Zobrazeno 1 - 10
of 499
pro vyhledávání: '"Gupta, Ashim"'
Large language models (LLMs) are increasingly deployed in real-world scenarios with the help of recent model compression techniques. Such momentum towards local deployment means the use of compressed LLMs will widely impact a large population. Howeve
Externí odkaz:
http://arxiv.org/abs/2407.04965
The $\texttt{Hi-COLA}$ code is an efficient dark matter simulation suite that flexibly handles the Horndeski family of modified gravity models. In this work we extend the scope of $\texttt{Hi-COLA}$ to accommodate Horndeski theories with K-mouflage s
Externí odkaz:
http://arxiv.org/abs/2407.00855
Autor:
Bose, Benjamin, Gupta, Ashim Sen, Fiorini, Bartolomeo, Brando, Guilherme, Hassani, Farbod, Baker, Tessa, Lombriser, Lucas, Li, Baojiu, Ruan, Cheng-Zong, Hernandez-Aguayo, Cesar, Atayde, Luis, Frusciante, Noemi
Testing gravity and the concordance model of cosmology, $\Lambda$CDM, at large scales is a key goal of this decade's largest galaxy surveys. Here we present a comparative study of dark matter power spectrum predictions from different numerical codes
Externí odkaz:
http://arxiv.org/abs/2406.13667
The increasing size of transformer-based models in NLP makes the question of compressing them important. In this work, we present a comprehensive analysis of factorization based model compression techniques. Specifically, we focus on comparing straig
Externí odkaz:
http://arxiv.org/abs/2406.11307
To completely understand a document, the use of textual information is not enough. Understanding visual cues, such as layouts and charts, is also required. While the current state-of-the-art approaches for document understanding (both OCR-based and O
Externí odkaz:
http://arxiv.org/abs/2406.10085
Do larger and more performant models resolve NLP's longstanding robustness issues? We investigate this question using over 20 models of different sizes spanning different architectural choices and pretraining objectives. We conduct evaluations using
Externí odkaz:
http://arxiv.org/abs/2311.09694
Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined categories
Externí odkaz:
http://arxiv.org/abs/2310.16761
Autor:
Gupta, Ashim, Krishna, Amrith
Clean-label (CL) attack is a form of data poisoning attack where an adversary modifies only the textual input of the training data, without requiring access to the labeling function. CL attacks are relatively unexplored in NLP, as compared to label f
Externí odkaz:
http://arxiv.org/abs/2305.19607
Autor:
Gupta, Ashim, Blum, Carter Wood, Choji, Temma, Fei, Yingjie, Shah, Shalin, Vempala, Alakananda, Srikumar, Vivek
Can language models transform inputs to protect text classifiers against adversarial attacks? In this work, we present ATINTER, a model that intercepts and learns to rewrite adversarial inputs to make them non-adversarial for a downstream text classi
Externí odkaz:
http://arxiv.org/abs/2305.16444
Autor:
Maheshwari, Ayush, Gupta, Ashim, Krishna, Amrith, Singh, Atul Kumar, Ramakrishnan, Ganesh, Kumar, G. Anil, Singla, Jitin
We release S\={a}mayik, a dataset of around 53,000 parallel English-Sanskrit sentences, written in contemporary prose. Sanskrit is a classical language still in sustenance and has a rich documented heritage. However, due to the limited availability o
Externí odkaz:
http://arxiv.org/abs/2305.14004