Related papers: GradSim: Gradient-Based Language Grouping for Effe…

Strategic classification~(SC) explores how individuals or entities modify their features strategically to achieve favorable classification outcomes. However, existing SC methods, which are largely based on linear models or shallow neural…

In a conventional Speech emotion recognition (SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data for a language does not exist, data from other languages…

We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector $g=(g_i)_i$, GradPower first applies the elementwise sign-power transformation: $\varphi_p(g)=({\rm…

This paper investigates the recently emerged problem of Language-assisted Image Clustering (LaIC), where textual semantics are leveraged to improve the discriminability of visual representations to facilitate image clustering. Due to the…

Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and…

Meta-learning has been shown to have better performance than supervised learning for few-shot monolingual spoken word classification. However, the meta-learning approach remains under-explored in multilingual spoken word classification. In…

Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al.,2024). Gradient influence scores (Pruthi et al., 2020; Xia et al., 2024)…

Multimodal learning has developed very fast in recent years. However, during the multimodal training process, the model tends to rely on only one modality based on which it could learn faster, thus leading to inadequate use of other…

Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures. While adaptive optimizers like AdamW help address gradient variations, they still struggle with efficient and effective…

Large language models are trained on massive scrapes of the web, as required by current scaling laws. Most progress is made for English, given its abundance of high-quality pretraining data. For most other languages, however, such high…

Cross-lingual text classification aims at training a classifier on the source language and transferring the knowledge to target languages, which is very useful for low-resource languages. Recent multilingual pretrained language models…

Instruction tuning is one of the key steps required for adapting large language models (LLMs) to a broad spectrum of downstream applications. However, this procedure is difficult because real-world datasets are rarely homogeneous; they…

Massive web-crawled image-text datasets lay the foundation for recent progress in multimodal learning. These datasets are designed with the goal of training a model to do well on standard computer vision benchmarks, many of which, however,…

Large-scale multilingual evaluations, such as MEGA, often include only a handful of African languages due to the scarcity of high-quality evaluation data and the limited discoverability of existing African datasets. This lack of…

In recent years, multilingual pre-trained language models have gained prominence due to their remarkable performance on numerous downstream Natural Language Processing tasks (NLP). However, pre-training these large multilingual language…

How can language learning systems be developed for languages that lack sufficient training resources? This challenge is increasingly faced by developers across the African continent who aim to build AI systems capable of understanding and…

Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in…

Improving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages. In this paper, we relax the reliance on texts in low-resource languages by…

We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms. We present a unified generative method to acquire a shared semantic/visual embedding that enables the learning…

Automated interlinear gloss prediction with neural networks is a promising approach to accelerate language documentation efforts. However, while state-of-the-art models like GlossLM achieve high scores on glossing benchmarks, user studies…