相关论文: A BERTology View of LLM Orchestrations: Token- and…

Speech Language Models (SpeechLMs) model tokenized speech to capture both semantic and acoustic information. When neural audio codecs based on Residual Vector Quantization (RVQ) are used as audio tokenizers, they produce multiple discrete…

Recent work shows that post-training datasets for LLMs can be substantially downsampled without noticeably deteriorating performance. However, data selection often incurs high computational costs or is limited to narrow domains. In this…

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Pretrained language models (PLMs) like BERT provide strong semantic representations but are costly and opaque, while symbolic models such as the Tsetlin Machine (TM) offer transparency but lack semantic generalization. We propose a semantic…

This study presents a multi-stage approach to mental health classification by leveraging traditional machine learning algorithms, deep learning architectures, and transformer-based models. A novel data set was curated and utilized to…

With the booming of Large Language Models (LLMs), prompt-learning has become a promising method mainly researched in various research areas. Recently, many attempts based on prompt-learning have been made to improve the performance of text…

Prompt Tuning is emerging as a scalable and cost-effective method to fine-tune Pretrained Language Models (PLMs), which are often referred to as Large Language Models (LLMs). This study benchmarks the performance and computational…

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during…

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Fine-tuning pre-trained Large Language Models (LLMs) for specialized tasks incurs substantial computational and data costs. While model merging offers a training-free solution to integrate multiple task-specific models, existing methods…

Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may involve a distinct Language Model (LM) and an associated prompt…

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context…

Deploying vision-language models (VLMs) in resource-constrained settings demands low latency and high throughput, yet existing compact VLMs often fall short of the inference speedups their smaller parameter counts suggest. To explain this…

In large language models (LLMs), each block operates on the residual stream to map input token sequences to output token distributions. However, most of the interpretability literature focuses on internal latent representations, leaving…

1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LLMs from scratch, failing to fully leverage pre-trained models. This results in high training…

Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding video and audio into temporally aligned token sequences interleaved at the window level. However, processing these dense non-textual tokens…

Congestion control is a fundamental component of Internet infrastructure, and researchers have dedicated considerable effort to developing improved congestion control algorithms. However, despite extensive study, existing algorithms…

Pretraining large language models effectively requires strategic data selection, blending and ordering. However, key details about data mixtures especially their scalability to longer token horizons and larger model sizes remain…

Hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs, underlining a growing need for more efficient finetuning and inference without sacrificing performance. This is…

Federated Learning (FL) has gained popularity for fine-tuning large language models (LLMs) across multiple nodes, each with its own private data. While LoRA has been widely adopted for parameter efficient federated fine-tuning, recent…