This paper presents the first study to explore the potential of parameter quantization for multimodal large language models to alleviate the significant resource constraint encountered during vision-language instruction tuning. We introduce a Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW. This method is grounded in two key innovations: (1) The learning of group-wise scale factors for quantized LLM weights to mitigate the quantization error arising from activation outliers and achieve more effective vision-language instruction tuning; (2) The implementation of a multimodal warmup that progressively integrates linguistic and multimodal training samples, thereby preventing overfitting of the quantized model to multimodal data while ensuring stable adaptation of multimodal large language models to downstream vision-language tasks. Extensive experiments demonstrate that models quantized by QSLAW perform on par with, or even surpass, their full-precision counterparts, while facilitating up to 1.4 times reduction in VL tuning time and GPU consumption. Our code is released at //github.com/xjjxmu/QSLAW.
相關內容
This paper presents a novel framework for tensor eigenvalue analysis in the context of multi-modal data fusion, leveraging topological invariants such as Betti numbers. Traditional approaches to tensor eigenvalue analysis often extend matrix theory, whereas this work introduces a topological perspective to enhance the understanding of tensor structures. By establishing new theorems that link eigenvalues to topological features, the proposed framework provides deeper insights into the latent structure of data, improving both interpretability and robustness. Applications in data fusion demonstrate the theoretical and practical significance of this approach, with potential for broad impact in machine learning and data science.
This paper presents a method for virtual contrast enhancement in breast MRI, offering a promising non-invasive alternative to traditional contrast agent-based DCE-MRI acquisition. Using a conditional generative adversarial network, we predict DCE-MRI images, including jointly-generated sequences of multiple corresponding DCE-MRI timepoints, from non-contrast-enhanced MRIs, enabling tumor localization and characterization without the associated health risks. Furthermore, we qualitatively and quantitatively evaluate the synthetic DCE-MRI images, proposing a multi-metric Scaled Aggregate Measure (SAMe), assessing their utility in a tumor segmentation downstream task, and conclude with an analysis of the temporal patterns in multi-sequence DCE-MRI generation. Our approach demonstrates promising results in generating realistic and useful DCE-MRI sequences, highlighting the potential of virtual contrast enhancement for improving breast cancer diagnosis and treatment, particularly for patients where contrast agent administration is contraindicated.
Physics-informed machine learning (PIML) has emerged as a promising alternative to conventional numerical methods for solving partial differential equations (PDEs). PIML models are increasingly built via deep neural networks (NNs) whose architecture and training process are designed such that the network satisfies the PDE system. While such PIML models have substantially advanced over the past few years, their performance is still very sensitive to the NN's architecture and loss function. Motivated by this limitation, we introduce kernel-weighted Corrective Residuals (CoRes) to integrate the strengths of kernel methods and deep NNs for solving nonlinear PDE systems. To achieve this integration, we design a modular and robust framework which consistently outperforms competing methods in solving a broad range of benchmark problems. This performance improvement has a theoretical justification and is particularly attractive since we simplify the training process while negligibly increasing the inference costs. Additionally, our studies on solving multiple PDEs indicate that kernel-weighted CoRes considerably decrease the sensitivity of NNs to factors such as random initialization, architecture type, and choice of optimizer. We believe our findings have the potential to spark a renewed interest in leveraging kernel methods for solving PDEs.
By framing reinforcement learning as a sequence modeling problem, recent work has enabled the use of generative models, such as diffusion models, for planning. While these models are effective in predicting long-horizon state trajectories in deterministic environments, they face challenges in dynamic settings with moving obstacles. Effective collision avoidance demands continuous monitoring and adaptive decision-making. While replanning at every timestep could ensure safety, it introduces substantial computational overhead due to the repetitive prediction of overlapping state sequences -- a process that is particularly costly with diffusion models, known for their intensive iterative sampling procedure. We propose an adaptive generative planning approach that dynamically adjusts replanning frequency based on the uncertainty of action predictions. Our method minimizes the need for frequent, computationally expensive, and redundant replanning while maintaining robust collision avoidance performance. In experiments, we obtain a 13.5% increase in the mean trajectory length and a 12.7% increase in mean reward over long-horizon planning, indicating a reduction in collision rates and an improved ability to navigate the environment safely.
Recent studies have evaluated the creativity/novelty of large language models (LLMs) primarily from a semantic perspective, using benchmarks from cognitive science. However, accessing the novelty in scholarly publications is a largely unexplored area in evaluating LLMs. In this paper, we introduce a scholarly novelty benchmark (SchNovel) to evaluate LLMs' ability to assess novelty in scholarly papers. SchNovel consists of 15000 pairs of papers across six fields sampled from the arXiv dataset with publication dates spanning 2 to 10 years apart. In each pair, the more recently published paper is assumed to be more novel. Additionally, we propose RAG-Novelty, which simulates the review process taken by human reviewers by leveraging the retrieval of similar papers to assess novelty. Extensive experiments provide insights into the capabilities of different LLMs to assess novelty and demonstrate that RAG-Novelty outperforms recent baseline models.
This study introduces a comprehensive benchmark designed to evaluate the performance of large language models (LLMs) in understanding and processing cultural knowledge, with a specific focus on Hakka culture as a case study. Leveraging Bloom's Taxonomy, the study develops a multi-dimensional framework that systematically assesses LLMs across six cognitive domains: Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating. This benchmark extends beyond traditional single-dimensional evaluations by providing a deeper analysis of LLMs' abilities to handle culturally specific content, ranging from basic recall of facts to higher-order cognitive tasks such as creative synthesis. Additionally, the study integrates Retrieval-Augmented Generation (RAG) technology to address the challenges of minority cultural knowledge representation in LLMs, demonstrating how RAG enhances the models' performance by dynamically incorporating relevant external information. The results highlight the effectiveness of RAG in improving accuracy across all cognitive domains, particularly in tasks requiring precise retrieval and application of cultural knowledge. However, the findings also reveal the limitations of RAG in creative tasks, underscoring the need for further optimization. This benchmark provides a robust tool for evaluating and comparing LLMs in culturally diverse contexts, offering valuable insights for future research and development in AI-driven cultural knowledge preservation and dissemination.
This paper introduces an innovative approach to the resource allocation problem, aiming to coordinate multiple independent x-applications (xAPPs) for network slicing and resource allocation in the Open Radio Access Network (O-RAN). Our approach maximizes the weighted throughput among user equipment (UE) and allocates physical resource blocks (PRBs). We prioritize two service types: enhanced Mobile Broadband and Ultra-Reliable Low-Latency Communication. Two xAPPs have been designed to achieve this: a power control xAPP for each UE and a PRB allocation xAPP. The method consists of a two-part training phase. The first part uses supervised learning with a Variational Autoencoder trained to regress the power transmission, UE association, and PRB allocation decisions, and the second part uses unsupervised learning with a contrastive loss approach to improve the generalization and robustness of the model. We evaluate the performance by comparing its results to those obtained from an exhaustive search and deep Q-network algorithms and reporting performance metrics for the regression task. The results demonstrate the superior efficiency of this approach in different scenarios among the service types, reaffirming its status as a more efficient and effective solution for network slicing problems compared to state-of-the-art methods. This innovative approach not only sets our research apart but also paves the way for exciting future advancements in resource allocation in O-RAN.
Translational distance-based knowledge graph embedding has shown progressive improvements on the link prediction task, from TransE to the latest state-of-the-art RotatE. However, N-1, 1-N and N-N predictions still remain challenging. In this work, we propose a novel translational distance-based approach for knowledge graph link prediction. The proposed method includes two-folds, first we extend the RotatE from 2D complex domain to high dimension space with orthogonal transforms to model relations for better modeling capacity. Second, the graph context is explicitly modeled via two directed context representations. These context representations are used as part of the distance scoring function to measure the plausibility of the triples during training and inference. The proposed approach effectively improves prediction accuracy on the difficult N-1, 1-N and N-N cases for knowledge graph link prediction task. The experimental results show that it achieves better performance on two benchmark data sets compared to the baseline RotatE, especially on data set (FB15k-237) with many high in-degree connection nodes.
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the difference between the actions committed by the expert (or ground truth) and the agent among complicated states in the environment. EE task benefits from these dynamic rewards because instances and labels yield to various extents of difficulty and the gains are expected to be diverse -- e.g., an ambiguous but correctly detected trigger or argument should receive high gains -- while the traditional RL models usually neglect such differences and pay equal attention on all instances. Moreover, our experiments also demonstrate that the proposed framework outperforms state-of-the-art methods, without explicit feature engineering.
In this paper, we propose the joint learning attention and recurrent neural network (RNN) models for multi-label classification. While approaches based on the use of either model exist (e.g., for the task of image captioning), training such existing network architectures typically require pre-defined label sequences. For multi-label classification, it would be desirable to have a robust inference process, so that the prediction error would not propagate and thus affect the performance. Our proposed model uniquely integrates attention and Long Short Term Memory (LSTM) models, which not only addresses the above problem but also allows one to identify visual objects of interests with varying sizes without the prior knowledge of particular label ordering. More importantly, label co-occurrence information can be jointly exploited by our LSTM model. Finally, by advancing the technique of beam search, prediction of multiple labels can be efficiently achieved by our proposed network model.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191