相关论文: Skill Weaving: Efficient LLM Improvement via Modul…

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…

As large language models (LLMs) scale, model compression is crucial for edge deployment and accessibility. Weight-only quantization reduces model size but suffers from performance degradation at lower bit widths. Moreover, standard…

Automatic software system optimization can improve software speed, reduce operating costs, and save energy. Traditional approaches to optimization rely on manual tuning and compiler heuristics, limiting their ability to generalize across…

Large Language Models (LLMs) have shown remarkable success in supporting a wide range of knowledge-intensive tasks. In specialized domains, there is growing interest in leveraging LLMs to assist subject matter experts with domain-specific…

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of…

Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and difficulties in model parallelization during training. Recent…

Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena…

Pre-trained language models can be fine-tuned to solve diverse NLP tasks, including in few-shot settings. Thus fine-tuning allows the model to quickly pick up task-specific ``skills,'' but there has been limited study of where these…

Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We identify and characterize two key failure modes: the…

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence. While general artificial intelligence is leveraged by…

While embeddings from multimodal large language models (LLMs) excel as general-purpose representations, their application to dynamic modalities like audio and video remains underexplored. We introduce WAVE (\textbf{u}nified \&…

While large language models (LLMs) are increasingly deployed as dense retrievers, the impact of their domain-specific specialization on retrieval effectiveness remains underexplored. This investigation systematically examines how…

Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or on…

The advancement of Large Language Models (LLMs) for domain applications in fields such as materials science and engineering depends on the development of fine-tuning strategies that adapt models for specialized, technical capabilities. In…

This research explores a hybrid approach to fine-tuning large language models (LLMs) by integrating real-world and synthetic data to boost model performance, particularly in generating accurate and contextually relevant responses. By…

Multimodal Large Language Models (MLLMs) hold huge potential for usage in the medical domain, but their computational costs necessitate efficient compression techniques. This paper evaluates the impact of structural pruning and…

Large Language Models (LLMs) like ChatGPT and GPT-4 are versatile and capable of addressing a diverse range of tasks. However, general LLMs, which are developed on open-domain data, may lack the domain-specific knowledge essential for tasks…

Competency modeling is widely used in human resource management to select, develop, and evaluate talent. However, traditional expert-driven approaches rely heavily on manual analysis of large volumes of interview transcripts, making them…

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

The learnware paradigm offers a novel approach to machine learning by enabling users to reuse a set of well-trained models for tasks beyond the models' original purposes. It eliminates the need to build models from scratch, instead relying…