arXiv subjects

Yong Zhang

Publications and source records attributed to Yong Zhang.

At least 289 records · Page 16Linked to original sources

arXiv2024

Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning

Prompt-based learning paradigm has demonstrated remarkable efficacy in enhancing the adaptability of pretrained language models (PLMs), particularly in few-shot scenarios. However, this learning paradigm has been shown to be vulnerable to backdoor attacks. The current clean-label attack, employing a specific prompt as a trigger, can achieve success without the need for external triggers and ensure correct labeling of poisoned samples, which is more stealthy compared to the poisoned-label attack, but on the other hand, it faces significant issues with false activations and poses greater challenges, necessitating a higher rate of poisoning. Using conventional negative data augmentation methods, we discovered that it is challenging to trade off between effectiveness and stealthiness in a clean-label setting. In addressing this issue, we are inspired by the notion that a backdoor acts as a shortcut and posit that this shortcut stems from the contrast between the trigger and the data utilized for poisoning. In this study, we propose a method named Contrastive Shortcut Injection (CSI), by leveraging activation values, integrates trigger design and data selection strategies to craft stronger shortcut features. With extensive experiments on full-shot and few-shot text classification tasks, we empirically validate CSI's high effectiveness and high stealthiness at low poisoning rates. Notably, we found that the two approaches play leading roles in full-shot and few-shot settings, respectively.

cs.LG↗

arXiv2024

GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation

Knowledge distillation from LLMs is essential for the efficient deployment of language models. Prior works have proposed data generation using LLMs for preparing distilled models. We argue that generating data with LLMs is prone to sampling mainly from the center of original content distribution. This limitation hinders the distilled model from learning the true underlying data distribution and to forget the tails of the distributions (samples with lower probability). To this end, we propose GOLD, a task-agnostic data generation and knowledge distillation framework, which employs an iterative out-of-distribution-guided feedback mechanism for the LLM. As a result, the generated data improves the generalizability of distilled models. An energy-based OOD evaluation approach is also introduced to deal with noisy generated data. Our extensive experiments on 10 different classification and sequence-to-sequence tasks in NLP show that GOLD respectively outperforms prior arts and the LLM with an average improvement of 5% and 14%. We will also show that the proposed method is applicable to less explored and novel tasks. The code is available.

cs.CL↗

arXiv2024

E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion

This paper proposes a novel approach to face swapping from the perspective of fine-grained facial editing, dubbed "editing for swapping" (E4S). The traditional face swapping methods rely on global feature extraction and fail to preserve the detailed source identity. In contrast, we propose a Regional GAN Inversion (RGI) method, which allows the explicit disentanglement of shape and texture. Specifically, our E4S performs face swapping in the latent space of a pretrained StyleGAN, where a multi-scale mask-guided encoder is applied to project the texture of each facial component into regional style codes and a mask-guided injection module manipulating feature maps with the style codes. Based on this disentanglement, face swapping can be simplified as style and mask swapping. Besides, due to the large lighting condition gap, transferring the source skin into the target image may lead to disharmony lighting. We propose a re-coloring network to make the swapped face maintain the target lighting condition while preserving the source skin. Further, to deal with the potential mismatch areas during mask exchange, we design a face inpainting module to refine the face shape. The extensive comparisons with state-of-the-art methods demonstrate that our E4S outperforms existing methods in preserving texture, shape, and lighting. Our implementation is available at https://github.com/e4s2024/E4S2024.

cs.CV↗

arXiv2024

Artificial Intelligence for Operations Research: Revolutionizing the Operations Research Process

The rapid advancement of artificial intelligence (AI) techniques has opened up new opportunities to revolutionize various fields, including operations research (OR). This survey paper explores the integration of AI within the OR process (AI4OR) to enhance its effectiveness and efficiency across multiple stages, such as parameter generation, model formulation, and model optimization. By providing a comprehensive overview of the state-of-the-art and examining the potential of AI to transform OR, this paper aims to inspire further research and innovation in the development of AI-enhanced OR methods and tools. The synergy between AI and OR is poised to drive significant advancements and novel solutions in a multitude of domains, ultimately leading to more effective and efficient decision-making.

math.OC↗

arXiv2024

Advanced tools for basis decompositions of genus-one string integrals

In string theories, one-loop scattering amplitudes are characterized by integrals over genus-one surfaces using the Kronecker-Eisenstein series. A recent methodology proposed a genus-one basis formed from products of these series of chain topologies. A prior work further deconstructed cyclic products of the Kronecker-Eisenstein series on this basis. Building on it, our study further employs advanced and comprehensive combinatorial techniques to decompose more general genus-one integrands including a product of an arbitrary number of cyclic products of Kronecker-Eisenstein series, supplemented by {\tt Mathematica} codes. Our insights enhance the understanding of multiparticle amplitudes across various string theories and illuminate loop-level parallels with string tree-level amplitudes.

hep-th↗

arXiv2024

Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework

Despite the remarkable process of talking-head-based avatar-creating solutions, directly generating anchor-style videos with full-body motions remains challenging. In this study, we propose Make-Your-Anchor, a novel system necessitating only a one-minute video clip of an individual for training, subsequently enabling the automatic generation of anchor-style videos with precise torso and hand movements. Specifically, we finetune a proposed structure-guided diffusion model on input video to render 3D mesh conditions into human appearances. We adopt a two-stage training strategy for the diffusion model, effectively binding movements with specific appearances. To produce arbitrary long temporal video, we extend the 2D U-Net in the frame-wise diffusion model to a 3D style without additional training cost, and a simple yet effective batch-overlapped temporal denoising module is proposed to bypass the constraints on video length during inference. Finally, a novel identity-specific face enhancement module is introduced to improve the visual quality of facial regions in the output videos. Comparative experiments demonstrate the effectiveness and superiority of the system in terms of visual quality, temporal coherence, and identity preservation, outperforming SOTA diffusion/non-diffusion methods. Project page: \url{https://github.com/ICTMCG/Make-Your-Anchor}.

cs.CV↗

arXiv2024

EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often use a few metrics, e.g., FVD or IS, to evaluate the performance. We argue that it is hard to judge the large conditional generative models from the simple metrics since these models are often trained on very large datasets with multi-aspect abilities. Thus, we propose a novel framework and pipeline for exhaustively evaluating the performance of the generated videos. Our approach involves generating a diverse and comprehensive list of 700 prompts for text-to-video generation, which is based on an analysis of real-world user data and generated with the assistance of a large language model. Then, we evaluate the state-of-the-art video generative models on our carefully designed benchmark, in terms of visual qualities, content qualities, motion qualities, and text-video alignment with 17 well-selected objective metrics. To obtain the final leaderboard of the models, we further fit a series of coefficients to align the objective metrics to the users' opinions. Based on the proposed human alignment method, our final score shows a higher correlation than simply averaging the metrics, showing the effectiveness of the proposed evaluation method.

cs.CV↗

arXiv2024

BjTT: A Large-scale Multimodal Dataset for Traffic Prediction

Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges. 1) insensitivity to unusual events. 2) limited performance in long-term prediction. In this work, we explore how generative models combined with text describing the traffic system can be applied for traffic generation, and name the task Text-to-Traffic Generation (TTG). The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations. To this end, we propose ChatTraffic, the first diffusion model for text-to-traffic generation. To guarantee the consistency between synthetic and real data, we augment a diffusion model with the Graph Convolutional Network (GCN) to extract spatial correlations of traffic data. In addition, we construct a large dataset containing text-traffic pairs for the TTG task. We benchmarked our model qualitatively and quantitatively on the released dataset. The experimental results indicate that ChatTraffic can generate realistic traffic situations from the text. Our code and dataset are available at https://github.com/ChyaZhang/ChatTraffic.

cs.AI↗

arXiv2024

Observation of quantum oscillations near the Mott-Ioffe-Regel limit in CaAs3

The Mott-Ioffe-Regel limit sets the lower bound of carrier mean free path for coherent quasiparticle transport. Metallicity beyond this limit is of great interest because it is often closely related to quantum criticality and unconventional superconductivity. Progress along this direction mainly focuses on the strange-metal behaviors originating from the evolution of quasiparticle scattering rate such as linear-in-temperature resistivity, while the quasiparticle coherence phenomena in this regime are much less explored due to the short mean free path at the diffusive bound. Here we report the observation of quantum oscillations from Landau quantization near the Mott-Ioffe-Regel limit in CaAs3. Despite the insulator-like temperature dependence of resistivity, CaAs3 presents giant magnetoresistance and prominent Shubnikov-de Haas oscillations from Fermi surfaces, indicating highly coherent band transport. In contrast, the quantum oscillation is absent in the magnetic torque. The quasiparticle effective mass increases systematically with magnetic fields, manifesting a much larger value than the expectation given by magneto-infrared spectroscopy. It suggests a strong many-body renormalization effect near Fermi surface. We find that these unconventional behaviors may be explained by the interplay between the mobility edge and the van Hove singularity, which results in the formation of coherent cyclotron orbits emerging at the diffusive bound. Our results call for further study on the electron correlation effect of the van Hove singularity.

cond-mat.str-el↗

arXiv2024

Excited-State OH Masers in the Water Fountain Source IRAS 18460-0151

Water fountain objects are generally defined as "evolved stars with low to intermediate initial mass accompanied by high-velocity molecular jets detectable in the 22.235 GHz H$_2$O maser line". They are the key objects of understanding the morphological transitions of circumstellar envelopes during the post asymptotic giant branch phase. Masers are useful tools to trace the kinematic environments of the circumstellar envelopes. In this letter we report the discovery of exceptionally uncommon excited-state hydroxyl (ex-OH) masers at 4660 and 6031 MHz toward the water fountain source IRAS 18460-0151. These are the brightest ex-OH masers discovered in late-type objects to date. To the best of our knowledge, prior to the current work, no evolved stellar object has been observed in the 4660 MHz ex-OH maser line. The ground-state hydroxyl (g-OH) masers at 1612 and 1665 MHz are also observed. The velocity components of the 4660 MHz ex-OH maser line and the much weaker 1665 MHz g-OH maser line all can be seen in the 1612 MHz g-OH maser line profile. The blue-shifted components of the three masers are more intense than the red-shifted ones, in contrast to the ex-OH maser line at 6031 MHz. The relevance of the behaviors of the ex-OH masers to the circumstellar environments is unclear.

astro-ph.GA↗

arXiv2024

A Causal Inspired Early-Branching Structure for Domain Generalization

Learning domain-invariant semantic representations is crucial for achieving domain generalization (DG), where a model is required to perform well on unseen target domains. One critical challenge is that standard training often results in entangled semantic and domain-specific features. Previous works suggest formulating the problem from a causal perspective and solving the entanglement problem by enforcing marginal independence between the causal (\ie semantic) and non-causal (\ie domain-specific) features. Despite its simplicity, the basic marginal independent-based idea alone may be insufficient to identify the causal feature. By d-separation, we observe that the causal feature can be further characterized by being independent of the domain conditioned on the object, and we propose the following two strategies as complements for the basic framework. First, the observation implicitly implies that for the same object, the causal feature should not be associated with the non-causal feature, revealing that the common practice of obtaining the two features with a shared base feature extractor and two lightweight prediction heads might be inappropriate. To meet the constraint, we propose a simple early-branching structure, where the causal and non-causal feature obtaining branches share the first few blocks while diverging thereafter, for better structure design; Second, the observation implies that the causal feature remains invariant across different domains for the same object. To this end, we suggest that augmentation should be incorporated into the framework to better characterize the causal feature, and we further suggest an effective random domain sampling scheme to fulfill the task. Theoretical and experimental results show that the two strategies are beneficial for the basic marginal independent-based framework. Code is available at \url{https://github.com/liangchen527/CausEB}.

cs.CV↗

arXiv2024

The impact of microscale physics in continuous time random walks for hydrodynamic dispersion in disordered media

The continuous time random walk (CTRW) approach has been widely applied to model large-scale non-Fickian transport in the flow through disordered media. Often, the underlying microscopic transport mechanisms and disorder characteristics are not known, and their effect on large-scale solute dispersion is encoded by a heavy-tailed transition time distribution. Here we study how the microscale physics manifests in the CTRW framework, and how it affects solute dispersion. To this end, we consider transport in disordered media with random sorption and random flow properties. Both disorder mechanisms can give rise to anomalous particle transport. We present the CTRW models corresponding to each of these physical scenarios to discuss the different manifestations of microscale heterogeneity on large-scale dispersion depending on the particle injection modes. The combined impact of random sorption and advection is studied with a novel CTRW model that explicitly represents both microscale disorder mechanisms. While random advection and sorption may show similar large-scale transport behaviors, they can be clearly distinguished in their response to uniform injection conditions, and, in general, to initial particle distributions that are not flux-weighted. These findings highlight the importance of the microscale physics for the interpretation and prediction of anomalous dispersion phenomena in disordered media.

physics.flu-dyn↗

arXiv2024

Color-Dressed Generalized Biadjoint Scalar Amplitudes: Local Planarity

The biadjoint scalar theory has cubic interactions and fields transforming in the biadjoint representation of ${\rm SU}(N)\times {\rm SU}\big({\tilde N}\big)$. Amplitudes are "color" decomposed in terms of partial amplitudes computed using Feynman diagrams which are simultaneously planar with respect to two orderings. In 2019, a generalization of biadjoint scalar amplitudes based on generalized Feynman diagrams (GFDs) was introduced. GFDs are collections of Feynman diagrams derived by incorporating an additional constraint of "local planarity" into the construction of the arrangements of metric trees in combinatorics. In this work, we propose a natural generalization of color orderings which leads to color-dressed amplitudes. A generalized color ordering (GCO) is defined as a collection of standard color orderings that is induced, in a precise sense, from an arrangement of projective lines on $\mathbb{RP}^2$. We present results for $n\leq 9$ generalized color orderings and GFDs, uncovering new phenomena in each case. We discover generalized decoupling identities and propose a definition of the "colorless" generalized scalar amplitude. We also propose a notion of GCOs for arbitrary $\mathbb{RP}^{k-1}$, discuss some of their properties, and comment on their GFDs. In a companion paper, we explore the definition of partial amplitudes using CEGM integral formulas.

hep-th↗

arXiv2024

Generation of True Quantum Random Numbers with On-Demand Probability Distributions via Single-Photon Quantum Walks

Random numbers are at the heart of diverse fields, ranging from simulations of stochastic processes to classical and quantum cryptography. The requirement for true randomness in these applications has motivated various proposals for generating random numbers based on the inherent randomness of quantum systems. The generation of true random numbers with arbitrarily defined probability distributions is highly desirable for applications, but it is very challenging. Here we show that single-photon quantum walks can generate multi-bit random numbers with on-demand probability distributions, when the required ``coin'' parameters are found with the gradient descent (GD) algorithm. Our theoretical and experimental results exhibit high fidelity for various selected distributions. This GD-enhanced single-photon system provides a convenient way for building flexible and reliable quantum random number generators. Multi-bit random numbers are a necessary resource for high-dimensional quantum key distribution.

quant-ph↗

arXiv2024

The Jiao Tong University Spectroscopic Telescope Project

The Jiao Tong University Spectroscopic Telescope (JUST) is a 4.4-meter f/6.0 segmentedmirror telescope dedicated to spectroscopic observations. The JUST primary mirror is composed of 18 hexagonal segments, each with a diameter of 1.1 m. JUST provides two Nasmyth platforms for placing science instruments. One Nasmyth focus fits a field of view of 10 arcmin and the other has an extended field of view of 1.2 deg with correction optics. A tertiary mirror is used to switch between the two Nasmyth foci. JUST will be installed at a site at Lenghu in Qinghai Province, China, and will conduct spectroscopic observations with three types of instruments to explore the dark universe, trace the dynamic universe, and search for exoplanets: (1) a multi-fiber (2000 fibers) medium-resolution spectrometer (R=4000-5000) to spectroscopically map galaxies and large-scale structure; (2) an integral field unit (IFU) array of 500 optical fibers and/or a long-slit spectrograph dedicated to fast follow-ups of transient sources for multimessenger astronomy; (3) a high-resolution spectrometer (R~100000) designed to identify Jupiter analogs and Earth-like planets, with the capability to characterize the atmospheres of hot exoplanets.

astro-ph.IM↗

arXiv2024

GTC Spectroscopic Surveys of Planetary Nebulae in the Milky Way and M31

We report spectroscopic surveys of planetary nebulae (PNe) in the Milky Way and Andromeda (M31), using the 10.4-m Gran Telescopio Canarias (GTC). The spectra are of high quality and cover the whole optical range, mostly from 3650 Å to beyond 1 micron, enabling detection of nebular emission lines critical for spectral analysis as well as photoionization modeling. We obtained GTC spectra of 24 compact (angular diameter <5 arcsec) PNe located in the Galactic disk, ~3-20 kpc from the Galactic centre, and can be used to constrain stellar evolution models and derive radial abundance gradients of the Milky Way. We have observed 30 PNe in the outer halo of M31 using the GTC. These halo PNe are uniformly metal-rich and probably all evolved from low-mass stars, consistent with the conjecture that they all formed from the metal-rich gas in M31 disk but displaced to their present locations due to galaxy interactions.

astro-ph.GA↗

arXiv2024

ChatTraffic: Text-to-Traffic Generation via Diffusion Model

cs.LG↗

arXiv2024

FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling

With the availability of large-scale video datasets and the advances of diffusion models, text-driven video generation has achieved substantial progress. However, existing video generation models are typically trained on a limited number of frames, resulting in the inability to generate high-fidelity long videos during inference. Furthermore, these models only support single-text conditions, whereas real-life scenarios often require multi-text conditions as the video content changes over time. To tackle these challenges, this study explores the potential of extending the text-driven capability to generate longer videos conditioned on multiple texts. 1) We first analyze the impact of initial noise in video diffusion models. Then building upon the observation of noise, we propose FreeNoise, a tuning-free and time-efficient paradigm to enhance the generative capabilities of pretrained video diffusion models while preserving content consistency. Specifically, instead of initializing noises for all frames, we reschedule a sequence of noises for long-range correlation and perform temporal attention over them by window-based function. 2) Additionally, we design a novel motion injection method to support the generation of videos conditioned on multiple text prompts. Extensive experiments validate the superiority of our paradigm in extending the generative capabilities of video diffusion models. It is noteworthy that compared with the previous best-performing method which brought about 255% extra time cost, our method incurs only negligible time cost of approximately 17%. Generated video samples are available at our website: http://haonanqiu.com/projects/FreeNoise.html.

cs.CV↗