Searcharxiv⌕ Search

arXiv subjects

Peng Gao

Publications and source records attributed to Peng Gao.

At least 199 records · Page 11Linked to original sources
arXiv2024

MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

The remarkable progress of Multi-modal Large Language Models (MLLMs) has garnered unparalleled attention, due to their superior performance in visual contexts. However, their capabilities in visual math problem-solving remain insufficiently evaluated and understood. We investigate current benchmarks to incorporate excessive visual content within textual questions, which potentially assist MLLMs in deducing answers without truly interpreting the input diagrams. To this end, we introduce MathVerse, an all-around visual math benchmark designed for an equitable and in-depth evaluation of MLLMs. We meticulously collect 2,612 high-quality, multi-subject math problems with diagrams from publicly available sources. Each problem is then transformed by human annotators into six distinct versions, each offering varying degrees of information content in multi-modality, contributing to 15K test samples in total. This approach allows MathVerse to comprehensively assess whether and how much MLLMs can truly understand the visual diagrams for mathematical reasoning. In addition, we propose a Chain-of-Thought (CoT) evaluation strategy for a fine-grained assessment of the output answers. Rather than naively judging True or False, we employ GPT-4(V) to adaptively extract crucial reasoning steps, and then score each step with detailed error analysis, which can reveal the intermediate CoT reasoning quality by MLLMs. We hope the MathVerse benchmark may provide unique insights to guide the future development of MLLMs. Project page: https://mathverse-cuhk.github.io

cs.CV↗
arXiv2024

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models

Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress in tackling complex multimodal tasks. Among these cutting-edge developments, Google's Bard stands out for its remarkable multimodal capabilities, promoting comprehensive comprehension and reasoning across various domains. This work presents an early and holistic evaluation of LVLMs' multimodal abilities, with a particular focus on Bard, by proposing a lightweight variant of LVLM-eHub, named Tiny LVLM-eHub. In comparison to the vanilla version, Tiny LVLM-eHub possesses several appealing properties. Firstly, it provides a systematic assessment of six categories of multimodal capabilities, including visual perception, visual knowledge acquisition, visual reasoning, visual commonsense, object hallucination, and embodied intelligence, through quantitative evaluation of $42$ standard text-related visual benchmarks. Secondly, it conducts an in-depth analysis of LVLMs' predictions using the ChatGPT Ensemble Evaluation (CEE), which leads to a robust and accurate evaluation and exhibits improved alignment with human evaluation compared to the word matching approach. Thirdly, it comprises a mere $2.1$K image-text pairs, facilitating ease of use for practitioners to evaluate their own offline LVLMs. Through extensive experimental analysis, this study demonstrates that Bard outperforms previous LVLMs in most multimodal capabilities except object hallucination, to which Bard is still susceptible. Tiny LVLM-eHub serves as a baseline evaluation for various LVLMs and encourages innovative strategies aimed at advancing multimodal techniques. Our project is publicly available at \url{https://github.com/OpenGVLab/Multi-Modality-Arena}.

cs.CV↗
arXiv2024

YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5

Object detection, a crucial aspect of computer vision, has seen significant advancements in accuracy and robustness. Despite these advancements, practical applications still face notable challenges, primarily the inaccurate detection or missed detection of small objects. In this paper, we propose YOLO-TLA, an advanced object detection model building on YOLOv5. We first introduce an additional detection layer for small objects in the neck network pyramid architecture, thereby producing a feature map of a larger scale to discern finer features of small objects. Further, we integrate the C3CrossCovn module into the backbone network. This module uses sliding window feature extraction, which effectively minimizes both computational demand and the number of parameters, rendering the model more compact. Additionally, we have incorporated a global attention mechanism into the backbone network. This mechanism combines the channel information with global information to create a weighted feature map. This feature map is tailored to highlight the attributes of the object of interest, while effectively ignoring irrelevant details. In comparison to the baseline YOLOv5s model, our newly developed YOLO-TLA model has shown considerable improvements on the MS COCO validation dataset, with increases of 4.6% in mAP@0.5 and 4% in mAP@0.5:0.95, all while keeping the model size compact at 9.49M parameters. Further extending these improvements to the YOLOv5m model, the enhanced version exhibited a 1.7% and 1.9% increase in mAP@0.5 and mAP@0.5:0.95, respectively, with a total of 27.53M parameters. These results validate the YOLO-TLA model's efficient and effective performance in small object detection, achieving high accuracy with fewer parameters and computational demands.

cs.CV↗
arXiv2024

Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning

Designing distributed filter circuits (DFCs) is complex and time-consuming, involving setting and optimizing multiple hyperparameters. Traditional optimization methods, such as using the commercial finite element solver HFSS (High-Frequency Structure Simulator) to enumerate all parameter combinations with fixed steps and then simulate each combination, are not only time-consuming and labor-intensive but also rely heavily on the expertise and experience of electronics engineers, making it difficult to adapt to rapidly changing design requirements. Additionally, these commercial tools struggle with precise adjustments when parameters are sensitive to numerical changes, resulting in limited optimization effectiveness. This study proposes a novel end-to-end automated method for DFC design. The proposed method harnesses reinforcement learning (RL) algorithms, eliminating the dependence on the design experience of engineers. Thus, it significantly reduces the subjectivity and constraints associated with circuit design. The experimental findings demonstrate clear improvements in design efficiency and quality when comparing the proposed method with traditional engineer-driven methods. Furthermore, the proposed method achieves superior performance when designing complex or rapidly evolving DFCs, highlighting the substantial potential of RL in circuit design automation. In particular, compared to the existing DFC automation design method CircuitGNN, our method achieves an average performance improvement of 8.72%. Additionally, the execution efficiency of our method is 2000 times higher than CircuitGNN on the CPU and 241 times higher on the GPU.

cs.LG↗
arXiv2024

Dynamic Identity-Guided Attention Network for Visible-Infrared Person Re-identification

Visible-infrared person re-identification (VI-ReID) aims to match people with the same identity between visible and infrared modalities. VI-ReID is a challenging task due to the large differences in individual appearance under different modalities. Existing methods generally try to bridge the cross-modal differences at image or feature level, which lacks exploring the discriminative embeddings. Effectively minimizing these cross-modal discrepancies relies on obtaining representations that are guided by identity and consistent across modalities, while also filtering out representations that are irrelevant to identity. To address these challenges, we introduce a dynamic identity-guided attention network (DIAN) to mine identity-guided and modality-consistent embeddings, facilitating effective bridging the gap between different modalities. Specifically, in DIAN, to pursue a semantically richer representation, we first use orthogonal projection to fuse the features from two connected coarse and fine layers. Furthermore, we first use dynamic convolution kernels to mine identity-guided and modality-consistent representations. More notably, a cross embedding balancing loss is introduced to effectively bridge cross-modal discrepancies by above embeddings. Experimental results on SYSU-MM01 and RegDB datasets show that DIAN achieves state-of-the-art performance. Specifically, for indoor search on SYSU-MM01, our method achieves 86.28% rank-1 accuracy and 87.41% mAP, respectively. Our code will be available soon.

cs.CV↗
arXiv2024

Nonlinear Faraday magneto-optic effects in a helically wound optical fiber

We thoroughly investigate the Faraday magneto-optical effects in a helically wound nonlinear optical fiber. We find the emergence of an additional rotation angle proportional to the optical intensity, arised from the nonlinear corrections to both the Verdet constant and the fiber torsion. By analyzing an oscillator model describing the electron motions in the fiber medium, we can obtain the third-order susceptibility in the presence of the magnetic field. According to the Maxwell's equations and the minimal coupling principle in the metric expression of the curved space, we derive the propagation equations of light in a helically wound optical fiber. Finally, we have obtained the analytic expressions of Faraday rotation angle for both linearly and elliptically polarized lights, which explicitly indicates an important nonlinear correction on the Faraday rotation angles. Possible experimental observations and some implications of our theoretical findings are discussed.

physics.optics↗
arXiv2024

VEnhancer: Generative Space-Time Enhancement for Video Generation

We present VEnhancer, a generative space-time enhancement framework that improves the existing text-to-video results by adding more details in spatial domain and synthetic detailed motion in temporal domain. Given a generated low-quality video, our approach can increase its spatial and temporal resolution simultaneously with arbitrary up-sampling space and time scales through a unified video diffusion model. Furthermore, VEnhancer effectively removes generated spatial artifacts and temporal flickering of generated videos. To achieve this, basing on a pretrained video diffusion model, we train a video ControlNet and inject it to the diffusion model as a condition on low frame-rate and low-resolution videos. To effectively train this video ControlNet, we design space-time data augmentation as well as video-aware conditioning. Benefiting from the above designs, VEnhancer yields to be stable during training and shares an elegant end-to-end training manner. Extensive experiments show that VEnhancer surpasses existing state-of-the-art video super-resolution and space-time super-resolution methods in enhancing AI-generated videos. Moreover, with VEnhancer, exisiting open-source state-of-the-art text-to-video method, VideoCrafter-2, reaches the top one in video generation benchmark -- VBench.

cs.CV↗
arXiv2024

Even-integer Quantum Hall Effect in an Oxide Caused by Hidden Rashba Effect

In the presence of high magnetic field, quantum Hall systems usually host both even- and odd-integer quantized states because of lifted band degeneracies. Selective control of these quantized states is challenging but essential to understand the exotic ground states and manipulate the spin textures. Here, we study the quantum Hall effect in Bi2O2Se thin films. In magnetic fields as high as 50 T, we observe only even-integer quantum Hall states, but no sign of odd-integer states. However, when reducing the thickness of the epitaxial Bi2O2Se film to one unit cell, we observe both odd- and even-integer states in this Janus (asymmetric) film grown on SrTiO3. By means of a Rashba bilayer model based on ab initio band structures of Bi2O2Se thin films, we can ascribe the absence of odd-integer states in thicker films to the hidden Rasbha effect, where the local inversion symmetry breaking in two sectors of the [Bi2O2]2+ layer yields opposite Rashba spin polarizations, which compensate with each other. In the one unit cell Bi2O2Se film grown on SrTiO3, the asymmetry introduced by top surface and bottom interface induces a net polar field. The resulting global Rashba effect lifts the band degeneracies present in the symmetric case of thicker films.

cond-mat.mes-hall↗
arXiv2024

Detecting Complex Multi-step Attacks with Explainable Graph Neural Network

Complex multi-step attacks have caused significant damage to numerous critical infrastructures. To detect such attacks, graph neural network based methods have shown promising results by modeling the system's events as a graph. However, existing methods still face several challenges when deployed in practice. First, there is a lack of sufficient real attack data especially considering the large volume of normal data. Second, the modeling of event graphs is challenging due to their dynamic and heterogeneous nature. Third, the lack of explanation in learning models undermines the trustworthiness of such methods in production environments. To address the above challenges, in this paper, we propose an attack detection method, Trace2Vec. The approach first designs an erosion function to augment rare attack samples, and integrates them into the event graphs. Next, it models the event graphs via a continuous-time dynamic heterogeneous graph neural network. Finally, it employs the Monte Carlo tree search algorithm to identify events with greater contributions to the attack, thus enhancing the explainability of the detection result. We have implemented a prototype for Trace2Vec, and the experimental evaluations demonstrate its superior detection and explanation performance compared to existing methods.

cs.CR↗
arXiv2024

Multi-User Localization and Tracking with Spatiotemporal Correlation in Multi-RIS-Assisted Systems

As a promising technique, reconfigurable intelligent surfaces (RISs) exhibit its tremendous potential for high accuracy positioning. In this paper, we investigates multi-user localization and tracking problem in multi-RISs-assisted system. In particular, we incorporate statistical spatiotemporal correlation of multi-user locations and develop a general spatiotemporal Markov random field model (ST-+MRF) to capture multi-user dynamic motion states. To achieve superior performance, a novel multi-user tracking algorithm is proposed based on Bayesian inference to effectively utilize the correlation among users. Besides that, considering the necessity of RISs configuration for tracking performance, we further propose a predictive RISs beamforming optimization scheme via semidefinite relaxation (SDR). Compared to other pioneering work, finally, we confirm that the proposed strategy by alternating tracking algorithm and RISs optimization, can achieve significant performance gains over benchmark schemes.

cs.IT↗
arXiv2024

Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers

Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating learnable placeholders such as [nextline] and [nextframe] tokens, Lumina-T2X seamlessly unifies the representations of different modalities across various spatial-temporal resolutions. This unified approach enables training within a single framework for different modalities and allows for flexible generation of multimodal data at any resolution, aspect ratio, and length during inference. Advanced techniques like RoPE, RMSNorm, and flow matching enhance the stability, flexibility, and scalability of Flag-DiT, enabling models of Lumina-T2X to scale up to 7 billion parameters and extend the context window to 128K tokens. This is particularly beneficial for creating ultra-high-definition images with our Lumina-T2I model and long 720p videos with our Lumina-T2V model. Remarkably, Lumina-T2I, powered by a 5-billion-parameter Flag-DiT, requires only 35% of the training computational costs of a 600-million-parameter naive DiT. Our further comprehensive analysis underscores Lumina-T2X's preliminary capability in resolution extrapolation, high-resolution editing, generating consistent 3D views, and synthesizing videos with seamless transitions. We expect that the open-sourcing of Lumina-T2X will further foster creativity, transparency, and diversity in the generative AI community.

cs.CV↗
arXiv2024

A3VLM: Actionable Articulation-Aware Vision Language Model

Vision Language Models (VLMs) have received significant attention in recent years in the robotics community. VLMs are shown to be able to perform complex visual reasoning and scene understanding tasks, which makes them regarded as a potential universal solution for general robotics problems such as manipulation and navigation. However, previous VLMs for robotics such as RT-1, RT-2, and ManipLLM have focused on directly learning robot-centric actions. Such approaches require collecting a significant amount of robot interaction data, which is extremely costly in the real world. Thus, we propose A3VLM, an object-centric, actionable, articulation-aware vision language model. A3VLM focuses on the articulation structure and action affordances of objects. Its representation is robot-agnostic and can be translated into robot actions using simple action primitives. Extensive experiments in both simulation benchmarks and real-world settings demonstrate the effectiveness and stability of A3VLM. We release our code and other materials at https://github.com/changhaonan/A3VLM.

cs.RO↗
arXiv2024

Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT

Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabilities, Lumina-T2X still encounters challenges including training instability, slow inference, and extrapolation artifacts. In this paper, we present Lumina-Next, an improved version of Lumina-T2X, showcasing stronger generation performance with increased training and inference efficiency. We begin with a comprehensive analysis of the Flag-DiT architecture and identify several suboptimal components, which we address by introducing the Next-DiT architecture with 3D RoPE and sandwich normalizations. To enable better resolution extrapolation, we thoroughly compare different context extrapolation methods applied to text-to-image generation with 3D RoPE, and propose Frequency- and Time-Aware Scaled RoPE tailored for diffusion transformers. Additionally, we introduced a sigmoid time discretization schedule to reduce sampling steps in solving the Flow ODE and the Context Drop method to merge redundant visual tokens for faster network evaluation, effectively boosting the overall sampling speed. Thanks to these improvements, Lumina-Next not only improves the quality and efficiency of basic text-to-image generation but also demonstrates superior resolution extrapolation capabilities and multilingual generation using decoder-based LLMs as the text encoder, all in a zero-shot manner. To further validate Lumina-Next as a versatile generative framework, we instantiate it on diverse tasks including visual recognition, multi-view, audio, music, and point cloud generation, showcasing strong performance across these domains. By releasing all codes and model weights, we aim to advance the development of next-generation generative AI capable of universal modeling.

cs.CV↗
arXiv2024

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models

Large Language Models (LLMs) have become pivotal in advancing the field of artificial intelligence, yet their immense sizes pose significant challenges for both fine-tuning and deployment. Current post-training pruning methods, while reducing the sizes of LLMs, often fail to maintain their original performance. To address these challenges, this paper introduces SPP, a Sparsity-Preserved Parameter-efficient fine-tuning method. Different from existing post-training pruning approaches that struggle with performance retention, SPP proposes to employ lightweight learnable column and row matrices to optimize sparse LLM weights, keeping the structure and sparsity of pruned pre-trained models intact. By element-wise multiplication and residual addition, SPP ensures the consistency of model sparsity pattern and ratio during both training and weight-merging processes. We demonstrate the effectiveness of SPP by applying it to the LLaMA and LLaMA-2 model families with recent post-training pruning methods. Our results show that SPP significantly enhances the performance of models with different sparsity patterns (i.e. unstructured and N:M sparsity), especially for those with high sparsity ratios (e.g. 75%), making it a promising solution for the efficient fine-tuning of sparse LLMs. Code will be made available at https://github.com/Lucky-Lance/SPP.

cs.CL↗
arXiv2024

P4Control: Line-Rate Cross-Host Attack Prevention via In-Network Information Flow Control Enabled by Programmable Switches and eBPF

Modern targeted attacks such as Advanced Persistent Threats use multiple hosts as stepping stones and move laterally across them to gain deeper access to the network. However, existing defenses lack end-to-end information flow visibility across hosts and cannot block cross-host attack traffic in real time. In this paper, we propose P4Control, a network defense system that precisely confines end-to-end information flows in a network and prevents cross-host attacks at line rate. P4Control introduces a novel in-network decentralized information flow control (DIFC) mechanism and is the first work that enforces DIFC at the network level at network line rate. This is achieved through: (1) an in-network primitive based on programmable switches for tracking inter-host information flows and enforcing line-rate DIFC policies; (2) a lightweight eBPF-based primitive deployed on hosts for tracking intra-host information flows. P4Control also provides an expressive policy framework for specifying DIFC policies against different attack scenarios. We conduct extensive evaluations to show that P4Control can effectively prevent cross-host attacks in real time, while maintaining line-rate network performance and imposing minimal overhead on the network and host machines. It is also noteworthy that P4Control can facilitate the realization of a zero trust architecture through its fine-grained least-privilege network access control.

cs.CR↗
arXiv2024

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion

Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained unified spaces. In this work, we propose FreeBind, an idea that treats multimodal representation spaces as basic units, and freely augments pre-trained unified space by integrating knowledge from extra expert spaces via "space bonds". Specifically, we introduce two kinds of basic space bonds: 1) Space Displacement Bond and 2) Space Combination Bond. Based on these basic bonds, we design Complex Sequential & Parallel Bonds to effectively integrate multiple spaces simultaneously. Benefiting from the modularization concept, we further propose a coarse-to-fine customized inference strategy to flexibly adjust the enhanced unified space for different purposes. Experimentally, we bind ImageBind with extra image-text and audio-text expert spaces, resulting in three main variants: ImageBind++, InternVL_IB, and InternVL_IB++. These resulting spaces outperform ImageBind on 5 audio-image-text downstream tasks across 9 datasets. Moreover, via customized inference, it even surpasses the advanced audio-text and image-text expert spaces.

cs.CV↗
arXiv2024

Stimulated Emission Depletion (STED) Magnetic Particle Imaging

Magnetic particle imaging (MPI) is an in-vivo imaging method to detect magnetic nanoparticles for blood vessel imaging and molecular target imaging. Compared with conventional molecular imaging devices (such as nuclear medicine imaging PET and SPECT), magnetic nanoparticles have longer storage periods than radionuclides without ionizing radiation. MPI has higher detection sensitivity compared with MRI. To accurately locate molecular probes in living organisms, high-resolution images are needed to meet the requirements of precision medicine. The spatial resolution of the latest domestic and international MPI equipment is 1-6 mm and has not yet met the requirements of medical imaging detection. We previously studied the spatial encoding technology based on pulsed square wave stimulation, which significantly improved the image resolution along the field free line (FFL) direction. This study proposes an innovative idea of high-resolution MPI based on stimulated emission depletion (STED) of magnetic nanoparticle signals. The stimulated emission was implemented by using cosine stimulation on FFL-based MPI scanner systems. The STED signal was generated by adding an offset magnetic field parallel to the FFL, which may form a donut-shaped focal spot or a regular Gaussian focal spot depending on the offset field strength. Focal spot modulation techniques and deconvolution algorithms were developed to improve image resolution.

physics.med-ph↗