CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation

Large language models (LLMs) with billions of parameters have sparked a new wave of exciting AI applications. However, their high computational costs and memory demands during inference pose significant challenges. Adaptive sparse activation inference, which activates only a small number of neurons for each token, offers a novel way to accelerate model inference without degrading performance, showing great potential for resource-constrained hardware devices. Nevertheless, existing methods predict activated neurons based on individual tokens with additional MLP, which involve frequent changes in activation maps and resource calls, limiting the acceleration benefits of sparse activation. In this paper, we introduce CoreInfer, an MLP-free adaptive sparse activation inference method based on sentence-level prediction. Specifically, we propose the concept of sentence-wise core neurons, which refers to the subset of neurons most critical for a given sentence, and empirically demonstrate its effectiveness. To determine the core neurons, we explore the correlation between core neurons and the sentence's semantics. Remarkably, we discovered that core neurons exhibit both stability and similarity in relation to the sentence's semantics -- an insight overlooked by previous studies. Building on this finding, we further design two semantic-based methods for predicting core neurons to fit different input scenarios. In CoreInfer, the core neurons are determined during the pre-filling stage and fixed during the encoding stage, enabling zero-cost sparse inference. We evaluated the model generalization and task generalization of CoreInfer across various models and tasks. Notably, on an NVIDIA TITAN XP GPU, CoreInfer achieved a 10.33 times and 2.72 times speedup compared to the Huggingface implementation and PowerInfer, respectively.

Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy

Diffusion models have recently achieved great success in the synthesis of high-quality images and videos. However, the existing denoising techniques in diffusion models are commonly based on step-by-step noise predictions, which suffers from high computation cost, resulting in a prohibitive latency for interactive applications. In this paper, we propose AdaptiveDiffusion to relieve this bottleneck by adaptively reducing the noise prediction steps during the denoising process. Our method considers the potential of skipping as many noise prediction steps as possible while keeping the final denoised results identical to the original full-step ones. Specifically, the skipping strategy is guided by the third-order latent difference that indicates the stability between timesteps during the denoising process, which benefits the reusing of previous noise prediction results. Extensive experiments on image and video diffusion models demonstrate that our method can significantly speed up the denoising process while generating identical results to the original process, achieving up to an average 2~5x speedup without quality degradation.

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models

Scientific documents record research findings and valuable human knowledge, comprising a vast corpus of high-quality data. Leveraging multi-modality data extracted from these documents and assessing large models' abilities to handle scientific document-oriented tasks is therefore meaningful. Despite promising advancements, large models still perform poorly on multi-page scientific document extraction and understanding tasks, and their capacity to process within-document data formats such as charts and equations remains under-explored. To address these issues, we present DocGenome, a structured document benchmark constructed by annotating 500K scientific documents from 153 disciplines in the arXiv open-access community, using our custom auto-labeling pipeline. DocGenome features four key characteristics: 1) Completeness: It is the first dataset to structure data from all modalities including 13 layout attributes along with their LaTeX source codes. 2) Logicality: It provides 6 logical relationships between different entities within each scientific document. 3) Diversity: It covers various document-oriented tasks, including document classification, visual grounding, document layout detection, document transformation, open-ended single-page QA and multi-page QA. 4) Correctness: It undergoes rigorous quality control checks conducted by a specialized team. We conduct extensive experiments to demonstrate the advantages of DocGenome and objectively evaluate the performance of large models on our benchmark.

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

Recent Vision Transformer Compression (VTC) works mainly follow a two-stage scheme, where the importance score of each model unit is first evaluated or preset in each submodule, followed by the sparsity score evaluation according to the target sparsity constraint. Such a separate evaluation process induces the gap between importance and sparsity score distributions, thus causing high search costs for VTC. In this work, for the first time, we investigate how to integrate the evaluations of importance and sparsity scores into a single stage, searching the optimal subnets in an efficient manner. Specifically, we present OFB, a cost-efficient approach that simultaneously evaluates both importance and sparsity scores, termed Once for Both (OFB), for VTC. First, a bi-mask scheme is developed by entangling the importance score and the differentiable sparsity score to jointly determine the pruning potential (prunability) of each unit. Such a bi-mask search strategy is further used together with a proposed adaptive one-hot loss to realize the progressive-and-efficient search for the most important subnet. Finally, Progressive Masked Image Modeling (PMIM) is proposed to regularize the feature space to be more representative during the search process, which may be degraded by the dimension reduction. Extensive experiments demonstrate that OFB can achieve superior compression performance over state-of-the-art searching-based and pruning-based methods under various Vision Transformer architectures, meanwhile promoting search efficiency significantly, e.g., costing one GPU search day for the compression of DeiT-S on ImageNet-1K.

Enhanced Sparsification via Stimulative Training

Sparsification-based pruning has been an important category in model compression. Existing methods commonly set sparsity-inducing penalty terms to suppress the importance of dropped weights, which is regarded as the suppressed sparsification paradigm. However, this paradigm inactivates the dropped parts of networks causing capacity damage before pruning, thereby leading to performance degradation. To alleviate this issue, we first study and reveal the relative sparsity effect in emerging stimulative training and then propose a structured pruning framework, named STP, based on an enhanced sparsification paradigm which maintains the magnitude of dropped weights and enhances the expressivity of kept weights by self-distillation. Besides, to find an optimal architecture for the pruned network, we propose a multi-dimension architecture space and a knowledge distillation-guided exploration strategy. To reduce the huge capacity gap of distillation, we propose a subnet mutating expansion technique. Extensive experiments on various benchmarks indicate the effectiveness of STP. Specifically, without fine-tuning, our method consistently achieves superior performance at different budgets, especially under extremely aggressive pruning scenarios, e.g., remaining 95.11% Top-1 accuracy (72.43% in 76.15%) while reducing 85% FLOPs for ResNet-50 on ImageNet. Codes will be released soon.

ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning

Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously. However, their capacity to query information depicted in visual charts and engage in reasoning based on the queried contents remains under-explored. In this paper, to comprehensively and rigorously benchmark the ability of the off-the-shelf MLLMs in the chart domain, we construct ChartX, a multi-modal evaluation set covering 18 chart types, 7 chart tasks, 22 disciplinary topics, and high-quality chart data. Besides, we develop ChartVLM to offer a new perspective on handling multi-modal tasks that strongly depend on interpretable patterns, such as reasoning tasks in the field of charts or geometric images. We evaluate the chart-related ability of mainstream MLLMs and our ChartVLM on the proposed ChartX evaluation set. Extensive experiments demonstrate that ChartVLM surpasses both versatile and chart-related large models, achieving results comparable to GPT-4V. We believe that our study can pave the way for further exploration in creating a more comprehensive chart evaluation set and developing more interpretable multi-modal models. Both ChartX and ChartVLM are available at: https://github.com/UniModal4Reasoning/ChartVLM

Rethinking of Feature Interaction for Multi-task Learning on Dense Prediction

Existing works generally adopt the encoder-decoder structure for Multi-task Dense Prediction, where the encoder extracts the task-generic features, and multiple decoders generate task-specific features for predictions. We observe that low-level representations with rich details and high-level representations with abundant task information are not both involved in the multi-task interaction process. Additionally, low-quality and low-efficiency issues also exist in current multi-task learning architectures. In this work, we propose to learn a comprehensive intermediate feature globally from both task-generic and task-specific features, we reveal an important fact that this intermediate feature, namely the bridge feature, is a good solution to the above issues. Based on this, we propose a novel Bridge-Feature-Centirc Interaction (BRFI) method. A Bridge Feature Extractor (BFE) is designed for the generation of strong bridge features and Task Pattern Propagation (TPP) is applied to ensure high-quality task interaction participants. Then a Task-Feature Refiner (TFR) is developed to refine final task predictions with the well-learned knowledge from the bridge features. Extensive experiments are conducted on NYUD-v2 and PASCAL Context benchmarks, and the superior performance shows the proposed architecture is effective and powerful in promoting different dense prediction tasks simultaneously.

Efficient Architecture Search via Bi-level Data Pruning

Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention. Previous works mainly adopted the Differentiable Architecture Search (DARTS) and improved its search strategies or modules to enhance search efficiency. Recently, some methods have started considering data reduction for speedup, but they are not tightly coupled with the architecture search process, resulting in sub-optimal performance. To this end, this work pioneers an exploration into the critical role of dataset characteristics for DARTS bi-level optimization, and then proposes a novel Bi-level Data Pruning (BDP) paradigm that targets the weights and architecture levels of DARTS to enhance efficiency from a data perspective. Specifically, we introduce a new progressive data pruning strategy that utilizes supernet prediction dynamics as the metric, to gradually prune unsuitable samples for DARTS during the search. An effective automatic class balance constraint is also integrated into BDP, to suppress potential class imbalances resulting from data-efficient algorithms. Comprehensive evaluations on the NAS-Bench-201 search space, DARTS search space, and MobileNet-like search space validate that BDP reduces search costs by over 50% while achieving superior performance when applied to baseline DARTS. Besides, we demonstrate that BDP can harmoniously integrate with advanced DARTS variants, like PC-DARTS and \b{eta}-DARTS, offering an approximately 2 times speedup with minimal performance compromises.

Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

Global channel pruning (GCP) aims to remove a subset of channels (filters) across different layers from a deep model without hurting the performance. Previous works focus on either single task model pruning or simply adapting it to multitask scenario, and still face the following problems when handling multitask pruning: 1) Due to the task mismatch, a well-pruned backbone for classification task focuses on preserving filters that can extract category-sensitive information, causing filters that may be useful for other tasks to be pruned during the backbone pruning stage; 2) For multitask predictions, different filters within or between layers are more closely related and interacted than that for single task prediction, making multitask pruning more difficult. Therefore, aiming at multitask model compression, we propose a Performance-Aware Global Channel Pruning (PAGCP) framework. We first theoretically present the objective for achieving superior GCP, by considering the joint saliency of filters from intra- and inter-layers. Then a sequentially greedy pruning strategy is proposed to optimize the objective, where a performance-aware oracle criterion is developed to evaluate sensitivity of filters to each task and preserve the globally most task-related filters. Experiments on several multitask datasets show that the proposed PAGCP can reduce the FLOPs and parameters by over 60% with minor performance drop, and achieves 1.2x$\sim$3.3x acceleration on both cloud and mobile platforms.

Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation

The linear ensemble based strategy, i.e., averaging ensemble, has been proposed to improve the performance in unsupervised domain adaptation tasks. However, a typical UDA task is usually challenged by dynamically changing factors, such as variable weather, views, and background in the unlabeled target domain. Most previous ensemble strategies ignore UDA's dynamic and uncontrollable challenge, facing limited feature representations and performance bottlenecks. To enhance the model, adaptability between domains and reduce the computational cost when deploying the ensemble model, we propose a novel framework, namely Instance aware Model Ensemble With Distillation, IMED, which fuses multiple UDA component models adaptively according to different instances and distills these components into a small model. The core idea of IMED is a dynamic instance aware ensemble strategy, where for each instance, a nonlinear fusion subnetwork is learned that fuses the extracted features and predicted labels of multiple component models. The nonlinear fusion method can help the ensemble model handle dynamically changing factors. After learning a large capacity ensemble model with good adaptability to different changing factors, we leverage the ensemble teacher model to guide the learning of a compact student model by knowledge distillation. Furthermore, we provide the theoretical analysis of the validity of IMED for UDA. Extensive experiments conducted on various UDA benchmark datasets, e.g., Office 31, Office Home, and VisDA 2017, show the superiority of the model based on IMED to the state of the art methods under the comparable computation cost.