Searcharxiv⌕ Search

arXiv subjects

Peng Gao

Publications and source records attributed to Peng Gao.

At least 235 records · Page 13Linked to original sources
arXiv2023

A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise

The surge of interest towards Multi-modal Large Language Models (MLLMs), e.g., GPT-4V(ision) from OpenAI, has marked a significant trend in both academia and industry. They endow Large Language Models (LLMs) with powerful capabilities in visual understanding, enabling them to tackle diverse multi-modal tasks. Very recently, Google released Gemini, its newest and most capable MLLM built from the ground up for multi-modality. In light of the superior reasoning capabilities, can Gemini challenge GPT-4V's leading position in multi-modal learning? In this paper, we present a preliminary exploration of Gemini Pro's visual understanding proficiency, which comprehensively covers four domains: fundamental perception, advanced cognition, challenging vision tasks, and various expert capacities. We compare Gemini Pro with the state-of-the-art GPT-4V to evaluate its upper limits, along with the latest open-sourced MLLM, Sphinx, which reveals the gap between manual efforts and black-box systems. The qualitative samples indicate that, while GPT-4V and Gemini showcase different answering styles and preferences, they can exhibit comparable visual reasoning capabilities, and Sphinx still trails behind them concerning domain generalizability. Specifically, GPT-4V tends to elaborate detailed explanations and intermediate steps, and Gemini prefers to output a direct and concise answer. The quantitative evaluation on the popular MME benchmark also demonstrates the potential of Gemini to be a strong challenger to GPT-4V. Our early investigation of Gemini also observes some common issues of MLLMs, indicating that there still remains a considerable distance towards artificial general intelligence. Our project for tracking the progress of MLLM is released at https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models.

cs.CV↗
arXiv2023

3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V

In this work, we present a new visual prompting method called 3DAxiesPrompts (3DAP) to unleash the capabilities of GPT-4V in performing 3D spatial tasks. Our investigation reveals that while GPT-4V exhibits proficiency in discerning the position and interrelations of 2D entities through current visual prompting techniques, its abilities in handling 3D spatial tasks have yet to be explored. In our approach, we create a 3D coordinate system tailored to 3D imagery, complete with annotated scale information. By presenting images infused with the 3DAP visual prompt as inputs, we empower GPT-4V to ascertain the spatial positioning information of the given 3D target image with a high degree of precision. Through experiments, We identified three tasks that could be stably completed using the 3DAP method, namely, 2D to 3D Point Reconstruction, 2D to 3D point matching, and 3D Object Detection. We perform experiments on our proposed dataset 3DAP-Data, the results from these experiments validate the efficacy of 3DAP-enhanced GPT-4V inputs, marking a significant stride in 3D spatial task execution.

cs.AI↗
arXiv2023

Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation

Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames. However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities. Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video. On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2% and +8.7% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.

cs.CV↗
arXiv2023

6G Network AI Architecture for Everyone-Centric Customized Services

Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone's Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system's overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.

cs.NI↗
arXiv2023

Digital Life Project: Autonomous 3D Characters with Social Intelligence

In this work, we present Digital Life Project, a framework utilizing language as the universal medium to build autonomous 3D characters, who are capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life in a digital environment. Our framework comprises two primary components: 1) SocioMind: a meticulously crafted digital brain that models personalities with systematic few-shot exemplars, incorporates a reflection process based on psychology principles, and emulates autonomy by initiating dialogue topics; 2) MoMat-MoGen: a text-driven motion synthesis paradigm for controlling the character's digital body. It integrates motion matching, a proven industry technique to ensure motion quality, with cutting-edge advancements in motion generation for diversity. Extensive experiments demonstrate that each module achieves state-of-the-art performance in its respective domain. Collectively, they enable virtual characters to initiate and sustain dialogues autonomously, while evolving their socio-psychological states. Concurrently, these characters can perform contextually relevant bodily movements. Additionally, a motion captioning module further allows the virtual character to recognize and appropriately respond to human players' actions. Homepage: https://digital-life-project.com/

cs.CV↗
arXiv2023

SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models

We present SPHINX, a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, tuning tasks, and visual embeddings. First, for stronger vision-language alignment, we unfreeze the large language model (LLM) during pre-training, and introduce a weight mix strategy between LLMs trained by real-world and synthetic data. By directly integrating the weights from two domains, the mixed LLM can efficiently incorporate diverse semantics with favorable robustness. Then, to enable multi-purpose capabilities, we mix a variety of tasks for joint visual instruction tuning, and design task-specific instructions to avoid inter-task conflict. In addition to the basic visual question answering, we include more challenging tasks such as region-level understanding, caption grounding, document layout detection, and human pose estimation, contributing to mutual enhancement over different scenarios. Additionally, we propose to extract comprehensive visual embeddings from various network architectures, pre-training paradigms, and information granularity, providing language models with more robust image representations. Based on our proposed joint mixing, SPHINX exhibits superior multi-modal understanding capabilities on a wide range of applications. On top of this, we further propose an efficient strategy aiming to better capture fine-grained appearances of high-resolution images. With a mixing of different scales and high-resolution sub-images, SPHINX attains exceptional visual parsing and reasoning performance on existing evaluation benchmarks. We hope our work may cast a light on the exploration of joint mixing in future MLLM research. Code is released at https://github.com/Alpha-VLLM/LLaMA2-Accessory.

cs.CV↗
arXiv2023

Quantum scattering treatment on the time-domain diffraction of a matter-wave soliton

We study the dynamics of the matter-wave soliton interacting with a vibrating mirror created by an evanescent light and provide a quantum scattering picture for the time-domain diffraction of the matter-wave soliton. Under Kramers-Henneberger (KH) transformation, i.e., in a vibrating coordinate, the vibration of the mirror can be cast to an effective gauge field. We then can exploit Dyson series and the quantum scattering theory to investigate the dynamics of the soliton that moves in the effective gauge field and is reflected by a static mirror. Our analytical theory can quantitatively deduce the locations and the relative weights of the scattered wave packets, which is consistent with our numerical simulations of directly solving a nonlinear Schrödinger equation. In particular, for a two-frequency vibrating case, our theory predicts some interesting multi-peak sideband structures in the diffracted matter-wave distributions, which can be resorted to the resonance of two frequencies. Underlying mechanisms and possible applications are discussed.

nlin.PS↗
arXiv2023

Collaborative Decision-Making Using Spatiotemporal Graphs in Connected Autonomy

Collaborative decision-making is an essential capability for multi-robot systems, such as connected vehicles, to collaboratively control autonomous vehicles in accident-prone scenarios. Under limited communication bandwidth, capturing comprehensive situational awareness by integrating connected agents' observation is very challenging. In this paper, we propose a novel collaborative decision-making method that efficiently and effectively integrates collaborators' representations to control the ego vehicle in accident-prone scenarios. Our approach formulates collaborative decision-making as a classification problem. We first represent sequences of raw observations as spatiotemporal graphs, which significantly reduce the package size to share among connected vehicles. Then we design a novel spatiotemporal graph neural network based on heterogeneous graph learning, which analyzes spatial and temporal connections of objects in a unified way for collaborative decision-making. We evaluate our approach using a high-fidelity simulator that considers realistic traffic, communication bandwidth, and vehicle sensing among connected autonomous vehicles. The experimental results show that our representation achieves over 100x reduction in the shared data size that meets the requirements of communication bandwidth for connected autonomous driving. In addition, our approach achieves over 30% improvements in driving safety.

cs.RO↗
arXiv2023

Improving Compositional Text-to-image Generation with Large Vision-Language Models

Recent advancements in text-to-image models, particularly diffusion models, have shown significant promise. However, compositional text-to-image models frequently encounter difficulties in generating high-quality images that accurately align with input texts describing multiple objects, variable attributes, and intricate spatial relationships. To address this limitation, we employ large vision-language models (LVLMs) for multi-dimensional assessment of the alignment between generated images and their corresponding input texts. Utilizing this assessment, we fine-tune the diffusion model to enhance its alignment capabilities. During the inference phase, an initial image is produced using the fine-tuned diffusion model. The LVLM is then employed to pinpoint areas of misalignment in the initial image, which are subsequently corrected using the image editing algorithm until no further misalignments are detected by the LVLM. The resultant image is consequently more closely aligned with the input text. Our experimental results validate that the proposed methodology significantly improves text-image alignment in compositional image generation, particularly with respect to object number, attribute binding, spatial relationships, and aesthetic quality.

cs.CV↗
arXiv2023

Personalize Segment Anything Model with One Shot

Driven by large-data pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promptable framework, revolutionizing the segmentation models. Despite the generality, customizing SAM for specific visual concepts without man-powered prompting is under explored, e.g., automatically segmenting your pet dog in different images. In this paper, we propose a training-free Personalization approach for SAM, termed as PerSAM. Given only a single image with a reference mask, PerSAM first localizes the target concept by a location prior, and segments it within other images or videos via three techniques: target-guided attention, target-semantic prompting, and cascaded post-refinement. In this way, we effectively adapt SAM for private use without any training. To further alleviate the mask ambiguity, we present an efficient one-shot fine-tuning variant, PerSAM-F. Freezing the entire SAM, we introduce two learnable weights for multi-scale masks, only training 2 parameters within 10 seconds for improved performance. To demonstrate our efficacy, we construct a new segmentation dataset, PerSeg, for personalized evaluation, and test our methods on video object segmentation with competitive performance. Besides, our approach can also enhance DreamBooth to personalize Stable Diffusion for text-to-image generation, which discards the background disturbance for better target appearance learning. Code is released at https://github.com/ZrrSkywalker/Personalize-SAM

cs.CV↗
arXiv2023

Atomic-scale mechanism of enhanced electron-phonon coupling at the interface of MgB$_2$ thin film

In this study, we explore the heterointerface of MgB$_2$ film on SiC substrate at atomic scale using electron microscopy and spectroscopy. We detect ~1 nm MgO between MgB$_2$ and SiC. Atomic-level electron energy loss spectra (EELS) show MgB$_2$-E2g mode splitting and softening near the MgB$_2$/MgO interface. Orbital-resolved core-level EELS link the phonon softening to in-plane boron-atom electron states' changes. Ab initio calculations confirm this softening enhances electron-phonon coupling at the interface. Our findings highlight interface engineering's potential for superconductivity enhancement.

cond-mat.supr-con↗
arXiv2023

Ratios conjecture for primitive quadratic Hecke $L$-functions

We develop the ratios conjecture with one shift in the numerator and denominator in certain ranges for families of primitive quadratic Hecke $L$-functions of imaginary quadratic number fields with class number one using multiple Dirichlet series under the generalized Riemann hypothesis. We also obtain unconditional asymptotic formulas for the first moments of central values of these families of $L$-functions with error terms of size that is the square root of that of the primary main terms.

math.NT↗
arXiv2023

Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill

Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the locomotion part, most works still depend on map-based planning approaches. The gap between RGB space and map space makes it difficult to directly transfer the knowledge from foundation models to navigation tasks. In this work, we propose a Pixel-guided Navigation skill (PixNav), which bridges the gap between the foundation models and the embodied navigation task. It is straightforward for recent foundation models to indicate an object by pixels, and with pixels as the goal specification, our method becomes a versatile navigation policy towards all different kinds of objects. Besides, our PixNav is a pure RGB-based policy that can reduce the cost of home-assistance robots. Experiments demonstrate the robustness of the PixNav which achieves 80+% success rate in the local path-planning task. To perform long-horizon object navigation, we design an LLM-based planner to utilize the commonsense knowledge between objects and rooms to select the best waypoint. Evaluations across both photorealistic indoor simulators and real-world environments validate the effectiveness of our proposed navigation strategy. Code and video demos are available at https://github.com/wzcai99/Pixel-Navigator.

cs.RO↗
arXiv2023

Nanoscale Cathodoluminescence Spectroscopy Probing the Nitride Quantum Wells in an Electron Microcope

To gain a deeper understanding of the luminescence of multiquantum wells and the factors affecting it on a microscopic level, cathodoluminescence combined with scanning transmission electron microscopy and spectroscopy was used to reveal the luminescence of In0.15Ga0.85N five-period multiquantum wells. The composition-wave-energy relationship was established in combination with energy-dispersive X-ray spectroscopy , and the bandgaps of In0.15Ga0.85N and GaN in multiple quantum wells were extracted by electron energy loss spectroscopy to understand the features of cathodoluminescence luminescence spectra. The luminescence differences between different periods of multiquantum wells and the effects on the luminescence of multiple quantum wells owing to defects such as composition fluctuation and dislocations were revealed. Our study establishing the direct correspondence between the atomic structure of InxGa1-xN multiquantum wells and photoelectric properties, provides useful information for nitride applications.

physics.app-ph↗
arXiv2023

ImageBind-LLM: Multi-modality Instruction Tuning

We present ImageBind-LLM, a multi-modality instruction tuning method of large language models (LLMs) via ImageBind. Existing works mainly focus on language and image instruction tuning, different from which, our ImageBind-LLM can respond to multi-modality conditions, including audio, 3D point clouds, video, and their embedding-space arithmetic by only image-text alignment training. During training, we adopt a learnable bind network to align the embedding space between LLaMA and ImageBind's image encoder. Then, the image features transformed by the bind network are added to word tokens of all layers in LLaMA, which progressively injects visual instructions via an attention-free and zero-initialized gating mechanism. Aided by the joint embedding of ImageBind, the simple image-text training enables our model to exhibit superior multi-modality instruction-following capabilities. During inference, the multi-modality inputs are fed into the corresponding ImageBind encoders, and processed by a proposed visual cache model for further cross-modal embedding enhancement. The training-free cache model retrieves from three million image features extracted by ImageBind, which effectively mitigates the training-inference modality discrepancy. Notably, with our approach, ImageBind-LLM can respond to instructions of diverse modalities and demonstrate significant language generation quality. Code is released at https://github.com/OpenGVLab/LLaMA-Adapter.

cs.MM↗
arXiv2023

Atomic-scale observation of localized phonons at FeSe/SrTiO3 interface

In single unit-cell FeSe grown on SrTiO3, the superconductivity transition temperature features a significant enhancement. Local phonon modes at the interface associated with electron-phonon coupling may play an important role in the interface-induced enhancement. However, such phonon modes have eluded direct experimental observations. Indeed, the complicated atomic structure of the interface brings challenges to obtain the accurate structure-phonon relation knowledge from either experiment or theory, thus hindering our understanding of the enhancement mechanism. Here, we achieve direct characterizations of atomic structure and phonon modes at the FeSe/SrTiO3 interface with atomically resolved imaging and electron energy loss spectroscopy in a scanning transmission electron microscope. We find several phonon modes highly localized (~1.3 nm) at the unique double layer Ti-O termination at the interface, one of which (~ 83 meV) engages in strong interactions with the electrons in FeSe based on ab initio calculations. The electron-phonon coupling strength for such a localized interface phonon with short-range interactions is comparable to that of Fuchs-Kliewer (FK) phonon mode with long-rang interactions. Thus, our atomic-scale study provides new insights into understanding the origin of superconductivity enhancement at the FeSe/SrTiO3 interface.

cond-mat.supr-con↗
arXiv2023

Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM.

cs.CV↗