arXiv subjects

Pan Zhang

Publications and source records attributed to Pan Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2024

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human-AI interaction applications. Therefore, we introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset, designed to evaluate and improve LVLMs' abilities in multi-turn and multi-image conversations. We employ the clustering algorithm to ffnd the relevant images and textual descriptions from the open-source Wikipedia and construct the question-answer pairs by human annotators with the assistance of the GPT-4o model. MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks and poses challenges to current LVLMs. Our in-depth analysis of 15 representative LVLMs using MMDU reveals that open-source LVLMs lag behind closed-source counterparts due to limited conversational instruction tuning data. We demonstrate that ffne-tuning open-source LVLMs on MMDU-45k signiffcantly address this gap, generating longer and more accurate conversations, and improving scores on MMDU and existing benchmarks (MMStar: +1.1%, MathVista: +1.5%, ChartQA:+1.2%). Our contributions pave the way for bridging the gap between current LVLM models and real-world application demands. This project is available at https://github.com/Liuziyu77/MMDU.

cs.CV↗

arXiv2024

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization algorithms like direct preference optimization (DPO). Existing visual alignment methods, primarily designed for single-image scenarios, struggle to effectively handle the complexity of multi-image tasks due to the scarcity of diverse training data and the high cost of annotating chosen/rejected pairs. We present Multi-Image Augmented Direct Preference Optimization (MIA-DPO), a visual preference alignment approach that effectively handles multi-image inputs. MIA-DPO mitigates the scarcity of diverse multi-image training data by extending single-image data with unrelated images arranged in grid collages or pic-in-pic formats, significantly reducing the costs associated with multi-image data annotations. Our observation reveals that attention values of LVLMs vary considerably across different images. We use attention values to identify and filter out rejected responses the model may have mistakenly focused on. Our attention-aware selection for constructing the chosen/rejected pairs without relying on (i) human annotation, (ii) extra data, and (iii) external models or APIs. MIA-DPO is compatible with various architectures and outperforms existing methods on five multi-image benchmarks, achieving an average performance boost of 3.0% on LLaVA-v1.5 and 4.3% on the recent InternLM-XC2.5. Moreover, MIA-DPO has a minimal effect on the model's ability to understand single images.

cs.CV↗

arXiv2024

MotionClone: Training-Free Motion Cloning for Controllable Video Generation

Motion-based controllable video generation offers the potential for creating captivating visual content. Existing methods typically necessitate model training to encode particular motion cues or incorporate fine-tuning to inject certain motion patterns, resulting in limited flexibility and generalization. In this work, we propose MotionClone, a training-free framework that enables motion cloning from reference videos to versatile motion-controlled video generation, including text-to-video and image-to-video. Based on the observation that the dominant components in temporal-attention maps drive motion synthesis, while the rest mainly capture noisy or very subtle motions, MotionClone utilizes sparse temporal attention weights as motion representations for motion guidance, facilitating diverse motion transfer across varying scenarios. Meanwhile, MotionClone allows for the direct extraction of motion representation through a single denoising step, bypassing the cumbersome inversion processes and thus promoting both efficiency and flexibility. Extensive experiments demonstrate that MotionClone exhibits proficiency in both global camera motion and local object motion, with notable superiority in terms of motion fidelity, textual alignment, and temporal consistency.

cs.CV↗

arXiv2024

Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate

We present the Modality Integration Rate (MIR), an effective, robust, and generalized metric to indicate the multi-modal pre-training quality of Large Vision Language Models (LVLMs). Large-scale pre-training plays a critical role in building capable LVLMs, while evaluating its training quality without the costly supervised fine-tuning stage is under-explored. Loss, perplexity, and in-context evaluation results are commonly used pre-training metrics for Large Language Models (LLMs), while we observed that these metrics are less indicative when aligning a well-trained LLM with a new modality. Due to the lack of proper metrics, the research of LVLMs in the critical pre-training stage is hindered greatly, including the training data choice, efficient module design, etc. In this paper, we propose evaluating the pre-training quality from the inter-modal distribution distance perspective and present MIR, the Modality Integration Rate, which is 1) \textbf{Effective} to represent the pre-training quality and show a positive relation with the benchmark performance after supervised fine-tuning. 2) \textbf{Robust} toward different training/evaluation data. 3) \textbf{Generalize} across training configurations and architecture choices. We conduct a series of pre-training experiments to explore the effectiveness of MIR and observe satisfactory results that MIR is indicative about training data selection, training strategy schedule, and model architecture design to get better pre-training results. We hope MIR could be a helpful metric for building capable LVLMs and inspire the following research about modality alignment in different areas. Our code is at: https://github.com/shikiw/Modality-Integration-Rate.

cs.CV↗

arXiv2024

Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data

Recent years have witnessed remarkable progress in multi-view diffusion models for 3D content creation. However, there remains a significant gap in image quality and prompt-following ability compared to 2D diffusion models. A critical bottleneck is the scarcity of high-quality 3D objects with detailed captions. To address this challenge, we propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images to assist in training multi-view diffusion models. Specifically, we introduce a data generation pipeline that employs (1) 2D and video diffusion models to generate multi-view images based on constructed text prompts, and (2) our fine-tuned 3D-aware MV-LLaVA for filtering high-quality data and rewriting inaccurate captions. Leveraging this pipeline, we have generated 1 million high-quality synthetic multi-view images with dense descriptive captions to address the shortage of high-quality 3D data. Furthermore, we present a Training Timestep Reschedule (TTR) strategy that leverages the denoising process to learn multi-view consistency while maintaining the original 2D diffusion prior. Extensive experiments demonstrate that Bootstrap3D can generate high-quality multi-view images with superior aesthetic quality, image-text alignment, and maintained view consistency.

cs.CV↗

arXiv2024

Bilayer TeO2: The First Oxide Semiconductor with Symmetric Sub-5-nm NMOS and PMOS

Wide bandgap oxide semiconductors are very promising channel candidates for next-generation electronics due to their large-area manufacturing, high-quality dielectrics, low contact resistance, and low leakage current. However, the absence of ultra-short gate length (Lg) p-type transistors has restricted their application in future complementary metal-oxide-semiconductor (CMOS) integration. Inspired by the successfully grown high-hole mobility bilayer (BL) beta tellurium dioxide (\b{eta}-TeO2), we investigate the performance of sub-5-nm-Lg BL \b{eta}-TeO2 field-effect transistors (FETs) by utilizing first-principles quantum transport simulation. The distinctive anisotropy of BL \b{eta}-TeO2 yields different transport properties. In the y-direction, both the sub-5-nm-Lg n-type and p-type BL \b{eta}-TeO2 FETs can fulfill the International Technology Roadmap for Semiconductors (ITRS) criteria for high-performance (HP) devices, which are superior to the reported oxide FETs (only n-type). Remarkably, we for the first time demonstrate the existence of the NMOS and PMOS symmetry in sub-5-nm-Lg oxide semiconductor FETs. As to the x-direction, the n-type BL \b{eta}-TeO2 FETs satisfy both the ITRS HP and low-power (LP) requirements with Lg down to 3 nm. Consequently, our work shed light on the tremendous prospects of BL \b{eta}-TeO2 for CMOS application.

cond-mat.mes-hall↗

arXiv2024

Efficient Quantum Circuit Simulation by Tensor Network Methods on Modern GPUs

Efficient simulation of quantum circuits has become indispensable with the rapid development of quantum hardware. The primary simulation methods are based on state vectors and tensor networks. As the number of qubits and quantum gates grows larger in current quantum devices, traditional state-vector based quantum circuit simulation methods prove inadequate due to the overwhelming size of the Hilbert space and extensive entanglement. Consequently, brutal force tensor network simulation algorithms become the only viable solution in such scenarios. The two main challenges faced in tensor network simulation algorithms are optimal contraction path finding and efficient execution on modern computing devices, with the latter determines the actual efficiency. In this study, we investigate the optimization of such tensor network simulations on modern GPUs and propose general optimization strategies from two aspects: computational efficiency and accuracy. Firstly, we propose to transform critical Einstein summation operations into GEMM operations, leveraging the specific features of tensor network simulations to amplify the efficiency of GPUs. Secondly, by analyzing the data characteristics of quantum circuits, we employ extended precision to ensure the accuracy of simulation results and mixed precision to fully exploit the potential of GPUs, resulting in faster and more precise simulations. Our numerical experiments demonstrate that our approach can achieve a 3.96x reduction in verification time for random quantum circuit samples in the 18-cycle case of Sycamore, with sustained performance exceeding 21 TFLOPS on one A100. This method can be easily extended to the 20-cycle case, maintaining the same performance, accelerating by 12.5x compared to the state-of-the-art CPU-based results and 4.48-6.78x compared to the state-of-the-art GPU-based results reported in the literature.

quant-ph↗

arXiv2024

FreeDrag: Feature Dragging for Reliable Point-based Image Editing

To serve the intricate and varied demands of image editing, precise and flexible manipulation in image content is indispensable. Recently, Drag-based editing methods have gained impressive performance. However, these methods predominantly center on point dragging, resulting in two noteworthy drawbacks, namely "miss tracking", where difficulties arise in accurately tracking the predetermined handle points, and "ambiguous tracking", where tracked points are potentially positioned in wrong regions that closely resemble the handle points. To address the above issues, we propose FreeDrag, a feature dragging methodology designed to free the burden on point tracking. The FreeDrag incorporates two key designs, i.e., template feature via adaptive updating and line search with backtracking, the former improves the stability against drastic content change by elaborately controls feature updating scale after each dragging, while the latter alleviates the misguidance from similar points by actively restricting the search area in a line. These two technologies together contribute to a more stable semantic dragging with higher efficiency. Comprehensive experimental results substantiate that our approach significantly outperforms pre-existing methodologies, offering reliable point-based editing even in various complex scenarios.

cs.CV↗

arXiv2024

Long-CLIP: Unlocking the Long-Text Capability of CLIP

Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant limitation of CLIP lies in the inadequate length of text input. The length of the text token is restricted to 77, and an empirical study shows the actual effective length is even less than 20. This prevents CLIP from handling detailed descriptions, limiting its applications for image retrieval and text-to-image generation with extensive prerequisites. To this end, we propose Long-CLIP as a plug-and-play alternative to CLIP that supports long-text input, retains or even surpasses its zero-shot generalizability, and aligns the CLIP latent space, making it readily replace CLIP without any further adaptation in downstream frameworks. Nevertheless, achieving this goal is far from straightforward, as simplistic fine-tuning can result in a significant degradation of CLIP's performance. Moreover, substituting the text encoder with a language model supporting longer contexts necessitates pretraining with vast amounts of data, incurring significant expenses. Accordingly, Long-CLIP introduces an efficient fine-tuning solution on CLIP with two novel strategies designed to maintain the original capabilities, including (1) a knowledge-preserved stretching of positional embedding and (2) a primary component matching of CLIP features. With leveraging just one million extra long text-image pairs, Long-CLIP has shown the superiority to CLIP for about 20% in long caption text-image retrieval and 6% in traditional text-image retrieval tasks, e.g., COCO and Flickr30k. Furthermore, Long-CLIP offers enhanced capabilities for generating images from detailed text descriptions by replacing CLIP in a plug-and-play manner.

cs.CV↗

arXiv2024

MindSpore Quantum: A User-Friendly, High-Performance, and AI-Compatible Quantum Computing Framework

We introduce MindSpore Quantum, a pioneering hybrid quantum-classical framework with a primary focus on the design and implementation of noisy intermediate-scale quantum (NISQ) algorithms. Leveraging the robust support of MindSpore, an advanced open-source deep learning training/inference framework, MindSpore Quantum exhibits exceptional efficiency in the design and training of variational quantum algorithms on both CPU and GPU platforms, delivering remarkable performance. Furthermore, this framework places a strong emphasis on enhancing the operational efficiency of quantum algorithms when executed on real quantum hardware. This encompasses the development of algorithms for quantum circuit compilation and qubit mapping, crucial components for achieving optimal performance on quantum processors. In addition to the core framework, we introduce QuPack, a meticulously crafted quantum computing acceleration engine. QuPack significantly accelerates the simulation speed of MindSpore Quantum, particularly in variational quantum eigensolver (VQE), quantum approximate optimization algorithm (QAOA), and tensor network simulations, providing astonishing speed. This combination of cutting-edge technologies empowers researchers and practitioners to explore the frontiers of quantum computing with unprecedented efficiency and performance.

quant-ph↗

arXiv2024

Research on target detection method of distracted driving behavior based on improved YOLOv8

With the development of deep learning technology, the detection and classification of distracted driving behaviour requires higher accuracy. Existing deep learning-based methods are computationally intensive and parameter redundant, limiting the efficiency and accuracy in practical applications. To solve this problem, this study proposes an improved YOLOv8 detection method based on the original YOLOv8 model by integrating the BoTNet module, GAM attention mechanism and EIoU loss function. By optimising the feature extraction and multi-scale feature fusion strategies, the training and inference processes are simplified, and the detection accuracy and efficiency are significantly improved. Experimental results show that the improved model performs well in both detection speed and accuracy, with an accuracy rate of 99.4%, and the model is smaller and easy to deploy, which is able to identify and classify distracted driving behaviours in real time, provide timely warnings, and enhance driving safety.

cs.CV↗

arXiv2024

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks. The InternLM-XComposer-2.5 is publicly available at https://github.com/InternLM/InternLM-XComposer.

cs.CV↗

arXiv2024

Achieving Energetic Superiority Through System-Level Quantum Circuit Simulation

Quantum Computational Superiority boasts rapid computation and high energy efficiency. Despite recent advances in classical algorithms aimed at refuting the milestone claim of Google's sycamore, challenges remain in generating uncorrelated samples of random quantum circuits. In this paper, we present a groundbreaking large-scale system technology that leverages optimization on global, node, and device levels to achieve unprecedented scalability for tensor networks. This enables the handling of large-scale tensor networks with memory capacities reaching tens of terabytes, surpassing memory space constraints on a single node. Our techniques enable accommodating large-scale tensor networks with up to tens of terabytes of memory, reaching up to 2304 GPUs with a peak computing power of 561 PFLOPS half-precision. Notably, we have achieved a time-to-solution of 14.22 seconds with energy consumption of 2.39 kWh which achieved fidelity of 0.002 and our most remarkable result is a time-to-solution of 17.18 seconds, with energy consumption of only 0.29 kWh which achieved a XEB of 0.002 after post-processing, outperforming Google's quantum processor Sycamore in both speed and energy efficiency, which recorded 600 seconds and 4.3 kWh, respectively.

quant-ph↗

arXiv2024

Leapfrogging Sycamore: Harnessing 1432 GPUs for 7$\times$ Faster Quantum Random Circuit Sampling

Random quantum circuit sampling serves as a benchmark to demonstrate quantum computational advantage. Recent progress in classical algorithms, especially those based on tensor network methods, has significantly reduced the classical simulation time and challenged the claim of the first-generation quantum advantage experiments. However, in terms of generating uncorrelated samples, time-to-solution, and energy consumption, previous classical simulation experiments still underperform the \textit{Sycamore} processor. Here we report an energy-efficient classical simulation algorithm, using 1432 GPUs to simulate quantum random circuit sampling which generates uncorrelated samples with higher linear cross entropy score and is 7 times faster than \textit{Sycamore} 53 qubits experiment. We propose a post-processing algorithm to reduce the overall complexity, and integrated state-of-the-art high-performance general-purpose GPU to achieve two orders of lower energy consumption compared to previous works. Our work provides the first unambiguous experimental evidence to refute \textit{Sycamore}'s claim of quantum advantage, and redefines the boundary of quantum computational advantage using random circuit sampling.

quant-ph↗

arXiv2024

V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results

Detecting objects in real-world scenes is a complex task due to various challenges, including the vast range of object categories, and potential encounters with previously unknown or unseen objects. The challenges necessitate the development of public benchmarks and challenges to advance the field of object detection. Inspired by the success of previous COCO and LVIS Challenges, we organize the V3Det Challenge 2024 in conjunction with the 4th Open World Vision Workshop: Visual Perception via Learning in an Open World (VPLOW) at CVPR 2024, Seattle, US. This challenge aims to push the boundaries of object detection research and encourage innovation in this field. The V3Det Challenge 2024 consists of two tracks: 1) Vast Vocabulary Object Detection: This track focuses on detecting objects from a large set of 13204 categories, testing the detection algorithm's ability to recognize and locate diverse objects. 2) Open Vocabulary Object Detection: This track goes a step further, requiring algorithms to detect objects from an open set of categories, including unknown objects. In the following sections, we will provide a comprehensive summary and analysis of the solutions submitted by participants. By analyzing the methods and solutions presented, we aim to inspire future research directions in vast vocabulary and open-vocabulary object detection, driving progress in this field. Challenge homepage: https://v3det.openxlab.org.cn/challenge

cs.CV↗

arXiv2024

ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

We present the ShareGPT4Video series, aiming to facilitate the video understanding of large video-language models (LVLMs) and the video generation of text-to-video models (T2VMs) via dense and precise captions. The series comprises: 1) ShareGPT4Video, 40K GPT4V annotated dense captions of videos with various lengths and sources, developed through carefully designed data filtering and annotating strategy. 2) ShareCaptioner-Video, an efficient and capable captioning model for arbitrary videos, with 4.8M high-quality aesthetic videos annotated by it. 3) ShareGPT4Video-8B, a simple yet superb LVLM that reached SOTA performance on three advancing video benchmarks. To achieve this, taking aside the non-scalable costly human annotators, we find using GPT4V to caption video with a naive multi-frame or frame-concatenation input strategy leads to less detailed and sometimes temporal-confused results. We argue the challenge of designing a high-quality video captioning strategy lies in three aspects: 1) Inter-frame precise temporal change understanding. 2) Intra-frame detailed content description. 3) Frame-number scalability for arbitrary-length videos. To this end, we meticulously designed a differential video captioning strategy, which is stable, scalable, and efficient for generating captions for videos with arbitrary resolution, aspect ratios, and length. Based on it, we construct ShareGPT4Video, which contains 40K high-quality videos spanning a wide range of categories, and the resulting captions encompass rich world knowledge, object attributes, camera movements, and crucially, detailed and precise temporal descriptions of events. Based on ShareGPT4Video, we further develop ShareCaptioner-Video, a superior captioner capable of efficiently generating high-quality captions for arbitrary videos...

cs.CV↗

arXiv2024

ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing

Instruction-based image editing focuses on equipping a generative model with the capacity to adhere to human-written instructions for editing images. Current approaches typically comprehend explicit and specific instructions. However, they often exhibit a deficiency in executing active reasoning capacities required to comprehend instructions that are implicit or insufficiently defined. To enhance active reasoning capabilities and impart intelligence to the editing model, we introduce ReasonPix2Pix, a comprehensive reasoning-attentive instruction editing dataset. The dataset is characterized by 1) reasoning instruction, 2) more realistic images from fine-grained categories, and 3) increased variances between input and edited images. When fine-tuned with our dataset under supervised conditions, the model demonstrates superior performance in instructional editing tasks, independent of whether the tasks require reasoning or not. The code will be available at https://github.com/Jin-Ying/ReasonPix2Pix.

cs.CV↗

arXiv2024

Streaming Long Video Understanding with Large Language Models

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected. The challenge of video understanding in the vision language area mainly lies in the significant computational burden caused by the great number of tokens extracted from long videos. Previous works rely on sparse sampling or frame compression to reduce tokens. However, such approaches either disregard temporal information in a long time span or sacrifice spatial details, resulting in flawed compression. To address these limitations, our VideoStreaming has two core designs: Memory-Propagated Streaming Encoding and Adaptive Memory Selection. The Memory-Propagated Streaming Encoding architecture segments long videos into short clips and sequentially encodes each clip with a propagated memory. In each iteration, we utilize the encoded results of the preceding clip as historical memory, which is integrated with the current clip to distill a condensed representation that encapsulates the video content up to the current timestamp. After the encoding process, the Adaptive Memory Selection strategy selects a constant number of question-related memories from all the historical memories and feeds them into the LLM to generate informative responses. The question-related selection reduces redundancy within the memories, enabling efficient and precise video understanding. Meanwhile, the disentangled video extraction and reasoning design allows the LLM to answer different questions about a video by directly selecting corresponding memories, without the need to encode the whole video for each question. Our model achieves superior performance and higher efficiency on long video benchmarks, showcasing precise temporal comprehension for detailed question answering.

cs.CV↗