arXiv subjects

Ning Liu

Publications and source records attributed to Ning Liu.

At least 109 records · Page 6Linked to original sources

arXiv2024

EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching

Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs, yet their extensive computational requirements hinder widespread practical applications. To reduce the computation budget of transformer-based DPMs, this work proposes the Efficient Diffusion Transformer (EDT) framework. The framework includes a lightweight-design diffusion model architecture, and a training-free Attention Modulation Matrix and its alternation arrangement in EDT inspired by human-like sketching. Additionally, we propose a token relation-enhanced masking training strategy tailored explicitly for EDT to augment its token relation learning capability. Our extensive experiments demonstrate the efficacy of EDT. The EDT framework reduces training and inference costs and surpasses existing transformer-based diffusion models in image synthesis performance, thereby achieving a significant overall enhancement. With lower FID, EDT-S, EDT-B, and EDT-XL attained speed-ups of 3.93x, 2.84x, and 1.92x respectively in the training phase, and 2.29x, 2.29x, and 2.22x respectively in inference, compared to the corresponding sizes of MDTv2. The source code is released at https://github.com/xinwangChen/EDT.

cs.CV↗

arXiv2024

AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking

Camera-LiDAR fusion models significantly enhance perception performance in autonomous driving. The fusion mechanism leverages the strengths of each modality while minimizing their weaknesses. Moreover, in practice, camera-LiDAR fusion models utilize pre-trained backbones for efficient training. However, we argue that directly loading single-modal pre-trained camera and LiDAR backbones into camera-LiDAR fusion models introduces similar feature redundancy across modalities due to the nature of the fusion mechanism. Unfortunately, existing pruning methods are developed explicitly for single-modal models, and thus, they struggle to effectively identify these specific redundant parameters in camera-LiDAR fusion models. In this paper, to address the issue above on camera-LiDAR fusion models, we propose a novelty pruning framework Alternative Modality Masking Pruning (AlterMOMA), which employs alternative masking on each modality and identifies the redundant parameters. Specifically, when one modality parameters are masked (deactivated), the absence of features from the masked backbone compels the model to reactivate previous redundant features of the other modality backbone. Therefore, these redundant features and relevant redundant parameters can be identified via the reactivation process. The redundant parameters can be pruned by our proposed importance score evaluation function, Alternative Evaluation (AlterEva), which is based on the observation of the loss changes when certain modality parameters are activated and deactivated. Extensive experiments on the nuScene and KITTI datasets encompassing diverse tasks, baseline models, and pruning algorithms showcase that AlterMOMA outperforms existing pruning methods, attaining state-of-the-art performance.

cs.CV↗

arXiv2024

MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition

Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image pre-training to realize zero-shot 3D shape recognition. However, due to the modality gap, pretrained language-image models are not confident enough in the generalization to 3D shape recognition. Consequently, this paper aims to improve the confidence with view selection and hierarchical prompts. Leveraging the CLIP model as an example, we employ view selection on the vision side by identifying views with high prediction confidence from multiple rendered views of a 3D shape. On the textual side, the strategy of hierarchical prompts is proposed for the first time. The first layer prompts several classification candidates with traditional class-level descriptions, while the second layer refines the prediction based on function-level descriptions or further distinctions between the candidates. Remarkably, without the need for additional training, our proposed method achieves impressive zero-shot 3D classification accuracies of 84.44%, 91.51%, and 66.17% on ModelNet40, ModelNet10, and ShapeNet Core55, respectively. Furthermore, we will make the code publicly available to facilitate reproducibility and further research in this area.

cs.CV↗

arXiv2024

Plethystic Murnaghan-Nakayama rule via vertex operators

Based on the vertex operator realization of the Schur functions, a determinant-type plethystic Murnaghan--Nakayama rule is obtained and utilized to derive a general formula of the expansion coefficients of $s_ν$ in the plethysm product $(p_{n}\circ h_{k})s_μ$. Meanwhile, the equivalence between our algebraic rule and the combinatorial one is also established. As an application, we provide a simple way to compute the generalized Waring formula.

math.CO↗

arXiv2024

A refined uniqueness result of Leray's problem in an infinite-long pipe with the Navier-slip boundary

We consider the generalized Leray's problem with the Navier-slip boundary condition in an infinite pipe $\mathcal{D}=Σ\times\mathbb{R}$. We show that if the flux $Φ$ of the solution is no larger than a critical value that is \emph{independent with the friction ratio} of the Navier-slip boundary condition, the solution to the problem must be the parallel Poiseuille flow with the given flux. Compared with known related 3D results, this seems to be the first conclusion with the size of critical flux being uniform with the friction ratio $α\in]0,\infty]$, and it is surprising since the prescribed uniqueness breaks down immediately when $α=0$, even if $Φ=0$. Our proof relies primarily on a refined gradient estimate of the Poiseuille flow with the Navier-slip boundary condition. Additionally, we prove the critical flux $Φ_0\geq\fracπ{16}$ provided that $Σ$ is a unit disk.

math.AP↗

arXiv2024

Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery

Despite the recent popularity of attention-based neural architectures in core AI fields like natural language processing (NLP) and computer vision (CV), their potential in modeling complex physical systems remains under-explored. Learning problems in physical systems are often characterized as discovering operators that map between function spaces based on a few instances of function pairs. This task frequently presents a severely ill-posed PDE inverse problem. In this work, we propose a novel neural operator architecture based on the attention mechanism, which we coin Nonlocal Attention Operator (NAO), and explore its capability towards developing a foundation physical model. In particular, we show that the attention mechanism is equivalent to a double integral operator that enables nonlocal interactions among spatial tokens, with a data-dependent kernel characterizing the inverse mapping from data to the hidden parameter field of the underlying operator. As such, the attention mechanism extracts global prior information from training data generated by multiple systems, and suggests the exploratory space in the form of a nonlinear kernel map. Consequently, NAO can address ill-posedness and rank deficiency in inverse PDE problems by encoding regularization and achieving generalizability. We empirically demonstrate the advantages of NAO over baseline neural models in terms of generalizability to unseen data resolutions and system states. Our work not only suggests a novel neural operator architecture for learning interpretable foundation models of physical systems, but also offers a new perspective towards understanding the attention mechanism.

cs.LG↗

arXiv2024

Autoregressive Enzyme Function Prediction with Multi-scale Multi-modality Fusion

Accurate prediction of enzyme function is crucial for elucidating biological mechanisms and driving innovation across various sectors. Existing deep learning methods tend to rely solely on either sequence data or structural data and predict the EC number as a whole, neglecting the intrinsic hierarchical structure of EC numbers. To address these limitations, we introduce MAPred, a novel multi-modality and multi-scale model designed to autoregressively predict the EC number of proteins. MAPred integrates both the primary amino acid sequence and the 3D tokens of proteins, employing a dual-pathway approach to capture comprehensive protein characteristics and essential local functional sites. Additionally, MAPred utilizes an autoregressive prediction network to sequentially predict the digits of the EC number, leveraging the hierarchical organization of EC classifications. Evaluations on benchmark datasets, including New-392, Price, and New-815, demonstrate that our method outperforms existing models, marking a significant advance in the reliability and granularity of protein function prediction within bioinformatics.

q-bio.QM↗

arXiv2024

Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment

With the rapid development of generative models, Artificial Intelligence-Generated Contents (AIGC) have exponentially increased in daily lives. Among them, Text-to-Video (T2V) generation has received widespread attention. Though many T2V models have been released for generating high perceptual quality videos, there is still lack of a method to evaluate the quality of these videos quantitatively. To solve this issue, we establish the largest-scale Text-to-Video Quality Assessment DataBase (T2VQA-DB) to date. The dataset is composed of 10,000 videos generated by 9 different T2V models. We also conduct a subjective study to obtain each video's corresponding mean opinion score. Based on T2VQA-DB, we propose a novel transformer-based model for subjective-aligned Text-to-Video Quality Assessment (T2VQA). The model extracts features from text-video alignment and video fidelity perspectives, then it leverages the ability of a large language model to give the prediction score. Experimental results show that T2VQA outperforms existing T2V metrics and SOTA video quality assessment models. Quantitative analysis indicates that T2VQA is capable of giving subjective-align predictions, validating its effectiveness. The dataset and code will be released at https://github.com/QMME/T2VQA.

cs.CV↗

arXiv2024

Neutron Star Collapse From Accretion: a Probe of Massive Dark Matter Particles

We explore the multi-scatter capturing of the massive dark matter (DM) particle inside the neutron star via a momentum-dependent dark matter-nucleon scattering cross-section. We find that the capturing enhanced for the positive velocity and momentum transfer dependent DM-nucleon scattering in comparison with the constant cross-section case. Further, a large capture of the DM particles can be thermalized and lead to black hole formation and, therefore, destroy the neutron star. Using the observation of the old neutron star in the DM-dominated region, we obtain strong constraints on massive DM parameters.

astro-ph.CO↗

arXiv2024

Weak and strong coupling polarons in binary Bose-Einstein condensates

The Bose polaron is a quasiparticle that arises from the interaction between impurities and Bogoliubov excitation in Bose-Einstein condensates, analogous to the polaron formed by electrons and phonons in solid-state physics. In this paper, we investigate the effect of phase separation on weakly coupled and strongly coupled Bose polarons. Our findings reveal that phase separation induces a remarkable alteration in the properties of weakly coupled Bose polarons. However, in the case of strong coupling, phase separation cannot destroy the highly self-trapping state of Bose polarons.

cond-mat.quant-gas↗

arXiv2024

Large language models, physics-based modeling, experimental measurements: the trinity of data-scarce learning of polymer properties

Large language models (LLMs) bear promise as a fast and accurate material modeling paradigm for evaluation, analysis, and design. Their vast number of trainable parameters necessitates a wealth of data to achieve accuracy and mitigate overfitting. However, experimental measurements are often limited and costly to obtain in sufficient quantities for finetuning. To this end, we present a physics-based training pipeline that tackles the pathology of data scarcity. The core enabler is a physics-based modeling framework that generates a multitude of synthetic data to align the LLM to a physically consistent initial state before finetuning. Our framework features a two-phase training strategy: (1) utilizing the large-in-amount while less accurate synthetic data for supervised pretraining, and (2) finetuning the phase-1 model with limited experimental data. We empirically demonstrate that supervised pretraining is vital to obtaining accurate finetuned LLMs, via the lens of learning polymer flammability metrics where cone calorimeter data is sparse.

cs.LG↗

arXiv2024

MMRo: Are Multimodal LLMs Eligible as the Brain for In-Home Robotics?

It is fundamentally challenging for robots to serve as useful assistants in human environments because this requires addressing a spectrum of sub-problems across robotics, including perception, language understanding, reasoning, and planning. The recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated their exceptional abilities in solving complex mathematical problems, mastering commonsense and abstract reasoning. This has led to the recent utilization of MLLMs as the brain in robotic systems, enabling these models to conduct high-level planning prior to triggering low-level control actions for task execution. However, it remains uncertain whether existing MLLMs are reliable in serving the brain role of robots. In this study, we introduce the first benchmark for evaluating Multimodal LLM for Robotic (MMRo) benchmark, which tests the capability of MLLMs for robot applications. Specifically, we identify four essential capabilities perception, task planning, visual reasoning, and safety measurement that MLLMs must possess to qualify as the robot's central processing unit. We have developed several scenarios for each capability, resulting in a total of 14 metrics for evaluation. We present experimental results for various MLLMs, including both commercial and open-source models, to assess the performance of existing systems. Our findings indicate that no single model excels in all areas, suggesting that current MLLMs are not yet trustworthy enough to serve as the cognitive core for robots. Our data can be found in https://mm-robobench.github.io/.

cs.RO↗

arXiv2024

Global stability of large Fourier mode for 3-D anisotropic Navier-Stokes equations in cylindrical domain

In this paper, we first establish the global existence and stability of solutions to 3-D classical Navier-Stokes equations $(NS)$ in an infinite cylindrical domain with large Fourier mode initial data. Then we extend similar result for 3-D anisotropic Navier-Stokes equations $(ANS).$ We remark that due to the loss of vertical viscosity in $(ANS),$ the construction of the energy functionals for $(ANS)$ is much more subtle than that of $(NS).$ Compared with our previous paper for $(NS)$, we improve the polynomial decay in $k$ for the Fourier coefficients of the solution to be exponential decay in $k$ here.

math.AP↗

arXiv2024

Search for nearly degenerate higgsinos via photon fusion with the semileptonic channel at the LHC

Electroweak scale higgsinos with a nearly degenerate spectrum in supersymmetric models are well-motivated, but generally less constrained at collider experiments as the decay products are often too soft to detect. Initial photon fusions alongside the collision of protons at the Large Hadron Collider (LHC) have drawn attention recently as a way to search for new physics with such kind of spectra. In this paper, we demonstrate a search strategy for chargino pair production from photon fusion $pp\to p(γγ\to\tildeχ^{+}_{1}\tildeχ^{-}_{1})p$ at the 13 TeV LHC via the semileptonic decay channel, as a probe for the compressed spectra of higgsinos. Forward detectors make it possible to detect the outgoing protons after emitting the initial photons in these processes. We here provide simple event selections on missing energy and transverse momentum of leptons, which are effective enough to reach significant sensitivity. The chargino mass can be excluded at 95\% C.L. up to about 295 GeV with the mass difference $Δm(\tildeχ^{\pm}_{1},\tildeχ^{0}_{1})$ being only a few GeV with the integrated luminosity of 3 ab$^{-1}$. With a relatively small luminosity of 100 fb$^{-1}$, the $2σ$ exclusion bounds can as well exceed current experimental limits in the range of $Δm=1\sim2$ GeV, reaching over 190 GeV for chargino mass.

hep-ph↗

arXiv2024

Harnessing the Power of Neural Operators with Automatically Encoded Conservation Laws

Neural operators (NOs) have emerged as effective tools for modeling complex physical systems in scientific machine learning. In NOs, a central characteristic is to learn the governing physical laws directly from data. In contrast to other machine learning applications, partial knowledge is often known a priori about the physical system at hand whereby quantities such as mass, energy and momentum are exactly conserved. Currently, NOs have to learn these conservation laws from data and can only approximately satisfy them due to finite training data and random noise. In this work, we introduce conservation law-encoded neural operators (clawNOs), a suite of NOs that endow inference with automatic satisfaction of such conservation laws. ClawNOs are built with a divergence-free prediction of the solution field, with which the continuity equation is automatically guaranteed. As a consequence, clawNOs are compliant with the most fundamental and ubiquitous conservation laws essential for correct physical consistency. As demonstrations, we consider a wide variety of scientific applications ranging from constitutive modeling of material deformation, incompressible fluid dynamics, to atmospheric simulation. ClawNOs significantly outperform the state-of-the-art NOs in learning efficacy, especially in small-data regimes.

cs.LG↗

arXiv2024

Deep Neural Operator Enabled Digital Twin Modeling for Additive Manufacturing

A digital twin (DT), with the components of a physics-based model, a data-driven model, and a machine learning (ML) enabled efficient surrogate, behaves as a virtual twin of the real-world physical process. In terms of Laser Powder Bed Fusion (L-PBF) based additive manufacturing (AM), a DT can predict the current and future states of the melt pool and the resulting defects corresponding to the input laser parameters, evolve itself by assimilating in-situ sensor data, and optimize the laser parameters to mitigate defect formation. In this paper, we present a deep neural operator enabled computational framework of the DT for closed-loop feedback control of the L-PBF process. This is accomplished by building a high-fidelity computational model to accurately represent the melt pool states, an efficient surrogate model to approximate the melt pool solution field, followed by an physics-based procedure to extract information from the computed melt pool simulation that can further be correlated to the defect quantities of interest (e.g., surface roughness). In particular, we leverage the data generated from the high-fidelity physics-based model and train a series of Fourier neural operator (FNO) based ML models to effectively learn the relation between the input laser parameters and the corresponding full temperature field of the melt pool. Subsequently, a set of physics-informed variables such as the melt pool dimensions and the peak temperature can be extracted to compute the resulting defects. An optimization algorithm is then exercised to control laser input and minimize defects. On the other hand, the constructed DT can also evolve with the physical twin via offline finetuning and online material calibration. Finally, a probabilistic framework is adopted for uncertainty quantification. The developed DT is envisioned to guide the AM process and facilitate high-quality manufacturing.

eess.SP↗

arXiv2024

STMGF: An Effective Spatial-Temporal Multi-Granularity Framework for Traffic Forecasting

Accurate Traffic Prediction is a challenging task in intelligent transportation due to the spatial-temporal aspects of road networks. The traffic of a road network can be affected by long-distance or long-term dependencies where existing methods fall short in modeling them. In this paper, we introduce a novel framework known as Spatial-Temporal Multi-Granularity Framework (STMGF) to enhance the capture of long-distance and long-term information of the road networks. STMGF makes full use of different granularity information of road networks and models the long-distance and long-term information by gathering information in a hierarchical interactive way. Further, it leverages the inherent periodicity in traffic sequences to refine prediction results by matching with recent traffic data. We conduct experiments on two real-world datasets, and the results demonstrate that STMGF outperforms all baseline models and achieves state-of-the-art performance.

cs.LG↗

arXiv2024

Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models

Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inference phases, restricting their use to a limited audience within the research and user communities. In this paper, we investigate the design aspects of Multimodal Small Language Models (MSLMs) and propose an efficient multimodal assistant named Mipha, which is designed to create synergy among various aspects: visual representation, language models, and optimization strategies. We show that without increasing the volume of training data, our Mipha-3B outperforms the state-of-the-art large MLLMs, especially LLaVA-1.5-13B, on multiple benchmarks. Through detailed discussion, we provide insights and guidelines for developing strong MSLMs that rival the capabilities of MLLMs. Our code is available at https://github.com/zhuyiche/llava-phi.

cs.CV↗