arXiv subjects

Yu Tian

Publications and source records attributed to Yu Tian.

At least 217 records · Page 12Linked to original sources

arXiv2024

VisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understanding

The evolution of text to visual components facilitates people's daily lives, such as generating image, videos from text and identifying the desired elements within the images. Computer vision models involving the multimodal abilities in the previous days are focused on image detection, classification based on well-defined objects. Large language models (LLMs) introduces the transformation from nature language to visual objects, which present the visual layout for text contexts. OpenAI GPT-4 has emerged as the pinnacle in LLMs, while the computer vision (CV) domain boasts a plethora of state-of-the-art (SOTA) models and algorithms to convert 2D images to their 3D representations. However, the mismatching between the algorithms with the problem could lead to undesired results. In response to this challenge, we propose an unified VisionGPT-3D framework to consolidate the state-of-the-art vision models, thereby facilitating the development of vision-oriented AI. VisionGPT-3D provides a versatile multimodal framework building upon the strengths of multimodal foundation models. It seamlessly integrates various SOTA vision models and brings the automation in the selection of SOTA vision models, identifies the suitable 3D mesh creation algorithms corresponding to 2D depth maps analysis, generates optimal results based on diverse multimodal inputs such as text prompts. Keywords: VisionGPT-3D, 3D vision understanding, Multimodal agent

cs.CV↗

arXiv2024

Semantic Role Labeling Guided Out-of-distribution Detection

Identifying unexpected domain-shifted instances in natural language processing is crucial in real-world applications. Previous works identify the out-of-distribution (OOD) instance by leveraging a single global feature embedding to represent the sentence, which cannot characterize subtle OOD patterns well. Another major challenge current OOD methods face is learning effective low-dimensional sentence representations to identify the hard OOD instances that are semantically similar to the in-distribution (ID) data. In this paper, we propose a new unsupervised OOD detection method, namely Semantic Role Labeling Guided Out-of-distribution Detection (SRLOOD), that separates, extracts, and learns the semantic role labeling (SRL) guided fine-grained local feature representations from different arguments of a sentence and the global feature representations of the full sentence using a margin-based contrastive loss. A novel self-supervised approach is also introduced to enhance such global-local feature learning by predicting the SRL extracted role. The resulting model achieves SOTA performance on four OOD benchmarks, indicating the effectiveness of our approach. The code is publicly accessible via \url{https://github.com/cytai/SRLOOD}.

cs.CL↗

arXiv2024

Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection

Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies (i.e., samples from open-set anomaly classes), while effectively identifying the seen anomalies. Benefiting from the prior knowledge illustrated by the seen anomalies, current OSAD methods can often largely reduce false positive errors. However, these methods are trained in a closed-set setting and treat the anomaly examples as from a homogeneous distribution, rendering them less effective in generalizing to unseen anomalies that can be drawn from any distribution. This paper proposes to learn heterogeneous anomaly distributions using the limited anomaly examples to address this issue. To this end, we introduce a novel approach, namely Anomaly Heterogeneity Learning (AHL), that simulates a diverse set of heterogeneous anomaly distributions and then utilizes them to learn a unified heterogeneous abnormality model in surrogate open-set environments. Further, AHL is a generic framework that existing OSAD models can plug and play for enhancing their abnormality modeling. Extensive experiments on nine real-world anomaly detection datasets show that AHL can 1) substantially enhance different state-of-the-art OSAD models in detecting seen and unseen anomalies, and 2) effectively generalize to unseen anomalies in new domains. Code is available at https://github.com/mala-lab/AHL.

cs.CV↗

arXiv2024

VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework

With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In this paper, we introduce VisionGPT to consolidate and automate the integration of state-of-the-art foundation models, thereby facilitating vision-language understanding and the development of vision-oriented AI. VisionGPT builds upon a generalized multimodal framework that distinguishes itself through three key features: (1) utilizing LLMs (e.g., LLaMA-2) as the pivot to break down users' requests into detailed action proposals to call suitable foundation models; (2) integrating multi-source outputs from foundation models automatically and generating comprehensive responses for users; (3) adaptable to a wide range of applications such as text-conditioned image understanding/generation/editing and visual question answering. This paper outlines the architecture and capabilities of VisionGPT, demonstrating its potential to revolutionize the field of computer vision through enhanced efficiency, versatility, and generalization, and performance. Our code and models will be made publicly available. Keywords: VisionGPT, Open-world visual perception, Vision-language understanding, Large language model, and Foundation model

cs.CV↗

arXiv2024

A Parallel Beam Splitting Based on Gradient Metasurface: Preparation and Fusion of Quantum Entanglement

Gradient metasurface, formed by a set of subwavelength unit cells with different phase modulation, is widely used in polarized beam splitting (BS) in the classical and quantum optics. Specifically, its phase gradient allows the path and polarization of multiple output lights to be locked by corresponding inputs.Using this unique path-polarization locked property, we demonstrate that the single metasurface can function as sequentially linked beamsplitters, enabling the parallelization of a series of BS processes. Such a parallel BS metasurface provides a multi-beam interference capability for both classical and quantum light manipulation. Taking this advantage, we first prepare path and polarization hybrid entangled states of two, three, and multi photons from unentangled photon sources. Then, the ability of parallel BS-facilitated entanglement is applied to demonstrate entanglement fusion among entangled photon pairs, which can greatly enlarge the entanglement dimension. The principle of parallel BS through the metasurface opens up a versatile way to manipulate the quantum state at the micro/nano scale, which will have potential applications in on-chip quantum optics and quantum information processing.

physics.optics↗

arXiv2024

Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization

Fairness (also known as equity interchangeably) in machine learning is important for societal well-being, but limited public datasets hinder its progress. Currently, no dedicated public medical datasets with imaging data for fairness learning are available, though minority groups suffer from more health issues. To address this gap, we introduce Harvard Glaucoma Fairness (Harvard-GF), a retinal nerve disease dataset with both 2D and 3D imaging data and balanced racial groups for glaucoma detection. Glaucoma is the leading cause of irreversible blindness globally with Blacks having doubled glaucoma prevalence than other races. We also propose a fair identity normalization (FIN) approach to equalize the feature importance between different identity groups. Our FIN approach is compared with various the-state-of-the-art fairness learning methods with superior performance in the racial, gender, and ethnicity fairness tasks with 2D and 3D imaging data, which demonstrate the utilities of our dataset Harvard-GF for fairness learning. To facilitate fairness comparisons between different models, we propose an equity-scaled performance measure, which can be flexibly used to compare all kinds of performance metrics in the context of fairness. The dataset and code are publicly accessible via \url{https://ophai.hms.harvard.edu/datasets/harvard-glaucoma-fairness-3300-samples/}.

cs.CV↗

arXiv2024

WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs

Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content. However, it remains a formidable challenge pertaining to maintaining temporal consistency and ensuring action smoothness throughout the generated sequences. In this paper, we present an innovative video generation AI agent that harnesses the power of Sora-inspired multimodal learning to build skilled world models framework based on textual prompts and accompanying images. The framework includes two parts: prompt enhancer and full video translation. The first part employs the capabilities of ChatGPT to meticulously distill and proactively construct precise prompts for each subsequent step, thereby guaranteeing the utmost accuracy in prompt communication and accurate execution in following model operations. The second part employ compatible with existing advanced diffusion techniques to expansively generate and refine the key frame at the conclusion of a video. Then we can expertly harness the power of leading and trailing key frames to craft videos with enhanced temporal consistency and action smoothness. The experimental results confirm that our method has strong effectiveness and novelty in constructing world models from text and image inputs over the other methods.

cs.CV↗

arXiv2024

Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters

We propose a novel framework for filtering image-text data by leveraging fine-tuned Multimodal Language Models (MLMs). Our approach outperforms predominant filtering methods (e.g., CLIPScore) via integrating the recent advances in MLMs. We design four distinct yet complementary metrics to holistically measure the quality of image-text data. A new pipeline is established to construct high-quality instruction data for fine-tuning MLMs as data filters. Comparing with CLIPScore, our MLM filters produce more precise and comprehensive scores that directly improve the quality of filtered data and boost the performance of pre-trained models. We achieve significant improvements over CLIPScore on popular foundation models (i.e., CLIP and BLIP2) and various downstream tasks. Our MLM filter can generalize to different models and tasks, and be used as a drop-in replacement for CLIPScore. An additional ablation study is provided to verify our design choices for the MLM filter.

cs.CV↗

arXiv2024

Emergence of Large-Scale Structures in Holographic Superfluid Turbulence

In two-dimensional turbulence systems, the emergence of large-scale structures holds profound physical implications, particularly as it indicates the occurrence of inverse energy cascades, thereby garnering significant attention. In this paper, we report a novel vortex clusters formation in the background of near-extreme Reissner-Nordstr$\ddot{o}$m black hole holographic model. At temperatures nearing absolute zero, we observe not only the formation of vortex clusters but also the emergence of an inverse energy cascade. Distinct from typical quantum systems, the genesis of holographic vortex clusters is rooted in unique quantum dissipation properties, characterized by the near immobilization of vortex dipoles at low temperatures. Through a comparative analysis with the dynamics of the Gross-Pitaevskii equation, our investigation enhances the understanding of inverse energy cascades under these extreme conditions, thereby broadening our comprehension of quantum turbulence.

hep-th↗

arXiv2024

BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators

Extremely large image generators offer significant transformative potential across diverse sectors. It allows users to design specific prompts to generate realistic images through some black-box APIs. However, some studies reveal that image generators are notably susceptible to attacks and generate Not Suitable For Work (NSFW) contents by manually designed toxin texts, especially imperceptible to human observers. We urgently need a multitude of universal and transferable prompts to improve the safety of image generators, especially black-box-released APIs. Nevertheless, they are constrained by labor-intensive design processes and heavily reliant on the quality of the given instructions. To achieve this, we introduce a black-box stealthy prompt attack (BSPA) that adopts a retriever to simulate attacks from API users. It can effectively harness filter scores to tune the retrieval space of sensitive words for matching the input prompts, thereby crafting stealthy prompts tailored for image generators. Significantly, this approach is model-agnostic and requires no internal access to the model's features, ensuring its applicability to a wide range of image generators. Building on BSPA, we have constructed an automated prompt tool and a comprehensive prompt attack dataset (NSFWeval). Extensive experiments demonstrate that BSPA effectively explores the security vulnerabilities in a variety of state-of-the-art available black-box models, including Stable Diffusion XL, Midjourney, and DALL-E 2/3. Furthermore, we develop a resilient text filter and offer targeted recommendations to ensure the security of image generators against prompt attacks in the future.

cs.CR↗

arXiv2024

Envisioning the Future Role of 3D Wireless Networks in Preventing and Managing Disasters and Emergency Situations

In an era marked by unprecedented climatic upheavals and evolving urban landscapes, the role of advanced communication networks in disaster prevention and management is becoming increasingly critical. This paper explores the transformative potential of 3D wireless networks, an innovative amalgamation of terrestrial, aerial, and satellite technologies, in enhancing disaster response mechanisms. We delve into a myriad of use cases, ranging from large facility evacuations to wildfire management, underscoring the versatility of these networks in ensuring timely communication, real-time situational awareness, and efficient resource allocation during crises. We also present an overview of cutting-edge prototypes, highlighting the practical feasibility and operational efficacy of 3D wireless networks in real-world scenarios. Simultaneously, we acknowledge the challenges posed by aspects such as cybersecurity, cross-border coordination, and physical layer technological hurdles, and propose future directions for research and development in this domain.

cs.NI↗

arXiv2024

A Novel Approach to WaveNet Architecture for RF Signal Separation with Learnable Dilation and Data Augmentation

In this paper, we address the intricate issue of RF signal separation by presenting a novel adaptation of the WaveNet architecture that introduces learnable dilation parameters, significantly enhancing signal separation in dense RF spectrums. Our focused architectural refinements and innovative data augmentation strategies have markedly improved the model's ability to discern complex signal sources. This paper details our comprehensive methodology, including the refined model architecture, data preparation techniques, and the strategic training strategy that have been pivotal to our success. The efficacy of our approach is evidenced by the substantial improvements recorded: a 58.82\% increase in SINR at a BER of $10^{-3}$ for OFDM-QPSK with EMI Signal 1, surpassing traditional benchmarks. Notably, our model achieved first place in the challenge \cite{datadrivenrf2024}, demonstrating its superior performance and establishing a new standard for machine learning applications within the RF communications domain.

eess.SP↗

arXiv2024

Evil Geniuses: Delving into the Safety of LLM-based Agents

Rapid advancements in large language models (LLMs) have revitalized in LLM-based agents, exhibiting impressive human-like behaviors and cooperative capabilities in various scenarios. However, these agents also bring some exclusive risks, stemming from the complexity of interaction environments and the usability of tools. This paper delves into the safety of LLM-based agents from three perspectives: agent quantity, role definition, and attack level. Specifically, we initially propose to employ a template-based attack strategy on LLM-based agents to find the influence of agent quantity. In addition, to address interaction environment and role specificity issues, we introduce Evil Geniuses (EG), an effective attack method that autonomously generates prompts related to the original role to examine the impact across various role definitions and attack levels. EG leverages Red-Blue exercises, significantly improving the generated prompt aggressiveness and similarity to original roles. Our evaluations on CAMEL, Metagpt and ChatDev based on GPT-3.5 and GPT-4, demonstrate high success rates. Extensive evaluation and discussion reveal that these agents are less robust, prone to more harmful behaviors, and capable of generating stealthier content than LLMs, highlighting significant safety challenges and guiding future research. Our code is available at https://github.com/T1aNS1R/Evil-Geniuses.

cs.CL↗

arXiv2024

Spreading and Structural Balance on Signed Networks

Two competing types of interactions often play an important part in shaping system behavior, such as activatory or inhibitory functions in biological systems. Hence, signed networks, where each connection can be either positive or negative, have become popular models over recent years. However, the primary focus of the literature is on the unweighted and structurally unbalanced ones, where all cycles have an even number of negative edges. Hence here, we first introduce a classification of signed networks into balanced, antibalanced or strictly unbalanced ones, and then characterize each type of signed networks in terms of the spectral properties of the signed weighted adjacency matrix. In particular, we show that the spectral radius of the matrix with signs is smaller than that without if and only if the signed network is strictly unbalanced. These properties are important to understand the dynamics on signed networks, both linear and nonlinear ones. Specifically, we find consistent patterns in a linear and a nonlinear dynamics theoretically, depending on their type of balance. We also propose two measures to further characterize strictly unbalanced networks, motivated by perturbation theory. Finally, we numerically verify these properties through experiments on both synthetic and real networks.

cs.SI↗

arXiv2024

Quench Dynamics in Holographic First-Order Phase Transition

In this work, we investigate the real-time dynamics of quenching a state from phase separation in a holographic model of first-order phase transition. In addition to the typical phase-separated and high-energy final states, we have discovered a novel dynamical process that drives the system to a low-temperature supercooled final state within a narrow range of quench parameters. The critical behavior is also revealed during the fully non-linear dynamics. Following a sudden quench with critical parameters, the phase separation can be attracted to a critical nucleus. Specifically, the critical nucleus will subsequently shrink in size and eventually disappear for super-critical parameters, where the system is actually supercooled with a temperature lower than the initial one. While for sub-critical parameters, the nucleus will grow in size and finally reform a phase separation, where the absorbed quenching energy is reflected in the increment of the latent heat.

hep-th↗

arXiv2023

Large Generative AI Models for Telecom: The Next Big Thing?

The evolution of generative artificial intelligence (GenAI) constitutes a turning point in reshaping the future of technology in different aspects. Wireless networks in particular, with the blooming of self-evolving networks, represent a rich field for exploiting GenAI and reaping several benefits that can fundamentally change the way how wireless networks are designed and operated nowadays. To be specific, large GenAI models are envisioned to open up a new era of autonomous wireless networks, in which multi-modal GenAI models trained over various Telecom data, can be fine-tuned to perform several downstream tasks, eliminating the need for building and training dedicated AI models for each specific task and paving the way for the realization of artificial general intelligence (AGI)-empowered wireless networks. In this article, we aim to unfold the opportunities that can be reaped from integrating large GenAI models into the Telecom domain. In particular, we first highlight the applications of large GenAI models in future wireless networks, defining potential use-cases and revealing insights on the associated theoretical and practical challenges. Furthermore, we unveil how 6G can open up new opportunities through connecting multiple on-device large GenAI models, and hence, paves the way to the collective intelligence paradigm. Finally, we put a forward-looking vision on how large GenAI models will be the key to realize self-evolving networks.

cs.CL↗

arXiv2023

Entanglement of defect subregions in double holography

In the framework of double holography, we investigate the entanglement behavior of a brane subregion in AdS spacetime coupled to a bath on its boundary and also extract the contribution from the quantum matter within this subregion. From the boundary perspective, the brane subregion serves as the entanglement wedge of a subsystem on the conformal defect. In the ground state, we find the subsystem undergoes an entanglement phase transition induced by the degrees of freedom on the brane. With subcritical parameters, the wedge and entanglement entropy sharply decrease to zero. In contrast, in the supercritical regime, both the wedge and entropy stabilize, enabling analysis of both entanglement and reflected entropy. In this phase, we derive formulas for entanglement measures based on defect and bath central charges in the semi-classical limit. For entanglement entropy, the classical geometry only contributes a subleading term with logarithmic divergence, but the brane-bath CFT entanglement exhibits a dominant linear divergence, even in the semi-classical limit. Regarding reflected entropy within the defect subsystem, classical geometry contributes a leading term with logarithmic divergence, while the quantum matter within the entanglement wedge only contributes a finite term.

hep-th↗

arXiv2023

Protected Transverse Electric Waves in Topological Dielectric Waveguides

Waveguides are fundamental components in communication systems. However, they suffer from reflection and scattering losses at sharp routes or defects. The breakthrough in developing topological photonic crystals (PhCs) provides promising solutions to robust signal transmission. In this work, we propose a new mechanism for protecting wave-guiding modes by decorating the boundaries of a conventional waveguide with valley-Hall PhCs. This special layout enables the robust propagation of conventional transverse electric waves against defects and bends. Moreover, the proposed waveguide is compatible with the substrate integrated waveguide (SIW). High efficient mode conversion from the SIW to the proposed waveguide is achievable. By leveraging the idea of topology to conventional waveguides, we provide a powerful and practical tool that can largely improve the performance of microwave and millimeter-wave integrated circuits while reserving the features of wave-guiding modes.

physics.app-ph↗