FM-TS: Flow Matching for Time Series Generation

Time series generation has emerged as an essential tool for analyzing temporal data across numerous fields. While diffusion models have recently gained significant attention in generating high-quality time series, they tend to be computationally demanding and reliant on complex stochastic processes. To address these limitations, we introduce FM-TS, a rectified Flow Matching-based framework for Time Series generation, which simplifies the time series generation process by directly optimizing continuous trajectories. This approach avoids the need for iterative sampling or complex noise schedules typically required in diffusion-based models. FM-TS is more efficient in terms of training and inference. Moreover, FM-TS is highly adaptive, supporting both conditional and unconditional time series generation. Notably, through our novel inference design, the model trained in an unconditional setting can seamlessly generalize to conditional tasks without the need for retraining. Extensive benchmarking across both settings demonstrates that FM-TS consistently delivers superior performance compared to existing approaches while being more efficient in terms of training and inference. For instance, in terms of discriminative score, FM-TS achieves 0.005, 0.019, 0.011, 0.005, 0.053, and 0.106 on the Sines, Stocks, ETTh, MuJoCo, Energy, and fMRI unconditional time series datasets, respectively, significantly outperforming the second-best method which achieves 0.006, 0.067, 0.061, 0.008, 0.122, and 0.167 on the same datasets. We have achieved superior performance in solar forecasting and MuJoCo imputation tasks, significantly enhanced by our innovative $t$ power sampling method. The code is available at https://github.com/UNITES-Lab/FMTS.

FairSkin: Fair Diffusion for Skin Disease Image Generation

Image generation is a prevailing technique for clinical data augmentation for advancing diagnostic accuracy and reducing healthcare disparities. Diffusion Model (DM) has become a leading method in generating synthetic medical images, but it suffers from a critical twofold bias: (1) The quality of images generated for Caucasian individuals is significantly higher, as measured by the Frechet Inception Distance (FID). (2) The ability of the downstream-task learner to learn critical features from disease images varies across different skin tones. These biases pose significant risks, particularly in skin disease detection, where underrepresentation of certain skin tones can lead to misdiagnosis or neglect of specific conditions. To address these challenges, we propose FairSkin, a novel DM framework that mitigates these biases through a three-level resampling mechanism, ensuring fairer representation across racial and disease categories. Our approach significantly improves the diversity and quality of generated images, contributing to more equitable skin disease detection in clinical settings.

Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching

Although Large Language Models (LLMs) have demonstrated remarkable capabilities, their massive parameter counts and associated extensive computing make LLMs' deployment the main part of carbon emission from nowadays AI applications. Compared to modern GPUs like H$100$, it would be significantly carbon-sustainable if we could leverage old-fashioned GPUs such as M$40$ (as shown in Figure 1, M$40$ only has one third carbon emission of H$100$'s) for LLM servings. However, the limited High Bandwidth Memory (HBM) available on such GPU often cannot support the loading of LLMs due to the gigantic model size and intermediate activation data, making their serving challenging. For instance, a LLaMA2 model with $70$B parameters typically requires $128$GB for inference, which substantially surpasses $24$GB HBM in a $3090$ GPU and remains infeasible even considering the additional $64$GB DRAM. To address this challenge, this paper proposes a mixed-precision with a model modularization algorithm to enable LLM inference on outdated hardware with resource constraints. (The precision denotes the numerical precision like FP16, INT8, INT4) and multi-level caching (M2Cache).) Specifically, our M2Cache first modulizes neurons in LLM and creates their importance ranking. Then, it adopts a dynamic sparse mixed-precision quantization mechanism in weight space to reduce computational demands and communication overhead at each decoding step. It collectively lowers the operational carbon emissions associated with LLM inference. Moreover, M2Cache introduces a three-level cache management system with HBM, DRAM, and SSDs that complements the dynamic sparse mixed-precision inference. To enhance communication efficiency, M2Cache maintains a neuron-level mixed-precision LRU cache in HBM, a larger layer-aware cache in DRAM, and a full model in SSD.

GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning

Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by retaining, synthesizing, or selecting a small yet informative subset from the full set. Among these methods, data pruning incurs the least additional training cost and offers the most practical acceleration benefits. However, it is the most vulnerable, often suffering significant performance degradation with imbalanced or biased data schema, thus raising concerns about its accuracy and reliability in on-device deployment. Therefore, there is a looming need for a new data pruning paradigm that maintains the efficiency of previous practices while ensuring balance and robustness. Unlike the fields of computer vision and natural language processing, where mature solutions have been developed to address these issues, graph neural networks (GNNs) continue to struggle with increasingly large-scale, imbalanced, and noisy datasets, lacking a unified dataset pruning solution. To achieve this, we introduce a novel dynamic soft-pruning method, GDeR, designed to update the training ``basket'' during the process using trainable prototypes. GDeR first constructs a well-modeled graph embedding hypersphere and then samples \textit{representative, balanced, and unbiased subsets} from this embedding space, which achieves the goal we called Graph Training Debugging. Extensive experiments on five datasets across three GNN backbones, demonstrate that GDeR (I) achieves or surpasses the performance of the full dataset with 30%~50% fewer training samples, (II) attains up to a 2.81x lossless training speedup, and (III) outperforms state-of-the-art pruning methods in imbalanced training and noisy training scenarios by 0.3%~4.3% and 3.6%~7.8%, respectively.

Adapt-$\infty$: Scalable Lifelong Multimodal Instruction Tuning via Dynamic Data Selection

Visual instruction datasets from various distributors are released at different times and often contain a significant number of semantically redundant text-image pairs, depending on their task compositions (i.e., skills) or reference sources. This redundancy greatly limits the efficient deployment of lifelong adaptable multimodal large language models, hindering their ability to refine existing skills and acquire new competencies over time. To address this, we reframe the problem of Lifelong Instruction Tuning (LiIT) via data selection, where the model automatically selects beneficial samples to learn from earlier and new datasets based on the current state of acquired knowledge in the model. Based on empirical analyses that show that selecting the best data subset using a static importance measure is often ineffective for multi-task datasets with evolving distributions, we propose Adapt-$\infty$, a new multi-way and adaptive data selection approach that dynamically balances sample efficiency and effectiveness during LiIT. We construct pseudo-skill clusters by grouping gradient-based sample vectors. Next, we select the best-performing data selector for each skill cluster from a pool of selector experts, including our newly proposed scoring function, Image Grounding score. This data selector samples a subset of the most important samples from each skill cluster for training. To prevent the continuous increase in the size of the dataset pool during LiIT, which would result in excessive computation, we further introduce a cluster-wise permanent data pruning strategy to remove the most semantically redundant samples from each cluster, keeping computational requirements manageable. Training with samples selected by Adapt-$\infty$ alleviates catastrophic forgetting, especially for rare tasks, and promotes forward transfer across the continuum using only a fraction of the original datasets.

Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts

Multimodal learning has gained increasing importance across various fields, offering the ability to integrate data from diverse sources such as images, text, and personalized records, which are frequently observed in medical domains. However, in scenarios where some modalities are missing, many existing frameworks struggle to accommodate arbitrary modality combinations, often relying heavily on a single modality or complete data. This oversight of potential modality combinations limits their applicability in real-world situations. To address this challenge, we propose Flex-MoE (Flexible Mixture-of-Experts), a new framework designed to flexibly incorporate arbitrary modality combinations while maintaining robustness to missing data. The core idea of Flex-MoE is to first address missing modalities using a new missing modality bank that integrates observed modality combinations with the corresponding missing ones. This is followed by a uniquely designed Sparse MoE framework. Specifically, Flex-MoE first trains experts using samples with all modalities to inject generalized knowledge through the generalized router ($\mathcal{G}$-Router). The $\mathcal{S}$-Router then specializes in handling fewer modality combinations by assigning the top-1 gate to the expert corresponding to the observed modality combination. We evaluate Flex-MoE on the ADNI dataset, which encompasses four modalities in the Alzheimer's Disease domain, as well as on the MIMIC-IV dataset. The results demonstrate the effectiveness of Flex-MoE highlighting its ability to model arbitrary modality combinations in diverse missing modality scenarios. Code is available at https://github.com/UNITES-Lab/flex-moe.

Glider: Global and Local Instruction-Driven Expert Router

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to particular domains. This has enabled the creation of powerful and adaptive routing-based "Model MoErging" methods with the goal of using expert modules to create an aggregate system with improved performance or generalization. However, existing MoErging methods often prioritize generalization to unseen tasks at the expense of performance on held-in tasks, which limits its practical applicability in real-world deployment scenarios. We observe that current token-level routing mechanisms neglect the global semantic context of the input task. This token-wise independence hinders effective expert selection for held-in tasks, as routing decisions fail to incorporate the semantic properties of the task. To address this, we propose, Global and Local Instruction Driven Expert Router (GLIDER) that integrates a multi-scale routing mechanism, encompassing a semantic global router and a learned local router. The global router leverages LLM's advanced reasoning capabilities for semantic-related contexts to enhance expert selection. Given the input query and LLM, the router generates semantic task instructions that guide the retrieval of the most relevant experts across all layers. This global guidance is complemented by a local router that facilitates token-level routing decisions within each module, enabling finer control and enhanced performance on unseen tasks. Our experiments using T5-based models for T0 and FLAN tasks demonstrate that GLIDER achieves substantially improved held-in performance while maintaining strong generalization on held-out tasks. We also perform ablations experiments to dive deeper into the components of GLIDER. Our experiments highlight the importance of our multi-scale routing that leverages LLM-driven semantic reasoning for MoErging methods.

Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning

Network pruning has emerged as a potential solution to make LLMs cheaper to deploy. However, existing LLM pruning approaches universally rely on the C4 dataset as the calibration data for calculating pruning scores, leaving its optimality unexplored. In this study, we evaluate the choice of calibration data on LLM pruning, across a wide range of datasets that are most commonly used in LLM training and evaluation, including four pertaining datasets as well as three categories of downstream tasks encompassing nine datasets. Each downstream dataset is prompted with In-Context Learning (ICL) and Chain-of-Thought (CoT), respectively. Besides the already intriguing observation that the choice of calibration data significantly impacts the performance of pruned LLMs, our results also uncover several subtle and often unexpected findings, summarized as follows: (1) C4 is not the optimal choice for LLM pruning, even among commonly used pre-training datasets; (2) arithmetic datasets, when used as calibration data, performs on par or even better than pre-training datasets; (3) pruning with downstream datasets does not necessarily help the corresponding downstream task, compared to pre-training data; (4) ICL is widely beneficial to all data categories, whereas CoT is only useful on certain tasks. Our findings shed light on the importance of carefully selecting calibration data for LLM pruning and pave the way for more efficient deployment of these powerful models in real-world applications. We release our code at: https://github.com/abx393/llm-pruning-calibration-data.

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

As large language models (LLMs) increasingly shape the AI landscape, fine-tuning pretrained models has become more popular than in the pre-LLM era for achieving optimal performance in domain-specific tasks. However, pretrained LLMs such as ChatGPT are periodically evolved, i.e., model parameters are frequently updated), making it challenging for downstream users with limited resources to keep up with fine-tuning the newest LLMs for their domain application. Even though fine-tuning costs have nowadays been reduced thanks to the innovations of parameter-efficient fine-tuning such as LoRA, not all downstream users have adequate computing for frequent personalization. Moreover, access to fine-tuning datasets, particularly in sensitive domains such as healthcare, could be time-restrictive, making it crucial to retain the knowledge encoded in earlier fine-tuned rounds for future adaptation. In this paper, we present PortLLM, a training-free framework that (i) creates an initial lightweight model update patch to capture domain-specific knowledge, and (ii) allows a subsequent seamless plugging for the continual personalization of evolved LLM at minimal cost. Our extensive experiments cover seven representative datasets, from easier question-answering tasks {BoolQ, SST2} to harder reasoning tasks {WinoGrande, GSM8K}, and models including {Mistral-7B, Llama2, Llama3.1, and Gemma2}, validating the portability of our designed model patches and showcasing the effectiveness of our proposed framework. For instance, PortLLM achieves comparable performance to LoRA fine-tuning with reductions of up to 12.2x in GPU memory usage. Finally, we provide theoretical justifications to understand the portability of our model update patches, which offers new insights into the theoretical dimension of LLMs' personalization.

Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild

As Large Language Models (LLMs) excel across tasks and specialized domains, scaling LLMs based on existing models has garnered significant attention, which faces the challenge of decreasing performance when combining disparate models. Various techniques have been proposed for the aggregation of pre-trained LLMs, including model merging, Mixture-of-Experts, and stacking. Despite their merits, a comprehensive comparison and synergistic application of them to a diverse model zoo is yet to be adequately addressed. In light of this research gap, this paper introduces Model-GLUE, a holistic LLM scaling guideline. First, our work starts with a benchmarking of existing LLM scaling techniques, especially selective merging, and variants of mixture. Utilizing the insights from the benchmark results, we formulate an strategy for the selection and aggregation of a heterogeneous model zoo characterizing different architectures and initialization. Our methodology involves the clustering of mergeable models and optimal merging strategy selection, and the integration of clusters through a model mixture. Finally, evidenced by our experiments on a diverse Llama-2-based model zoo, Model-GLUE shows an average performance enhancement of 5.61%, achieved without additional training. Codes are available at: https://github.com/Model-GLUE/Model-GLUE.