Search

Endeavors have been made to explore Large Language Models for video analysis (Video-LLMs), particularly in understanding and interpreting long videos. However, existing Video-LLMs still face challenges in effectively integrating the rich and diverse audio-visual information inherent in long videos, which is crucial for comprehensive understanding. This raises the question: how can we leverage embedded audio-visual information to enhance long video understanding? Therefore, (i) we introduce SAVEn-Vid, the first-ever long audio-visual video dataset comprising over 58k audio-visual instructions. (ii) From the model perspective, we propose a time-aware Audio-Visual Large Language Model (AV-LLM), SAVEnVideo, fine-tuned on SAVEn-Vid. (iii) Besides, we present AVBench, a benchmark containing 2,500 QAs designed to evaluate models on enhanced audio-visual comprehension tasks within long video, challenging their ability to handle intricate audio-visual interactions. Experiments on AVBench reveal the limitations of current AV-LLMs. Experiments also demonstrate that SAVEnVideo outperforms the best Video-LLM by 3.61% on the zero-shot long video task (Video-MME) and surpasses the leading audio-visual LLM by 1.29% on the zero-shot audio-visual task (Music-AVQA). Consequently, at the 7B parameter scale, SAVEnVideo can achieve state-of-the-art performance. Our dataset and code will be released at https://ljungang.github.io/SAVEn-Vid/ upon acceptance., Comment: The publication has some processing errors (language short-cuts in synthetic data are not avoided) that invalidate some of the conclusions

We study the following higher order Schr\"odinger equation on hyperbolic space $\mathbb{H}^n$: $P_m u +a(x) u = |u|^{q - 2}u,$ where $P_m$ is the $2m$ order GJMS operator, $q=\frac{2n}{n-2m}$, $a(x) \in L^{\frac{n}{2m}}(\mathbb{H}^n)$ is a nonnegative potential function. We obtain a new concentration compactness principal for higher order problems on hyperbolic spaces. Under certain integrability assumptions on $a(x)$, we obtain the existence of solutions of the Schr\"odinger equations., Comment: 42 pages

The classification of solutions to semilinear partial differential equations, as well as the classification of critical points of the corresponding functionals, have wide applications in the study of partial differential equations and differential geometry. The classical moving plane method and the method of moving sphere on the Euclidean space $\mathbb{R}^n$ provide an effective approach to capture the symmetry of solutions. As far as we know, the moving sphere method has yet to be developed on the hyperbolic space $\mathbb{H}^n$. In the present paper, we focus on the following equation \begin{equation*} P_k u = f(u) \end{equation*} on hyperbolic spaces $\mathbb{H}^n$, where $P_k$ denotes the GJMS operators on $\mathbb{H}^n$ and $f : \mathbb{R} \to \mathbb{R}$ satisfies certain growth conditions. We develop a moving sphere approach on $\mathbb{H}^n$ to obtain the symmetry propertyas well as the classification of positive solutions to the above equation. Our methods also rely on the Helgason-Fourier analysis and Hardy-Littlewood-Sobolev inequalities on hyperbolic space together with a Kelvin transform we introduce on the hyperbolic space in this paper. We also present applications to the higher order prescribed $Q$-curvature problem on the hyperbolic space., Comment: 32 pages. The title has been changed. The paper has been improved substantially by adding the classification of the solutions to the higher order equations associated to the GJMS operators on the hyperbolic space. Applications to the prescribed Q-curvature problem on the hyperbolic space has also been added

We show that nontrivial solutions to higher and fractional order equations with certain nonlinearity are radially symmetric and nonincreasing on geodesic balls in the hyperbolic space $\mathbb{H}^n$ as well as on the entire space $\mathbb{H}^n$. Applying the Helgason-Fourier analysis techniques on $\mathbb{H}^n$, we develop a moving plane approach for integral equations on $\mathbb{H}^n$. We also establish the symmetry to solutions of certain equations with singular terms on Euclidean spaces. Moreover, we obtain symmetry to solutions of some semilinear equations involving fractional order derivatives., Comment: 25 pages

In their celebrated work [5], Chang and Marshall established a critical trace inequality of Moser-Trudinger type for holomorphic functions with mean value zero on unit disc in the complex plane. The main purpose is to address a question proposed to us by S. Y. Alice Chang who asked whether the Chang-Marshall type inequality for holomorphic functions on unit disk in the complex plane holds for Sobolev functions on general domains in higher dimensional Euclidean space $\mathbb{R}^n$ for all $n\ge 2$. We partially answer her question affirmatively., Comment: Some typos are corrected and some clarifications of the proofs of the main theorems are given

The main purpose of this paper is to establish the existence, nonexistence and symmetry of nontrivial solutions to the higher order Brezis-Nirenberg problems associated with the GJMS operators $P_k$ on bounded domains in the hyperbolic space $\mathbb{H}^n$ and as well as on the entire hyperbolic space $\mathbb{H}^n$. Among other techniques, one of our main novelties is to use crucially the Helgason-Fourier analysis on hyperbolic spaces and the higher order Hardy-Sobolev-Maz'ya inequalities and careful study of delicate properties of Green's functions of $P_k-\lambda$ on hyperbolic spaces which are of independent interests in dealing with such problems. Such Green's functions allow us to obtain the integral representations of solutions and thus to avoid using the maximum principle to establish the symmetry of solutions., Comment: 29 pages

The notion of $p$-ellipticity has recently played a significant role in improving our understanding of issues of solvability of boundary value problems for scalar complex valued elliptic PDEs. In particular, the presence of $p$-ellipticity ensures higher regularity of solutions of such equations. In this work we extend the notion of $p$-ellipticity to second order elliptic systems. Recall that for systems, there is no single notion of ellipticity, rather a more complicated picture emerges with ellipticity conditions of varying strength such as the Legendre, Legendre-Hadamard and integral conditions. A similar picture emerges when $p$-ellipticity is considered. In this paper, we define three new notions of $p$-ellipticity, establish relationships between them and show that each of them does play an important role in solving boundary value problems. These important roles are demonstrated by establishing extrapolation results for solvability of the $L^p$ Dirichlet problem for elliptic systems, followed by applications of this result in two different scenarios: one for the Lam\'e system of linear elasticity and another in the theory of homogenization., Comment: 31 pages

The 10 MeV accelerator-driven subcritical system (ADS) Injector-I test stand at Institute of High Energy Physics (IHEP) is a testing facility dedicated to demonstrate one of the two injector design schemes [Injector Scheme-I, which works at 325 MHz], for the ADS project in China. The Injector adopted a four vane copper structure RFQ with output energy of 3.2 MeV and a superconducting (SC) section accommodating fourteen \b{eta}g=0.12 single spoke cavities, fourteen SC solenoids and fourteen cold BPMs. The ion source was installed since April of 2014, periods of commissioning are regularly scheduled between installation phases of the rest of the injector. Continuous wave (CW) beam was shooting through the injector and 10 MeV CW proton beam with average beam current around 2 mA was obtained recently. This contribution describe the results achieved so far and the difficulties encountered in CW commissioning., Comment: 11 pages,27 figures

Let $\mathbb{H}^{n}=\mathbb{C}^{n}\times\mathbb{R}$ be the $n$-dimensional Heisenberg group, $Q=2n+2$ be the homogeneous dimension of $\mathbb{H}^{n}$. We extend the well-known concentration-compactness principle on finite domains in the Euclidean spaces of \ P. L. Lions to the setting of the Heisenberg group $\mathbb{H}^{n}$. Furthermore, we also obtain the corresponding concentration-compactness principle for the Sobolev space $HW^{1,Q}\left( \mathbb{H}^{n}\right) $ on the entire Heisenberg group $\mathbb{H}^{n}$. Our results improve the sharp Trudinger-Moser inequality on domains of finite measure in $\mathbb{H}^{n}$ by Cohn and the second author [8] and the corresponding one on the whole space $\mathbb{H}^n$ by Lam and the second author [21]. All the proofs of the concentration-compactness principles in the literature even in the Euclidean spaces use the rearrangement argument and the Poly\'a-Szeg\"{o} inequality. Due to the absence of the Poly\'a-Szeg\"{o} inequality on the Heisenberg group, we will develop a different argument. Our approach is surprisingly simple and general and can be easily applied to other settings where symmetrization argument does not work. As an application of the concentration-compactness principle, we establish the existence of ground state solutions for a class of $Q$- Laplacian subelliptic equations on $\mathbb{H}^{n}$ with nonlinear terms $f$ of maximal exponential growth $\exp\left( \alpha t^{\frac{Q}{Q-1}}\right) $ as $t\rightarrow+\infty$., Comment: 28 pages