Search

The pretrain+fine-tune paradigm is foundational in deploying large language models (LLMs) across a diverse range of downstream applications. Among these, Low-Rank Adaptation (LoRA) stands out for its parameter-efficient fine-tuning (PEFT), producing numerous off-the-shelf task-specific LoRA adapters. However, this approach requires explicit task intention selection, posing challenges for automatic task sensing and switching during inference with multiple existing LoRA adapters embedded in a single LLM. In this work, we introduce MeteoRA (Multiple-Tasks embedded LoRA), a scalable multi-knowledge LoRA fusion framework designed for LLMs. MeteoRA integrates various LoRA adapters in a Mixture-of-Experts (MoE) style into the base LLM, enabling the model to automatically select the most pertinent adapter based on the task input. This advancement significantly enhances the LLM's capability to handle composite tasks that require different adapters to solve various components of the problem. Our evaluations, featuring the LlaMA2-13B and LlaMA3-8B base models equipped with off-the-shelf 28 LoRA adapters through MeteoRA, demonstrate equivalent performance with the individual adapters. Furthermore, both base models equipped with MeteoRA achieve superior performance in sequentially solving composite tasks with ten problems in only a single inference process, highlighting the ability of timely intention switching in MeteoRA embedded LLMs., Comment: 23 pages

As foundation models (FMs) continue to shape the landscape of AI, the in-context learning (ICL) paradigm thrives but also encounters issues such as toxicity, hallucination, disparity, adversarial vulnerability, and inconsistency. Ensuring the reliability and responsibility of FMs is crucial for the sustainable development of the AI ecosystem. In this concise overview, we investigate recent advancements in enhancing the reliability and trustworthiness of FMs within ICL frameworks, focusing on four key methodologies, each with its corresponding subgoals. We sincerely hope this paper can provide valuable insights for researchers and practitioners endeavoring to build safe and dependable FMs and foster a stable and consistent ICL environment, thereby unlocking their vast potential., Comment: 18 pages, 15 figures

Transformer-based Large Language Models (LLMs) have been applied in diverse areas such as knowledge bases, human interfaces, and dynamic agents, and marking a stride towards achieving Artificial General Intelligence (AGI). However, current LLMs are predominantly pretrained on short text snippets, which compromises their effectiveness in processing the long-context prompts that are frequently encountered in practical scenarios. This article offers a comprehensive survey of the recent advancement in Transformer-based LLM architectures aimed at enhancing the long-context capabilities of LLMs throughout the entire model lifecycle, from pre-training through to inference. We first delineate and analyze the problems of handling long-context input and output with the current Transformer-based models. We then provide a taxonomy and the landscape of upgrades on Transformer architecture to solve these problems. Afterwards, we provide an investigation on wildly used evaluation necessities tailored for long-context LLMs, including datasets, metrics, and baseline models, as well as optimization toolkits such as libraries, frameworks, and compilers to boost the efficacy of LLMs across different stages in runtime. Finally, we discuss the challenges and potential avenues for future research. A curated repository of relevant literature, continuously updated, is available at https://github.com/Strivin0311/long-llms-learning., Comment: 40 pages, 3 figures, 4 tables

Quadratic band crossing points (QBCPs) and quantum anomalous Hall effect (QAHE) have attracted the attention of both theoretical and experimental researchers in recent years. Based on first-principle calculations, we find that the FeB$_2$ monolayer is a nonmagnetic semimetal with QBCPs at $K$. Through symmetry analysis and $\mathbf{k}\cdot\mathbf{p}$ invariant theory, we find that the QBCP is not protected by rotation symmetry and consists of two Dirac points with same chirality (Berry phase of $2\pi$). Once introducing Coulomb interactions, we find that there is a spontaneous-time-reversal-breaking instability of the spinful QBCPs, which gives rise to a $C=2$ QAH insulator with orbital moment ordering.

This paper describes a mode locking technique based on enhanced polarization dependent loss (PDL). The method utilizes a bent single mode fiber (SMF28) coil to induce sufficient PDL at 2 \(\mu\)m wavelength region. Significant PDL in SMF28 coils is enabled since the light is much more weakly guided. A passively mode-locked thulium doped all-fiber laser is demonstrated using this simple device with polarization controllers as mode locker. The results indicate a moderate amount of 1 dB is sufficient to initiate and sustain stable mode-locking operation. We believe, to the best of our knowledge, this is the first demonstration of mode-locked fiber laser fully based on polarization dependent property of bent fiber section., Comment: 4 pages, 7 figures