for density estimation of general real-valued data. Firs

Externí odkaz: http://arxiv.org/abs/1705.10750

Zobrazit plný text záznamu