Related papers: Multilingual State Space Models for Structured Que…

Scaling existing applications and solutions to multiple human languages has traditionally proven to be difficult, mainly due to the language-dependent nature of preprocessing and feature engineering techniques employed in traditional…

Whispered speech recognition presents significant challenges for conventional automatic speech recognition systems, particularly when combined with dialect variation. However, utilizing an efficient method to solve this problem using a…

Multilingual LLMs support a variety of languages; however, their performance is suboptimal for low-resource languages. In this work, we emphasize the importance of continued pre-training of multilingual LLMs and the use of translation-based…

State space models (SSMs) have demonstrated state-of-the-art sequence modeling performance in some modalities, but underperform attention in language modeling. Moreover, despite scaling nearly linearly in sequence length instead of…

Recent advances show that large language models (LLMs) generalize strong performance across different natural language benchmarks. However, the large size of LLMs makes training and inference expensive and impractical to run in…

Lack of proper linguistic resources is the major challenges faced by the Machine Translation system developments when dealing with the resource poor languages. In this paper, we describe effective ways to utilize the lexical resources to…

State-space models (SSMs) face a fundamental trade-off between efficiency and expressivity that is mainly dictated by the structure of the model's transition matrix. Unstructured transition matrices enable maximal expressivity, as measured…

Current Text-to-Speech models pose a multilingual challenge, where most of the models traditionally focus on English and European languages, thereby hurting the potential to provide access to information to many more people. To address this…

In second language learning, scenario-based conversation practice is important for language learners to achieve fluency in speaking, but students often lack sufficient opportunities to practice their conversational skills with qualified…

Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inference-time memory requirements from the key-value cache.…

In question answering (QA), different questions can be effectively addressed with different answering strategies. Some require a simple lookup, while others need complex, multi-step reasoning to be answered adequately. This observation…

While Indic NLP has made rapid advances recently in terms of the availability of corpora and pre-trained models, benchmark datasets on standard NLU tasks are limited. To this end, we introduce IndicXNLI, an NLI dataset for 11 Indic…

We propose Samba ASR,the first state of the art Automatic Speech Recognition(ASR)model leveraging the novel Mamba architecture as both encoder and decoder,built on the foundation of state space models(SSMs).Unlike transformerbased ASR…

Despite impressive high-level video comprehension, multimodal language models struggle with spatial reasoning across time and space. While current spatial training approaches rely on real-world video data, obtaining diverse footage with…

State space models (SSMs) are a powerful and widely-used class of probabilistic models for analysing time-series data across various fields, from econometrics to robotics. Despite their prevalence, existing software frameworks for SSMs…

In the era of generative artificial intelligence (AI), the fusion of large language models (LLMs) offers unprecedented opportunities for innovation in the field of modern education. We embark on an exploration of prompted LLMs within the…

Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art language model that learns interpretable structure from character-level input. Such models can provide fertile ground for (cognitive) computational linguistics…

This study examines how Large Language Models (LLMs) perform when tackling quantitative management decision problems in a zero-shot setting. Drawing on 900 responses generated by five leading models across 20 diverse managerial scenarios,…

Simulation is an invaluable tool for developing and evaluating controllers for self-driving cars. Current simulation frameworks are driven by highly-specialist domain specific languages, and so a natural language interface would greatly…

Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D…