arXiv subjects

Jie Liu

Publications and source records attributed to Jie Liu.

At least 361 records · Page 20Linked to original sources

arXiv2024

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Recent advancements have seen Large Language Models (LLMs) and Large Multimodal Models (LMMs) surpassing general human capabilities in various tasks, approaching the proficiency level of human experts across multiple domains. With traditional benchmarks becoming less challenging for these models, new rigorous challenges are essential to gauge their advanced abilities. In this work, we present OlympiadBench, an Olympiad-level bilingual multimodal scientific benchmark, featuring 8,476 problems from Olympiad-level mathematics and physics competitions, including the Chinese college entrance exam. Each problem is detailed with expert-level annotations for step-by-step reasoning. Evaluating top-tier models on OlympiadBench, we implement a comprehensive assessment methodology to accurately evaluate model responses. Notably, the best-performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. Our analysis orienting GPT-4V points out prevalent issues with hallucinations, knowledge omissions, and logical fallacies. We hope that our challenging benchmark can serve as a valuable resource for helping future AGI research endeavors. The data and evaluation code are available at \url{https://github.com/OpenBMB/OlympiadBench}

cs.CL↗

arXiv2024

Constant-roll inflation with non-minimally derivative coupling

We investigate the constant-roll inflation with non-minimally kinetic coupling to the Einstein tensor. With the slow-roll parameter $η_ϕ= -\ddotϕ/(H\dotϕ)$ being a constant, we calculate the power spectra for scalar and tensor perturbations, and derive the expressions for the scalar spectral tilt $n_s$, the tensor spectral tilt $n_T$, and the tensor-to-scalar ratio $r$. We find that the expressions for $n_s$ are different with different ordering of taking the derivative of the scalar power spectrum with respect to the scale $k$ and the horizon crossing condition $c_sk=aH$ in the constant-roll inflation, the consistency relation $r=-8n_T$ does not hold if $|η_ϕ|$ is not small, and the duality of the tensor-to-scalar ratio between the slow-roll inflation and ultra-slow-roll inflation does not exist in inflationary models with non-minimally derivative coupling. The result offers a fresh perspective on the understanding of the inflationary models with non-minimally derivative coupling and is helpful for the production of scalar induced gravitational waves in the framework of ultra-slow-roll inflation with non-minimally derivative coupling.

gr-qc↗

arXiv2024

Unsupervised Domain Adaptation for Low-dose CT Reconstruction via Bayesian Uncertainty Alignment

Low-dose computed tomography (LDCT) image reconstruction techniques can reduce patient radiation exposure while maintaining acceptable imaging quality. Deep learning is widely used in this problem, but the performance of testing data (a.k.a. target domain) is often degraded in clinical scenarios due to the variations that were not encountered in training data (a.k.a. source domain). Unsupervised domain adaptation (UDA) of LDCT reconstruction has been proposed to solve this problem through distribution alignment. However, existing UDA methods fail to explore the usage of uncertainty quantification, which is crucial for reliable intelligent medical systems in clinical scenarios with unexpected variations. Moreover, existing direct alignment for different patients would lead to content mismatch issues. To address these issues, we propose to leverage a probabilistic reconstruction framework to conduct a joint discrepancy minimization between source and target domains in both the latent and image spaces. In the latent space, we devise a Bayesian uncertainty alignment to reduce the epistemic gap between the two domains. This approach reduces the uncertainty level of target domain data, making it more likely to render well-reconstructed results on target domains. In the image space, we propose a sharpness-aware distribution alignment to achieve a match of second-order information, which can ensure that the reconstructed images from the target domain have similar sharpness to normal-dose CT images from the source domain. Experimental results on two simulated datasets and one clinical low-dose imaging dataset show that our proposed method outperforms other methods in quantitative and visualized performance.

eess.IV↗

arXiv2024

Domain Adaptation with Cauchy-Schwarz Divergence

Domain adaptation aims to use training data from one or multiple source domains to learn a hypothesis that can be generalized to a different, but related, target domain. As such, having a reliable measure for evaluating the discrepancy of both marginal and conditional distributions is crucial. We introduce Cauchy-Schwarz (CS) divergence to the problem of unsupervised domain adaptation (UDA). The CS divergence offers a theoretically tighter generalization error bound than the popular Kullback-Leibler divergence. This holds for the general case of supervised learning, including multi-class classification and regression. Furthermore, we illustrate that the CS divergence enables a simple estimator on the discrepancy of both marginal and conditional distributions between source and target domains in the representation space, without requiring any distributional assumptions. We provide multiple examples to illustrate how the CS divergence can be conveniently used in both distance metric- or adversarial training-based UDA frameworks, resulting in compelling performance.

cs.LG↗

arXiv2024

Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomography

The advancement of artificial intelligence (AI) for organ segmentation and tumor detection is propelled by the growing availability of computed tomography (CT) datasets with detailed, per-voxel annotations. However, these AI models often struggle with flexibility for partially annotated datasets and extensibility for new classes due to limitations in the one-hot encoding, architectural design, and learning scheme. To overcome these limitations, we propose a universal, extensible framework enabling a single model, termed Universal Model, to deal with multiple public datasets and adapt to new classes (e.g., organs/tumors). Firstly, we introduce a novel language-driven parameter generator that leverages language embeddings from large language models, enriching semantic encoding compared with one-hot encoding. Secondly, the conventional output layers are replaced with lightweight, class-specific heads, allowing Universal Model to simultaneously segment 25 organs and six types of tumors and ease the addition of new classes. We train our Universal Model on 3,410 CT volumes assembled from 14 publicly available datasets and then test it on 6,173 CT volumes from four external datasets. Universal Model achieves first place on six CT tasks in the Medical Segmentation Decathlon (MSD) public leaderboard and leading performance on the Beyond The Cranial Vault (BTCV) dataset. In summary, Universal Model exhibits remarkable computational efficiency (6x faster than other dataset-specific models), demonstrates strong generalization across different hospitals, transfers well to numerous downstream tasks, and more importantly, facilitates the extensibility to new classes while alleviating the catastrophic forgetting of previously learned classes. Codes, models, and datasets are available at https://github.com/ljwztc/CLIP-Driven-Universal-Model

eess.IV↗

arXiv2024

Scalable and Versatile Linear Computation with Minimalistic Photonic Matrix Processor

The advancement of artificial intelligence demands flexible multimodal data processing with high throughput and energy efficiency. Photonic integrated circuits (PIC) has demonstrated promising potentials in terms of low latency and low power consumption per operation for linear operations such as matrix-vector multiplication. However, the existing schemes face challenges in their scalability due to the use of photonic circuits that expand with the scale of the operants, despite efforts of exploiting the multiple optical parameter dimensions such as time, wavelength and spatial parallelism. They also lacked flexibility and efficiency in switching between different types of operations or tasks and adapting to multimodal data. In this article, we introduce an optical matrix processor (MP) with a minimalistic recursive structure for both multiplications and accumulations. The MP consists of an eletro-optic ring-modulator implemented as a thin-film lithium niobate PIC that allows flexible configurability and time-division multiplexed scheduling. The MP supports not only versatile linear operations including vector/matrix-vector multiplication and single/multi-kernel convolution but also ultrafast task switching and adaptability to data of different sizes, by simply adjusting the data baud rate relative to the ring delay without structural modifications. We demonstrate its capabilities in a optic-electronic convolutional neural network with a computing throughput up to 73.4 billion operations per second. The MP further supports high scalability through appropriate allocation of wavelength and space resources,extending computing parallelism to handle higher data volumes with higher energy efficiency. This novel scheme paves the way for a new class of photonic processorscapable of managing escalating data workloads with unprecedented flexibility, efficiency and scalability.

physics.optics↗

arXiv2024

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models. Code and pretrained models are publicly available at github.com/Tencent/HunyuanDiT

cs.CV↗

arXiv2024

3DMeshNet: A Three-Dimensional Differential Neural Network for Structured Mesh Generation

Mesh generation is a crucial step in numerical simulations, significantly impacting simulation accuracy and efficiency. However, generating meshes remains time-consuming and requires expensive computational resources. In this paper, we propose a novel method, 3DMeshNet, for three-dimensional structured mesh generation. The method embeds the meshing-related differential equations into the loss function of neural networks, formulating the meshing task as an unsupervised optimization problem. It takes geometric points as input to learn the potential mapping between parametric and computational domains. After suitable offline training, 3DMeshNet can efficiently output a three-dimensional structured mesh with a user-defined number of quadrilateral/hexahedral cells through the feed-forward neural prediction. To enhance training stability and accelerate convergence, we integrate loss function reweighting through weight adjustments and gradient projection alongside applying finite difference methods to streamline derivative computations in the loss. Experiments on different cases show that 3DMeshNet is robust and fast. It outperforms neural network-based methods and yields superior meshes compared to traditional mesh partitioning methods. 3DMeshNet significantly reduces training times by up to 85% compared to other neural network-based approaches and lowers meshing overhead by 4 to 8 times relative to traditional meshing methods.

cs.GR↗

arXiv2024

Entanglement enhancement of two giant atoms with multiple connection points in bidirectional-chiral quantum waveguide-QED system

We study the entanglement generation of two giant atoms within a one-dimensional bidirectional-chiral waveguide quantum electrodynamics (QED) system, where the initial state of the two giant atoms are $|e_a,g_b\rangle $. Here, each giant atom is coupled to the waveguide through three connection points, with the configurations divided into five types based on the arrangement of coupling points between the giant atoms and the waveguide: separate, fully braided, partially braided, fully nested, and partially nested. We explore the entanglement generation process within each configuration in both nonchiral and chiral coupling cases. It is demonstrated that entanglement can be controlled as needed by either adjusting the phase shift or selecting different configurations. For nonchiral coupling, the entanglement of each configuration exhibits steady state properties attributable to the presence of dark state. In addition, we find that steady-state entanglement can be obtained at more phase shifts in certain configurations by increasing the number of coupling points between the giant atoms and the bidirectional waveguide. In the case of chiral coupling, the entanglement is maximally enhanced compared to the one of nonchiral case. Especially in fully braided configuration, the concurrence reaches its peak value 1, which is robust to chirality. We further show the influence of atomic initial states on the evolution of interatomic entanglement. Our scheme can be used for entanglement generation in chiral quantum networks of giant-atom waveguide-QED systems, with potential applications in quantum networks and quantum communications.

quant-ph↗

arXiv2024

High Spectral-Efficiency, Ultra-low MIMO SDM Transmission over a Field-Deployed Multi-Core OAM Fiber

Few-mode multi-core fiber (FM-MCF) based Space-Division Multiplexing (SDM) systems possess the potential to maximize the number of multiplexed spatial channels per fiber by harnessing both the space (fiber cores) and mode (optical mode per core) dimensions. However, to date, no SDM transmissions over field-deployed FM-MCFs in realistic outdoor settings have been reported, which contrasts with SDM schemes demonstrated using single-mode multi-core fibers (SM-MCFs) installed in practical fiber cable ducts. In this paper, we present the successful demonstration of bidirectional SDM transmission over a 5-km field-deployed seven ring-core fiber (7-RCF) with a cladding diameter of 178 $μ$m, achieving a Spectral Efficiency (SE) of 2$\times$201.6 bit/s/Hz. This work establishes a new record for the highest SE attained in SDM demonstrations utilizing field-deployed fiber cables, achieving an approximate 10x increase compared to the SE of reported field-deployed optical fiber cable transmission systems. Notably, these results are realized through the utilization of small-scale modular 4$\times$4 multiple-input multiple-output (MIMO) processing with a time-domain equalization (TDE) tap number not exceeding 15, maintaining a complexity per unit capacity comparable to that of MIMO equalization in SDM demonstrations employing weakly coupled SM-MCF cables. These results underscore the significant potential for achieving heightened SE and expanding capacity per individual fiber using SDM techniques in practical applications.

cs.NI↗

arXiv2024

SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition

Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in multilingual ASR, it is worth noting that various layers' representations potentially contain distinct information that has not been fully leveraged. In this study, we propose a novel method that leverages self-supervised hierarchical representations (SSHR) to fine-tune the MMS model. We first analyze the different layers of MMS and show that the middle layers capture language-related information, and the high layers encode content-related information, which gradually decreases in the final layers. Then, we extract a language-related frame from correlated middle layers and guide specific language extraction through self-attention mechanisms. Additionally, we steer the model toward acquiring more content-related information in the final layers using our proposed Cross-CTC. We evaluate SSHR on two multilingual datasets, Common Voice and ML-SUPERB, and the experimental results demonstrate that our method achieves state-of-the-art performance.

cs.CL↗

arXiv2024

Topological polarization singularities induced by the non-Hermitian Dirac points

A Dirac point in the Hermitian photonic system will split into a pair of exceptional points (EPs) or even spawn a ring of EPs if non-Hermiticity is involved. Here, we present a new type of non-Hermitian Dirac point which is situated in the complex plane of eigenfrequency. When there is differential loss, the Dirac point exhibits a dual behavior: it not only splits into a pair of EPs with opposite chirality in the band structure but also induces a pair of circularly polarized states (C points) with opposite handedness in the far-field radiation. Furthermore, breaking the corresponding mirror symmetries enables independent control of these Dirac-point induced C points, facilitating the merging of two C points and generation of unidirectional guided resonances. Our results demonstrate an explicit relation between the band singularities and polarization singularities, and provide a new mechanism to generate unidirectional emission, which can be useful in the band engineering and polarization manipulation.

physics.optics↗

arXiv2024

Accurate Chemical Reaction Modeling on Noisy Intermediate-Scale Quantum Computers Using a Noise-Resilient Wavefunction Ansatz

Quantum computing is of great potential for chemical system simulations. In this study, we propose an efficient protocol of quantum computer based simulation of chemical systems which enables accurate chemical reaction modeling on noisy intermediate-scale quantum (NISQ) devices. In this protocol, we combine an correlation energy-based active orbital selection, an effective Hamiltonian from the driven similarity renormalization group (DSRG) method, and a noise-resilient wavefunction ansatz. Such a combination gives a quantum resource-efficient way to accurately simulate chemical systems. The power of this protocol is demonstrated by numerical results for systems with up to tens of atoms. Modeling of a Diels-Alder (DA) reaction is also performed on a cloud-based superconducting quantum computer. These results represent an important step forward in realizing quantum utility in the NISQ era.

quant-ph↗

arXiv2024

Proposing an intelligent mesh smoothing method with graph neural networks

In CFD, mesh smoothing methods are commonly utilized to refine the mesh quality to achieve high-precision numerical simulations. Specifically, optimization-based smoothing is used for high-quality mesh smoothing, but it incurs significant computational overhead. Pioneer works improve its smoothing efficiency by adopting supervised learning to learn smoothing methods from high-quality meshes. However, they pose difficulty in smoothing the mesh nodes with varying degrees and also need data augmentation to address the node input sequence problem. Additionally, the required labeled high-quality meshes further limit the applicability of the proposed method. In this paper, we present GMSNet, a lightweight neural network model for intelligent mesh smoothing. GMSNet adopts graph neural networks to extract features of the node's neighbors and output the optimal node position. During smoothing, we also introduce a fault-tolerance mechanism to prevent GMSNet from generating negative volume elements. With a lightweight model, GMSNet can effectively smoothing mesh nodes with varying degrees and remain unaffected by the order of input data. A novel loss function, MetricLoss, is also developed to eliminate the need for high-quality meshes, which provides a stable and rapid convergence during training. We compare GMSNet with commonly used mesh smoothing methods on two-dimensional triangle meshes. The experimental results show that GMSNet achieves outstanding mesh smoothing performances with 5% model parameters of the previous model, and attains 13.56 times faster than optimization-based smoothing.

cs.CV↗

arXiv2024

A Unified Editing Method for Co-Speech Gesture Generation via Diffusion Inversion

Diffusion models have shown great success in generating high-quality co-speech gestures for interactive humanoid robots or digital avatars from noisy input with the speech audio or text as conditions. However, they rarely focus on providing rich editing capabilities for content creators other than high-level specialized measures like style conditioning. To resolve this, we propose a unified framework utilizing diffusion inversion that enables multi-level editing capabilities for co-speech gesture generation without re-training. The method takes advantage of two key capabilities of invertible diffusion models. The first is that through inversion, we can reconstruct the intermediate noise from gestures and regenerate new gestures from the noise. This can be used to obtain gestures with high-level similarities to the original gestures for different speech conditions. The second is that this reconstruction reduces activation caching requirements during gradient calculation, making the direct optimization on input noises possible on current hardware with limited memory. With different loss functions designed for, e.g., joint rotation or velocity, we can control various low-level details by automatically tweaking the input noises through optimization. Extensive experiments on multiple use cases show that this framework succeeds in unifying high-level and low-level co-speech gesture editing.

cs.HC↗

arXiv2024

The algebra of symmetric tensors on smooth projective varieties

We discuss in this note the algebra H^0(X, Sym*TX) for a smooth complex projective variety X . We compute it in some simple examples, and give a sharp bound on its Krull dimension. Then we propose a conjectural characterization of non-uniruled projective manifolds with pseudo-effective tangent bundle.

math.AG↗

arXiv2024

Nonperturbative aspects of two-dimensional $T\bar{T}$-deformed scalar theory from functional renormalization group

We study $T\bar{T}$-deformed $O(N)$ scalar field theory in two-dimensional spacetime using the functional renormalization group. We derive the $β$ functions for the couplings in the system and explore the fixed points. In addition to the Gaussian (trivial) fixed point, we find a nontrivial fixed point at which a new universality class exists. The deformation parameter becomes relevant at the nontrivial fixed point. Therefore, the $T\bar T$-deformed scalar field theory in two-dimensional spacetime could be defined as a nonperturbatively renormalizable theory.

hep-th↗

arXiv2024

Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks

With the proliferation of intelligent mobile devices in wireless device-to-device (D2D) networks, decentralized federated learning (DFL) has attracted significant interest. Compared to centralized federated learning (CFL), DFL mitigates the risk of central server failures due to communication bottlenecks. However, DFL faces several challenges, such as the severe heterogeneity of data distributions in diverse environments, and the transmission outages and package errors caused by the adoption of the User Datagram Protocol (UDP) in D2D networks. These challenges often degrade the convergence of training DFL models. To address these challenges, we conduct a thorough theoretical convergence analysis for DFL and derive a convergence bound. By defining a novel quantity named unreliable links-aware neighborhood discrepancy in this convergence bound, we formulate a tractable optimization objective, and develop a novel Topology Learning method considering the Representation Discrepancy and Unreliable Links in DFL, named ToLRDUL. Intensive experiments under both feature skew and label skew settings have validated the effectiveness of our proposed method, demonstrating improved convergence speed and test accuracy, consistent with our theoretical findings.

cs.LG↗