Large language models (LLMs) demonstrate powerful capabilities, but they still face
challenges in practical applications, such as hallucinations, slow knowledge updates, and …

On-device large language models (LLMs), referring to running LLMs on edge devices, have
raised considerable interest since they are more cost-effective, latency-efficient, and privacy …

The emergence of large language models (LLMs) has marked a significant breakthrough in
natural language processing (NLP), fueling a paradigm shift in information acquisition …

Low-rank adaptations (LoRA) are often employed to fine-tune large language models
(LLMs) for new tasks. This paper investigates LoRA composability for cross-task …

Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating
up-to-date information, mitigating hallucinations, and enhancing response quality …

This work aims at decreasing the end-to-end generation latency of large language models
(LLMs). One of the major causes of the high generation latency is the sequential decoding …

In the rapidly evolving landscape of artificial intelligence (AI), generative large language
models (LLMs) stand at the forefront, revolutionizing how we interact with our data. However …

In long context scenarios, large language models (LLMs) face three main challenges: higher
computational/financial cost, longer latency, and inferior performance. Some studies reveal …

With the bomb ignited by ChatGPT, Transformer-based Large Language Models (LLMs)
have paved a revolutionary path toward Artificial General Intelligence (AGI) and have been …

The utilization of long contexts poses a big challenge for large language models due to their
limited context window length. Although the context window can be extended through fine …