Related papers: Pooling And Attention: What Are Effective Designs …

We present the first comprehensive study of Memorization in Multilingual Large Language Models (MLLMs), analyzing 95 languages using models across diverse model scales, architectures, and memorization definitions. As MLLMs are increasingly…

Multimodal Large Language Model (MLLM) have demonstrated strong generalization capabilities across diverse distributions and tasks, largely due to extensive pre-training datasets. Fine-tuning MLLM has become a common practice to improve…

Tables stored in databases and tables which are present in web pages and articles account for a large part of semi-structured data that is available on the internet. It then becomes pertinent to develop a modeling approach with large…

Embodied multimodal large models (EMLMs) have gained significant attention in recent years due to their potential to bridge the gap between perception, cognition, and action in complex, real-world environments. This comprehensive review…

Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity. Progress in these models-through increased size, instruction-tuning, and…

Representation learning is central to many downstream tasks such as search, clustering, classification, and reranking. State-of-the-art sequence encoders typically collapse a variable-length token sequence to a single vector using a pooling…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various NLP tasks. However, previous works have shown these models are sensitive towards prompt wording, and few-shot demonstrations and their order, posing…

Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these intermediate reasoning…

This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…

Linearization has emerged as a strategy for developing efficient language models (LMs). Starting from an existing Transformer-based LM, linearization replaces the attention component with computationally efficient subquadratic \textit{token…

Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence. While prior surveys focus on efficiency by examining how to shorten reasoning chains or reduce computation, this view…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

The increasing use of tools and solutions based on Large Language Models (LLMs) for various tasks in the medical domain has become a prominent trend. Their use in this highly critical and sensitive domain has thus raised important questions…

Most state-of-the-art Deep Learning systems for speaker verification are based on speaker embedding extractors. These architectures are commonly composed of a feature extractor front-end together with a pooling layer to encode…

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing…

Large Language Models (LLMs) struggle with complex reasoning due to limited diversity and inefficient search. We propose Soft Reasoning, an embedding-based search framework that optimises the embedding of the first token to guide…

Bidirectional models are considered essential for strong text embeddings. Recent approaches to adapt autoregressive language models (LMs) into strong text embedding models have largely had the requirement to modify the LM architecture to be…

Sentence embeddings are crucial in measuring semantic similarity. Most recent studies employed large language models (LLMs) to learn sentence embeddings. Existing LLMs mainly adopted autoregressive architecture without explicit backward…

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible…

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…