Vision-Language Transformers (VLTs) have shown great success recently, but are meanwhile accompanied by heavy computation costs, where a major reason can be attributed to the large number of visual and language tokens. Existing token pruning research for compressing VLTs mainly follows a single-modality-based scheme yet ignores the critical role of aligning different modalities for guiding the token pruning process, causing the important tokens for one modality to be falsely pruned in another modality branch. Meanwhile, existing VLT pruning works also lack the flexibility to dynamically compress each layer based on different input samples. To this end, we propose a novel framework named Multimodal Alignment-Guided Dynamic Token Pruning (MADTP) for accelerating various VLTs. Specifically, we first introduce a well-designed Multi-modality Alignment Guidance (MAG) module that can align features of the same semantic concept from different modalities, to ensure the pruned tokens are less important for all modalities. We further design a novel Dynamic Token Pruning (DTP) module, which can adaptively adjust the token compression ratio in each layer based on different input instances. Extensive experiments on various benchmarks demonstrate that MADTP significantly reduces the computational complexity of kinds of multimodal models while preserving competitive performance. Notably, when applied to the BLIP model in the NLVR2 dataset, MADTP can reduce the GFLOPs by 80% with less than 4% performance degradation.
相關內容
Visual Question Answering (VQA) is a complicated task that requires the capability of simultaneously processing natural language and images. Initially, this task was researched, focusing on methods to help machines understand objects and scene contexts in images. However, some text appearing in the image that carries explicit information about the full content of the image is not mentioned. Along with the continuous development of the AI era, there have been many studies on the reading comprehension ability of VQA models in the world. As a developing country, conditions are still limited, and this task is still open in Vietnam. Therefore, we introduce the first large-scale dataset in Vietnamese specializing in the ability to understand text appearing in images, we call it ViTextVQA (\textbf{Vi}etnamese \textbf{Text}-based \textbf{V}isual \textbf{Q}uestion \textbf{A}nswering dataset) which contains \textbf{over 16,000} images and \textbf{over 50,000} questions with answers. Through meticulous experiments with various state-of-the-art models, we uncover the significance of the order in which tokens in OCR text are processed and selected to formulate answers. This finding helped us significantly improve the performance of the baseline models on the ViTextVQA dataset. Our dataset is available at this \href{//github.com/minhquan6203/ViTextVQA-Dataset}{link} for research purposes.
Multi-modal Event Reasoning (MMER) endeavors to endow machines with the ability to comprehend intricate event relations across diverse data modalities. MMER is fundamental and underlies a wide broad of applications. Despite extensive instruction fine-tuning, current multi-modal large language models still fall short in such ability. The disparity stems from that existing models are insufficient to capture underlying principles governing event evolution in various scenarios. In this paper, we introduce Multi-Modal Event Evolution Learning (MEEL) to enable the model to grasp the event evolution mechanism, yielding advanced MMER ability. Specifically, we commence with the design of event diversification to gather seed events from a rich spectrum of scenarios. Subsequently, we employ ChatGPT to generate evolving graphs for these seed events. We propose an instruction encapsulation process that formulates the evolving graphs into instruction-tuning data, aligning the comprehension of event reasoning to humans. Finally, we observe that models trained in this way are still struggling to fully comprehend event evolution. In such a case, we propose the guiding discrimination strategy, in which models are trained to discriminate the improper evolution direction. We collect and curate a benchmark M-EV2 for MMER. Extensive experiments on M-EV2 validate the effectiveness of our approach, showcasing competitive performance in open-source multi-modal LLMs.
Large Multimodal Models (LMMs) have shown significant reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically use a fixed amount of visual tokens, such as the penultimate layer features in the CLIP visual encoder, as the prefix content. Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which increase the number of visual tokens significantly. However, due to the design of the Transformer architecture, computational costs associated with these models tend to increase quadratically with the number of input tokens. To tackle this problem, we explore a token reduction mechanism and find, similar to prior work, that many visual tokens are spatially redundant. Based on this, we propose PruMerge, a novel adaptive visual token reduction approach, which largely reduces the number of visual tokens while maintaining comparable model performance. We first select the unpruned visual tokens based on their similarity to class tokens and spatial tokens. We then cluster the pruned tokens based on key similarity and merge the clustered tokens with the unpruned tokens to supplement their information. Empirically, when applied to LLaVA-1.5, our approach can compress the visual tokens by 18 times on average, and achieve comparable performance across diverse visual question-answering and reasoning tasks. Code and checkpoints are at //llava-prumerge.github.io/.
Reconfigurable Intelligent Surfaces (RIS) have emerged as a disruptive technology with the potential to revolutionize wireless communication systems. In this paper, we present RIShield, a novel application of RIS technology specifically designed for radiation-sensitive environments. The aim of RIShield is to enable electromagnetic blackouts, preventing radiation leakage from target areas. We propose a comprehensive framework for RIShield deployment, considering the unique challenges and requirements of radiation-sensitive environments. By strategically positioning RIS panels, we create an intelligent shielding mechanism that selectively absorbs and reflects electromagnetic waves, effectively blocking radiation transmission. To achieve optimal performance, we model the corresponding channel and design a dynamic control that adjusts the RIS configuration based on real-time radiation monitoring. By leveraging the principles of reconfiguration and intelligent control, RIShield ensures adaptive and efficient protection while minimizing signal degradation. Through full-wave and ray-tracing simulations, we demonstrate the effectiveness of RIShield in achieving significant electromagnetic attenuation. Our results highlight the potential of RIS technology to address critical concerns in radiation-sensitive environments, paving the way for safer and more secure operations in industries such as healthcare, nuclear facilities, and defense.
Integrating LiDAR and camera information into Bird's-Eye-View (BEV) representation has emerged as a crucial aspect of 3D object detection in autonomous driving. However, existing methods are susceptible to the inaccurate calibration relationship between LiDAR and the camera sensor. Such inaccuracies result in errors in depth estimation for the camera branch, ultimately causing misalignment between LiDAR and camera BEV features. In this work, we propose a robust fusion framework called Graph BEV. Addressing errors caused by inaccurate point cloud projection, we introduce a Local Align module that employs neighbor-aware depth features via Graph matching. Additionally, we propose a Global Align module to rectify the misalignment between LiDAR and camera BEV features. Our Graph BEV framework achieves state-of-the-art performance, with an mAP of 70.1\%, surpassing BEV Fusion by 1.6\% on the nuscenes validation set. Importantly, our Graph BEV outperforms BEV Fusion by 8.3\% under conditions with misalignment noise.
Offline Reinforcement Learning (RL) faces distributional shift and unreliable value estimation, especially for out-of-distribution (OOD) actions. To address this, existing uncertainty-based methods penalize the value function with uncertainty quantification and demand numerous ensemble networks, posing computational challenges and suboptimal outcomes. In this paper, we introduce a novel strategy employing diverse randomized value functions to estimate the posterior distribution of $Q$-values. It provides robust uncertainty quantification and estimates lower confidence bounds (LCB) of $Q$-values. By applying moderate value penalties for OOD actions, our method fosters a provably pessimistic approach. We also emphasize on diversity within randomized value functions and enhance efficiency by introducing a diversity regularization method, reducing the requisite number of networks. These modules lead to reliable value estimation and efficient policy learning from offline data. Theoretical analysis shows that our method recovers the provably efficient LCB-penalty under linear MDP assumptions. Extensive empirical results also demonstrate that our proposed method significantly outperforms baseline methods in terms of performance and parametric efficiency.
Evolutionary multitasking (EMT) has emerged as a popular topic of evolutionary computation over the past years. It aims to concurrently address multiple optimization tasks within limited computing resources, leveraging inter-task knowledge transfer techniques. Despite the abundance of multitask evolutionary algorithms (MTEAs) proposed for multitask optimization (MTO), there remains a comprehensive software platform to help researchers evaluate MTEA performance on benchmark MTO problems as well as explore real-world applications. To bridge this gap, we introduce the first open-source optimization platform, named MTO-Platform (MToP), for EMT. MToP incorporates over 40 MTEAs, more than 150 MTO problem cases with real-world applications, and over 10 performance metrics. Moreover, to facilitate comparative analyses between MTEAs and traditional evolutionary algorithms, we adapted over 40 popular single-task evolutionary algorithms to address MTO problems. MToP boasts a user-friendly graphical interface, facilitating results analysis, data export, and schematics visualization. More importantly, MToP is designed with extensibility in mind, allowing users to develop new algorithms and tackle emerging problem domains. The source code of MToP is available at //github.com/intLyc/MTO-Platform.
Accuracy and computational efficiency are the most important metrics to Visual Inertial Navigation System (VINS). The existing VINS algorithms with either high accuracy or low computational complexity, are difficult to provide the high precision localization in resource-constrained devices. To this end, we propose a novel filter-based VINS framework named SchurVINS, which could guarantee both high accuracy by building a complete residual model and low computational complexity with Schur complement. Technically, we first formulate the full residual model where Gradient, Hessian and observation covariance are explicitly modeled. Then Schur complement is employed to decompose the full model into ego-motion residual model and landmark residual model. Finally, Extended Kalman Filter (EKF) update is implemented in these two models with high efficiency. Experiments on EuRoC and TUM-VI datasets show that our method notably outperforms state-of-the-art (SOTA) methods in both accuracy and computational complexity. The experimental code of SchurVINS is available at //github.com/bytedance/SchurVINS.
Large Language Models (LLMs), such as ChatGPT, are increasingly sophisticated and exhibit capabilities closely resembling those of humans. A significant application of these LLMs is their use as chat agents, responding to human inquiries across various domains. While current LLMs proficiently answer general questions, they often fall short in complex diagnostic scenarios such as legal, medical, or other specialized consultations. These scenarios typically require Task-Oriented Dialogue (TOD), where an AI chat agent must proactively pose questions and guide users toward specific goals or task completion. Previous fine-tuning models have underperformed in TOD and the full potential of this capability in current LLMs has not yet been fully explored. In this paper, we introduce DiagGPT (Dialogue in Diagnosis GPT), an innovative approach that extends LLMs to more TOD scenarios. In addition to guiding users to complete tasks, DiagGPT can effectively manage the status of all topics throughout the dialogue development. This feature enhances user experience and offers a more flexible interaction in TOD. Our experiments demonstrate that DiagGPT exhibits outstanding performance in conducting TOD with users, showing its potential for practical applications in various fields.
Emotion Recognition in Conversation (ERC) involves detecting the underlying emotion behind each utterance within a conversation. Effectively generating representations for utterances remains a significant challenge in this task. Recent works propose various models to address this issue, but they still struggle with differentiating similar emotions such as excitement and happiness. To alleviate this problem, We propose an Emotion-Anchored Contrastive Learning (EACL) framework that can generate more distinguishable utterance representations for similar emotions. To achieve this, we utilize label encodings as anchors to guide the learning of utterance representations and design an auxiliary loss to ensure the effective separation of anchors for similar emotions. Moreover, an additional adaptation process is proposed to adapt anchors to serve as effective classifiers to improve classification performance. Across extensive experiments, our proposed EACL achieves state-of-the-art emotion recognition performance and exhibits superior performance on similar emotions. Our code is available at //github.com/Yu-Fangxu/EACL.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191