Related papers: Layer-Aware Embedding Fusion for LLMs in Text Clas…

To efficiently select optimal dataset combinations for enhancing multi-task learning (MTL) performance in large language models, we proposed a novel framework that leverages a neural network to predict the best dataset combinations. The…

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by…

Foundation models update slowly due to resource-intensive training, whereas domain-specific models evolve rapidly between releases. Model merging seeks to combine multiple expert models into a single, more capable model, reducing storage…

Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data inputs, especially for MLLMs that have been fine-tuned for…

As the parameter size of Large Language Models (LLMs) continues to expand, there is an urgent need to address the scarcity of high-quality data. In response, existing research has attempted to make a breakthrough by incorporating Federated…

A variety of contextualised language models have been proposed in the NLP community, which are trained on diverse corpora to produce numerous Neural Language Models (NLMs). However, different NLMs have reported different levels of…

The proposed method extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts. A fully convolutional network is trained to produce consistent pixel-level embedding…

Large language models (LLMs) have become an important semantic infrastructure for modern recommender systems. A prevailing paradigm integrates LLM-derived semantic embeddings with collaborative representations via representation alignment,…

Large language models (LLMs) have demonstrated significant progress in multilingual language understanding and generation. However, due to the imbalance in training data, their capabilities in non-English languages are limited. Recent…

Neural approaches to learning term embeddings have led to improved computation of similarity and ranking in information retrieval (IR). So far neural representation learning has not been extended to meta-textual information that is readily…

Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of…

We propose a compact and effective framework to fuse multimodal features at multiple layers in a single network. The framework consists of two innovative fusion schemes. Firstly, unlike existing multimodal methods that necessitate…

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

Training large language models is a computationally intensive process that often requires substantial resources to achieve state-of-the-art results. Incremental layer-wise training has been proposed as a potential strategy to optimize the…

Reasoning capabilities represent a critical frontier for large language models (LLMs), but developing them requires extensive proprietary datasets and computational resources. One way to efficiently supplement capabilities with is by model…

Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions…

Intermediate-task transfer can benefit a wide range of NLP tasks with properly selected source datasets. However, it is computationally infeasible to experiment with all intermediate transfer combinations, making choosing a useful source…

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion…

Handling varying computational resources is a critical issue in modern AI applications. Adaptive deep networks, featuring the dynamic employment of multiple classifier heads among different layers, have been proposed to address…

Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data, however, this process might suffer from privacy issues and violations of data protection regulations. As a…