Search

We present the Atacama Large Millimeter/submillimeter Array Band 7 observations of the CO (J=3-2) line emission of the protostellar system HH 212 at $\sim$24 au spatial resolution and compare them to those of the SiO (J=8-7) and SO (J=8-7) line emission reported in the literature. We find that the CO line traces four distinct regions: (1) an outer outflow shell, (2) a rotating wind region between the SiO and CO shells, (3) the shocked and wide-angle inner X-wind inside a SiO shell, and (4) the jet. The origin of the CO outer outflow shell could be associated with the entrained material of the envelope, or an extended disk wind. The rotating wind, which is shocked, is launched from a radius of 9-15 au, slightly exterior to that of the previously detected SO shell, which marks the boundary where the wide-angle X-wind is interacting with and shocking the disk wind. Additionally, the SO is found to be mixed with the CO emission within the thick and extended rotating wind region. The large scale CO shocked wind coexists with the SO emission near the upper portion of the inner shocked region converged on top of the inner SiO knots. The CO jet is traced by a chain of knots with roughly equal interval, exhibiting quasi-periodicity, as reported in other jets in the literature., Comment: 18 pages, 12 figures, 2 tables. Accepted by ApJ

We present NOrthern Extended Millimeter Array observations of CO(8-7), (9-8), and (10-9) lines, as well as the underlying continuum for two far-infrared luminous quasars: SDSS J2054-0005 at $\rm z=6.0389$ and SDSS J0129-0035 at $\rm z=5.7788$. Both quasars were previously detected in CO (2-1) and (6-5) transitions, making them candidates for studying the CO Spectral Line Energy Distribution (SLED) of quasars at $z \sim 6$. Utilizing the radiative transfer code CLOUDY, we fit the CO SLED with two heating mechanisms, including the photo-dissociation region (PDR) and X-ray-dominated region (XDR) for both objects. The CO SLEDs can be fitted by either a dense PDR component with an extremely strong far-ultraviolet radiation field (gas density $ n_{\rm H} \sim 10^6 \, \rm cm^{-3}$ and field strength $G_0 \gtrsim 10^6$) or a two-component model including a PDR and an XDR. However, the line ratios, including \tir and previous \cii and \ci measurements, argue against a very high PDR radiation field strength. Thus, the results prefer a PDR+XDR origin for the CO SLED. The excitation of the high-J CO lines in both objects is likely dominated by the central AGN. We then check the CO (9-8)-to-(6-5) line luminosity ratio $r_{96}$ for all $z \sim 6$ quasars with available CO SLEDs (seven in total) and find that there are no clear correlations between $r_{96}$ and both \fir and the AGN UV luminosities. This further demonstrates the complexity of the CO excitation powered by both the AGN and nuclear star formation in these young quasar host galaxies., Comment: 19 pages, 9 figures, accepted for publication in ApJ

The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging the Transformer architecture's scalability and the benefits of parameter sharing to exploit task similarities. However, variations in task content and complexity pose significant challenges in policy formulation, necessitating judicious parameter sharing and management of conflicting gradients for optimal policy performance. Furthermore, identifying the optimal parameter subspace for each task often necessitates prior knowledge of the task identifier during inference, limiting applicability in real-world scenarios with variable task content and unknown current tasks. In this work, we introduce the Harmony Multi-Task Decision Transformer (HarmoDT), a novel solution designed to identify an optimal harmony subspace of parameters for each task. We formulate this as a bi-level optimization problem within a meta-learning framework, where the upper level learns masks to define the harmony subspace, while the inner level focuses on updating parameters to improve the overall performance of the unified policy. To eliminate the need for task identifiers, we further design a group-wise variant (G-HarmoDT) that clusters tasks into coherent groups based on gradient information, and utilizes a gating network to determine task identifiers during inference. Empirical evaluations across various benchmarks highlight the superiority of our approach, demonstrating its effectiveness in the multi-task context with specific improvements of 8% gain in task-provided settings, 5% in task-agnostic settings, and 10% in unseen settings., Comment: Extension of corresponding ICML edition arXiv:2405.18080. arXiv admin note: substantial text overlap with arXiv:2405.18080

Diabetic retinopathy (DR) is a leading cause of blindness worldwide and a common complication of diabetes. As two different imaging tools for DR grading, color fundus photography (CFP) and infrared fundus photography (IFP) are highly-correlated and complementary in clinical applications. To the best of our knowledge, this is the first study that explores a novel multi-modal deep learning framework to fuse the information from CFP and IFP towards more accurate DR grading. Specifically, we construct a dual-stream architecture Cross-Fundus Transformer (CFT) to fuse the ViT-based features of two fundus image modalities. In particular, a meticulously engineered Cross-Fundus Attention (CFA) module is introduced to capture the correspondence between CFP and IFP images. Moreover, we adopt both the single-modality and multi-modality supervisions to maximize the overall performance for DR grading. Extensive experiments on a clinical dataset consisting of 1,713 pairs of multi-modal fundus images demonstrate the superiority of our proposed method. Our code will be released for public access., Comment: 10 pages, 4 figures

An asymptotically flat hairy black hole (HBH) can exhibit distinct characteristics when compared to the Schwarzschild black hole, due to the evasion of no-hair theorem by minimally coupling the Einstein gravity with a scalar potential which possesses asymmetric vacua, i.e, a false vacuum $(\phi=0)$ and a true vacuum $(\phi=\phi_1)$. In this paper, we investigate the geodesic motion of both massive test particles and photons in the vicinity of HBH with $\phi_1=0.5$ and $\phi_1=1.0$ by analyzing their effective potentials derived from the geodesic equation. By fixing $\phi_1$, the effective potential of a massive test particle increases monotonically when its angular momentum $L$ is very small. When $L$ increases to a critical value, the effective potential possesses an inflection point which is known as the innermost stable of circular orbit (ISCO), where the test particle can still remain stable in a circular orbit with a minimal radius without being absorbed by the HBH or fleeing to infinity. Beyond the critical value of $L$, the effective potential possesses a local minimum and a local maximum, indicating the existence of unstable and stable circular orbits, respectively. Moreover, the HBH possesses an unstable photon sphere but its location slightly deviates from the Schwarzschild black hole. The trajectories of null geodesics in the vicinity of HBH can also be classified into three types, which are the direct, lensing and photon sphere, based on the deflection angle of light, but the values of impact parameters can vary significantly than the Schwarzschild black hole., Comment: 11 pages with total 11 figures

With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by systematically introducing the mechanisms of human long-term memory, then explores AI long-term memory mechanisms, establishing a mapping between the two. Based on the mapping relationships identified, we extend the current cognitive architectures and propose the Cognitive Architecture of Self-Adaptive Long-term Memory (SALM). SALM provides a theoretical framework for the practice of AI long-term memory and holds potential for guiding the creation of next-generation long-term memory driven AI systems. Finally, we delve into the future directions and application prospects of AI long-term memory.

In this paper, we study a nonlinear system involving a generalized tempered fractional $p$-Laplacian in $B_{1}(0)$: \begin{equation*} \left\{ \begin{array}{ll} \partial_tu(x,t)+(-\Delta-\lambda_{f})_{p}^{s}u(x,t)=g(t,u(x,t)), &(x,t)\in B_{1}(0)\times[0,+\infty),\\ u(x)=0,&(x,t)\in B_{1}^{c}(0)\times[0,+\infty), \end{array} \right. \end{equation*} where $02,\ n\geq2$. We establish Hopf's lemma for parabolic equations involving a generalized tempered fractional $p$-Laplacian. Hopf's lemma will become powerful tools in obtaining qualitative properties of solutions for nonlocal parabolic equations..

Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2. A core challenge in employing RLHF lies in training a reliable reward model (RM), which relies on high-quality labels typically provided by human experts or advanced AI system. These methods can be costly and may introduce biases that affect the language model's responses. As language models improve, human input may become less effective in further enhancing their performance. In this paper, we propose Self-Evolved Reward Learning (SER), a novel approach where the RM generates additional training data to iteratively improve itself. We conducted extensive experiments on multiple datasets such as HH-RLHF and UltraFeedback, using models like Mistral and Llama 3, and compare SER against various baselines. Our results demonstrate that even with limited human-annotated data, learning from self-feedback can robustly enhance RM performance, thereby boosting the capabilities of large language models (LLMs)., Comment: 19 pages,6 figures

Reminiscence, the act of revisiting past memories, is crucial for self-reflection and social interaction, significantly enhancing psychological well-being, life satisfaction, and self-identity among older adults. In HCI and CSCW, there is growing interest in leveraging technology to support reminiscence for older adults. However, understanding how older adults actively use technologies for realistic and practical reminiscence in their daily lives remains limited. This paper addresses this gap by providing an in-depth, empirical understanding of technology-mediated, photo-based reminiscence among older adults. Through a two-part study involving 20 older adults, we conducted semi-structured interviews and co-design sessions to explore their use and vision of digital technologies for photo-based reminiscence activities. Based on these insights, we propose design implications to make future reminiscence technologies more accessible and empowering for older adults., Comment: 30 pages, 7 figures, 1 table

Soft robot arms have made significant progress towards completing human-scale tasks, but designing arms for tasks with specific load and workspace requirements remains difficult. A key challenge is the lack of model-based design tools, forcing advancement to occur through empirical iteration and observation. Existing models are focused on control and rely on parameter fits, which means they cannot provide general conclusions about the mapping between design and performance or the influence of factors outside the fitting data. As a first step toward model-based design tools, we introduce a novel method of analyzing whether a proposed arm design can complete desired tasks. Our method is informative, interpretable, and fast; it provides novel metrics for quantifying a proposed arm design's ability to perform a task, it yields a graphical interpretation of performance through segment forces, and computing it is over 80x faster than optimization based methods. Our formulation focuses on antagonistic, pneumatically-driven soft arms. We demonstrate our approach through example analysis, and also through consideration of antagonistic vs non-antagonistic designs. Our method enables fast, direct and task-specific comparison of these two architectures, and provides a new visualization of the comparative mechanics. While only a first step, the proposed approach will support advancement of model-based design tools, leading to highly capable soft arms., Comment: 8 pages, 7 figures. Submission for the 8th IEEE-RAS International Conference on Soft Robotics (RoboSoft 2025). For code, proofs, and other supplementary information, see https://github.com/wfan19/antagonistic-task-competency

Text-to-SQL generation aims to translate natural language questions into SQL statements. In large language models (LLMs) based Text-to-SQL, schema linking is a widely adopted strategy to streamline the input for LLMs by selecting only relevant schema elements, therefore reducing noise and computational overhead. However, schema linking faces risks that requires caution, including the potential omission of necessary elements and disruption of database structural integrity. To address these challenges, we propose a novel framework called RSL-SQL that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. Our approach improves the recall of schema linking through forward and backward pruning and hedges the risk by voting between full schema and contextual information augmented simplified schema. Experiments on the BIRD and Spider benchmarks demonstrate that our approach achieves state-of-the-art execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on Spider using GPT-4o. Furthermore, our approach outperforms a series of GPT-4 based Text-to-SQL systems when adopting DeepSeek (much cheaper) with same intact prompts. Extensive analysis and ablation studies confirm the effectiveness of each component in our framework. The codes are available at https://github.com/Laqcce-cao/RSL-SQL.

Imitation learning from human demonstrations is an effective means to teach robots manipulation skills. But data acquisition is a major bottleneck in applying this paradigm more broadly, due to the amount of cost and human effort involved. There has been significant interest in imitation learning for bimanual dexterous robots, like humanoids. Unfortunately, data collection is even more challenging here due to the challenges of simultaneously controlling multiple arms and multi-fingered hands. Automated data generation in simulation is a compelling, scalable alternative to fuel this need for data. To this end, we introduce DexMimicGen, a large-scale automated data generation system that synthesizes trajectories from a handful of human demonstrations for humanoid robots with dexterous hands. We present a collection of simulation environments in the setting of bimanual dexterous manipulation, spanning a range of manipulation behaviors and different requirements for coordination among the two arms. We generate 21K demos across these tasks from just 60 source human demos and study the effect of several data generation and policy learning decisions on agent performance. Finally, we present a real-to-sim-to-real pipeline and deploy it on a real-world humanoid can sorting task. Videos and more are at https://dexmimicgen.github.io/, Comment: Project website: https://dexmimicgen.github.io/

In this work, we introduce general purpose touch representations for the increasingly accessible class of vision-based tactile sensors. Such sensors have led to many recent advances in robot manipulation as they markedly complement vision, yet solutions today often rely on task and sensor specific handcrafted perception models. Collecting real data at scale with task centric ground truth labels, like contact forces and slip, is a challenge further compounded by sensors of various form factor differing in aspects like lighting and gel markings. To tackle this we turn to self-supervised learning (SSL) that has demonstrated remarkable performance in computer vision. We present Sparsh, a family of SSL models that can support various vision-based tactile sensors, alleviating the need for custom labels through pre-training on 460k+ tactile images with masking and self-distillation in pixel and latent spaces. We also build TacBench, to facilitate standardized benchmarking across sensors and models, comprising of six tasks ranging from comprehending tactile properties to enabling physical perception and manipulation planning. In evaluations, we find that SSL pre-training for touch representation outperforms task and sensor-specific end-to-end training by 95.1% on average over TacBench, and Sparsh (DINO) and Sparsh (IJEPA) are the most competitive, indicating the merits of learning in latent space for tactile images. Project page: https://sparsh-ssl.github.io/, Comment: Conference on Robot Learning (CoRL), 2024

Percolation is a cornerstone concept in physics, providing crucial insights into critical phenomena and phase transitions. In this study, we adopt a kinetic perspective to reveal the scaling behaviors of higher-order gaps in the largest cluster across various percolation models, spanning from latticebased to network systems, encompassing both continuous and discontinuous percolation. Our results uncover an inherent self-similarity in the dynamical process both for critical and supercritical phase, characterized by two independent Fisher exponents, respectively. Utilizing a scaling ansatz, we propose a novel scaling relation that links the discovered Fisher exponents with other known critical exponents. Additionally, we demonstrate the application of our theory to real systems, showing its practical utility in extracting the corresponding Fisher exponents. These findings enrich our understanding of percolation dynamics and highlight the robust and universal scaling laws that transcend individual models and extend to broader classes of complex systems., Comment: 4.5 + 6 pages ; 4 + 12 figures

Plasma surface high-order harmonics generation (SHHG) driven by intense laser pulses on plasma targets enables a high-quality extreme ultraviolet source with high pulse energy and outstanding spatiotemporal coherence. Optimizing the performance of SHHG is important for its applications in single-shot imaging and absorption spectroscopy. In this work, we demonstrate the optimization of laser-driven SHHG by an improved Bayesian strategy in conjunction with particle-in-cell simulations. A traditional Bayesian algorithm is first employed to optimize the SHHG intensity in a two-dimensional space of parameter. Then an improved Bayesian strategy, using the Latin hypercube sampling technique and a dynamic acquisition strategy, is developed to overcome the curse of dimensionality and the risk of local optima in a high-dimensional space optimization. The improved Bayesian optimization approach is efficient and robust in three-dimensionally optimizing the harmonic ellipticity, paving the way for the upcoming SHHG experiments with a considerable repetition rate., Comment: 7 pages, 6 figures

The concept of periodic structures has driven the development of advanced materials like photonic and phononic crystals. These metamaterials typically rely on complex repeating units or meta-atoms, limiting their adaptability after fabrication. To overcome this limitation, we introduce the concept of metafields, which are repeating patterns of local magnetic fields instead of material structures. Unlike metamaterials, which consist of atoms arranged in structured patterns, metafields focus on the patterns of fields alone, allowing for dynamic property adjustments through external electric currents. This study explores a specific metafield where the repeating pattern is the magnetic disk (MD), defined by a uniform magnetic field perpendicular to its surface. By arranging multiple MDs, we form a magnetic disk array (MDA) and theoretically investigate the charged particle dynamics within this array. Our analysis highlights Hall transport phenomena, such as Hall diffusivity, conductivity, and thermal Hall effects. Using complex variables, we derive the collision integral and Boltzmann equation for particle distribution, applying perturbation methods and Fourier analysis to calculate transport coefficients. Simulations reveal a one-way preferential diffusion at the interface between MDAs with opposing field directions, where diffusion intensity varies with the particle movement direction. This highlights metafields' potential for dynamic particle control applications.

As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result in information loss, token merging shows promising results when used in collaboration with transformers. However, the application of token merging for long-form video processing is not trivial. We begin with the premise that token merging should not rely solely on the similarity of video tokens; the saliency of tokens should also be considered. To address this, we explore various video token merging strategies for long-form video classification, starting with a simple extension of image token merging, moving to region-concentrated merging, and finally proposing a learnable video token merging (VTM) algorithm that dynamically merges tokens based on their saliency. Extensive experimental results show that we achieve better or comparable performances on the LVU, COIN, and Breakfast datasets. Moreover, our approach significantly reduces memory costs by 84% and boosts throughput by approximately 6.89 times compared to baseline algorithms., Comment: 21 pages, NeurIPS 2024

Recent research arXiv:2410.15027 has explored the use of diffusion transformers (DiTs) for task-agnostic image generation by simply concatenating attention tokens across images. However, despite substantial computational resources, the fidelity of the generated images remains suboptimal. In this study, we reevaluate and streamline this framework by hypothesizing that text-to-image DiTs inherently possess in-context generation capabilities, requiring only minimal tuning to activate them. Through diverse task experiments, we qualitatively demonstrate that existing text-to-image DiTs can effectively perform in-context generation without any tuning. Building on this insight, we propose a remarkably simple pipeline to leverage the in-context abilities of DiTs: (1) concatenate images instead of tokens, (2) perform joint captioning of multiple images, and (3) apply task-specific LoRA tuning using small datasets (e.g., 20~100 samples) instead of full-parameter tuning with large datasets. We name our models In-Context LoRA (IC-LoRA). This approach requires no modifications to the original DiT models, only changes to the training data. Remarkably, our pipeline generates high-fidelity image sets that better adhere to prompts. While task-specific in terms of tuning data, our framework remains task-agnostic in architecture and pipeline, offering a powerful tool for the community and providing valuable insights for further research on product-level task-agnostic generation systems. We release our code, data, and models at https://github.com/ali-vilab/In-Context-LoRA, Comment: Tech report. Project page: https://ali-vilab.github.io/In-Context-LoRA-Page/

On User-Generated Content (UGC) platforms, recommendation algorithms significantly impact creators' motivation to produce content as they compete for algorithmically allocated user traffic. This phenomenon subtly shapes the volume and diversity of the content pool, which is crucial for the platform's sustainability. In this work, we demonstrate, both theoretically and empirically, that a purely relevance-driven policy with low exploration strength boosts short-term user satisfaction but undermines the long-term richness of the content pool. In contrast, a more aggressive exploration policy may slightly compromise user satisfaction but promote higher content creation volume. Our findings reveal a fundamental trade-off between immediate user satisfaction and overall content production on UGC platforms. Building on this finding, we propose an efficient optimization method to identify the optimal exploration strength, balancing user and creator engagement. Our model can serve as a pre-deployment audit tool for recommendation algorithms on UGC platforms, helping to align their immediate objectives with sustainable, long-term goals.

Precise phase measurements by interferometers are crucial in science for detecting subtle changes, such as gravitational waves. However, phase sensitivity is typically limited by the standard quantum limit (SQL) with uncorrelated particles N. This limit can be surpassed using quantum correlations, but achieving high-quality correlations in large systems is challenging. Here, we propose and demonstrate an atom-light hybrid quantum interferometry whose sensitivity is enhanced beyond the SQL with atom-light quantum correlation and newly developed phase comb superposition via atomic-memory-assisted multiple quantum amplification. Finally, a phase sensitivity beyond the SQL of up to $8.3\pm 0.2$ dB is achieved, especially at $N=4 \times10^{13}/s$, resulting in both atomic and optical phase sensitivities of $6\times10^{-8} rad/\sqrt{Hz}$. This technique can advance sensitive quantum measurements in various fields., Comment: 11 pages, 3 figures

With the advancement of deepfake generation techniques, the importance of deepfake detection in protecting multimedia content integrity has become increasingly obvious. Recently, temporal inconsistency clues have been explored to improve the generalizability of deepfake video detection. According to our observation, the temporal artifacts of forged videos in terms of motion information usually exhibits quite distinct inconsistency patterns along horizontal and vertical directions, which could be leveraged to improve the generalizability of detectors. In this paper, a transformer-based framework for Diffusion Learning of Inconsistency Pattern (DIP) is proposed, which exploits directional inconsistencies for deepfake video detection. Specifically, DIP begins with a spatiotemporal encoder to represent spatiotemporal information. A directional inconsistency decoder is adopted accordingly, where direction-aware attention and inconsistency diffusion are incorporated to explore potential inconsistency patterns and jointly learn the inherent relationships. In addition, the SpatioTemporal Invariant Loss (STI Loss) is introduced to contrast spatiotemporally augmented sample pairs and prevent the model from overfitting nonessential forgery artifacts. Extensive experiments on several public datasets demonstrate that our method could effectively identify directional forgery clues and achieve state-of-the-art performance., Comment: 13 pages, accepted with IEEE Trans. on Multimedia

Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood. This paper rigorously analyzes the convergence properties of gradient flow in training Transformers with weight decay regularization. First, we construct the mean-field limit of large-scale Transformers, showing that as the model width and depth go to infinity, gradient flow converges to the Wasserstein gradient flow, which is represented by a partial differential equation. Then, we demonstrate that the gradient flow reaches a global minimum consistent with the PDE solution when the weight decay regularization parameter is sufficiently small. Our analysis is based on a series of novel mean-field techniques that adapt to Transformers. Compared with existing tools for deep networks (Lu et al., 2020) that demand homogeneity and global Lipschitz smoothness, we utilize a refined analysis assuming only $\textit{partial homogeneity}$ and $\textit{local Lipschitz smoothness}$. These new techniques may be of independent interest., Comment: to be published in 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

First-order methods (FOMs) are arguably the most scalable algorithms for equilibrium computation in large extensive-form games. To operationalize these methods, a distance-generating function, acting as a regularizer for the strategy space, must be chosen. The ratio between the strong convexity modulus and the diameter of the regularizer is a key parameter in the analysis of FOMs. A natural question is then: what is the optimal distance-generating function for extensive-form decision spaces? In this paper, we make a number of contributions, ultimately establishing that the weight-one dilated entropy (DilEnt) distance-generating function is optimal up to logarithmic factors. The DilEnt regularizer is notable due to its iterate-equivalence with Kernelized OMWU (KOMWU) -- the algorithm with state-of-the-art dependence on the game tree size in extensive-form games -- when used in conjunction with the online mirror descent (OMD) algorithm. However, the standard analysis for OMD is unable to establish such a result; the only current analysis is by appealing to the iterate equivalence to KOMWU. We close this gap by introducing a pair of primal-dual treeplex norms, which we contend form the natural analytic viewpoint for studying the strong convexity of DilEnt. Using these norm pairs, we recover the diameter-to-strong-convexity ratio that predicts the same performance as KOMWU. Along with a new regret lower bound for online learning in sequence-form strategy spaces, we show that this ratio is nearly optimal. Finally, we showcase our analytic techniques by refining the analysis of Clairvoyant OMD when paired with DilEnt, establishing an $\mathcal{O}(n \log |\mathcal{V}| \log T/T)$ approximation rate to coarse correlated equilibrium in $n$-player games, where $|\mathcal{V}|$ is the number of reduced normal-form strategies of the players, establishing the new state of the art.

Vocal education in the music field is difficult to quantify due to the individual differences in singers' voices and the different quantitative criteria of singing techniques. Deep learning has great potential to be applied in music education due to its efficiency to handle complex data and perform quantitative analysis. However, accurate evaluations with limited samples over rare vocal types, such as Mezzo-soprano, requires extensive well-annotated data support using deep learning models. In order to attain the objective, we perform transfer learning by employing deep learning models pre-trained on the ImageNet and Urbansound8k datasets for the improvement on the precision of vocal technique evaluation. Furthermore, we tackle the problem of the lack of samples by constructing a dedicated dataset, the Mezzo-soprano Vocal Set (MVS), for vocal technique assessment. Our experimental results indicate that transfer learning increases the overall accuracy (OAcc) of all models by an average of 8.3%, with the highest accuracy at 94.2%. We not only provide a novel approach to evaluating Mezzo-soprano vocal techniques but also introduce a new quantitative assessment method for music education.

In this paper, we propose OpenSatMap, a fine-grained, high-resolution satellite dataset for large-scale map construction. Map construction is one of the foundations of the transportation industry, such as navigation and autonomous driving. Extracting road structures from satellite images is an efficient way to construct large-scale maps. However, existing satellite datasets provide only coarse semantic-level labels with a relatively low resolution (up to level 19), impeding the advancement of this field. In contrast, the proposed OpenSatMap (1) has fine-grained instance-level annotations; (2) consists of high-resolution images (level 20); (3) is currently the largest one of its kind; (4) collects data with high diversity. Moreover, OpenSatMap covers and aligns with the popular nuScenes dataset and Argoverse 2 dataset to potentially advance autonomous driving technologies. By publishing and maintaining the dataset, we provide a high-quality benchmark for satellite-based map construction and downstream tasks like autonomous driving., Comment: NeurIPS 2024 D&B Track. Project Page:https://opensatmap.github.io/

Transformers have become the predominant architecture in foundation models due to their excellent performance across various domains. However, the substantial cost of scaling these models remains a significant concern. This problem arises primarily from their dependence on a fixed number of parameters within linear projections. When architectural modifications (e.g., channel dimensions) are introduced, the entire model typically requires retraining from scratch. As model sizes continue growing, this strategy results in increasingly high computational costs and becomes unsustainable. To overcome this problem, we introduce TokenFormer, a natively scalable architecture that leverages the attention mechanism not only for computations among input tokens but also for interactions between tokens and model parameters, thereby enhancing architectural flexibility. By treating model parameters as tokens, we replace all the linear projections in Transformers with our token-parameter attention layer, where input tokens act as queries and model parameters as keys and values. This reformulation allows for progressive and efficient scaling without necessitating retraining from scratch. Our model scales from 124M to 1.4B parameters by incrementally adding new key-value parameter pairs, achieving performance comparable to Transformers trained from scratch while greatly reducing training costs. Code and models are available at \url{https://github.com/Haiyang-W/TokenFormer}.

Model order reduction encompasses mathematical techniques aimed at reducing the complexity of mathematical models in simulations while retaining the essential characteristics and behaviors of the original model. This is particularly useful in the context of large-scale dynamical systems, which can be computationally expensive to analyze and simulate. Here, we present a model order reduction technique to reduce the time complexity of open quantum systems, grounded in the principle of measurement-adapted coarse-graining. This method, governed by a coarse-graining time scale $\tau$ and the spectral band center $\omega_0$, organizes corrections to the lowest-order model which aligns with the RWA Hamiltonian in certain limits, and rigorously justifies the resulting effective quantum master equation (EQME). The focus on calculating to a high degree of accuracy only what can be resolved by the measurement introduces a principled regularization procedure to address singularities and generates low-stiffness models suitable for efficient long-time integration. Furthermore, the availability of the analytical form of the EQME parameters significantly boosts the interpretive capabilities of the method. As a demonstration, we derive the fourth-order EQME for a challenging problem related to the dynamics of a superconducting qubit under high-power dispersive readout in the presence of a continuum of dissipative waveguide modes. This derivation shows that the lowest-order terms align with previous results, while higher-order corrections suggest new phenomena.

This paper investigates distributed computing and cooperative control of connected and automated vehicles (CAVs) in ramp merging scenario under transportation cyber-physical system. Firstly, a centralized cooperative trajectory planning problem is formulated subject to the safely constraints and traffic performance in ramp merging scenario, where the trajectories of all vehicles are jointly optimized. To get rid of the reliance on a central controller and reduce computation time, a distributed solution to this problem implemented among CAVs through Vehicles-to-Everything (V2X) communication is proposed. Unlike existing method, our method can distribute the computational task among CAVs and carry out parallel solving through V2X communication. Then, a multi-vehicles model predictive control (MPC) problem aimed at maximizing system stability and minimizing control input is formulated based on the solution of the first problem subject to strict safety constants and input limits. Due to these complex constraints, this problem becomes high-dimensional, centralized, and non-convex. To solve it in a short time, a decomposition and convex reformulation method, namely distributed cooperative iterative model predictive control (DCIMPC), is proposed. This method leverages the communication capability of CAVs to decompose the problem, making full use of the computational resources on vehicles to achieve fast solutions and distributed control. The two above problems with their corresponding solving methods form the systemic framework of the V2X assisted distributed computing and control. Simulations have been conducted to evaluate the framework's convergence, safety, and solving speed. Additionally, extra experiments are conducted to validate the performance of DCIMPC. The results show that our method can greatly improve computation speed without sacrificing system performance., Comment: This paper has been submitted to IEEE Journal. The source code has been released at: https://github.com/qiongwu86/V2X-Assisted-Distributed-Computing-and-Control-Framework-for-Connected-and-Automated-Vehicles.git

Anderson localization transitions are a universal quantum phenomenon sensitive to the disorder and dimensionality of electronic systems. Over the past decades, this intriguing topic has inspired overwhelmingly more theoretical studies than experimental verifications due to the difficulty of controlling a material's disorder or dimensionality without modifying its fundamental electronic properties. Organic crystals with their rich disorders would be terrific playgrounds to investigate such disorder-driven phase transitions except for their low conductivities which usually prohibit low-temperature measurements. Here, we conduct systematic transport experiments in mesoscopic devices made with copper benzenehexathiol thin films across a wide range of thicknesses. We find metal-insulator transitions both among three-dimensional samples with different disorder strengths and between three-dimensional and quasi-two-dimensional samples. Temperature-dependence analysis of the conductivities corroborates the dimensionality crossover. Moreover, our theoretical modeling provides a basis for understanding both types of metal-insulator transitions within the framework of Anderson localization transitions. Our findings establish for the first time that organic crystals such as conductive metal-organic frameworks can exhibit such quantum interference effects. With organic materials' versatile chemical designs and crystalline structures, our work opens new avenues to search for novel quantum phenomena in organic material platforms.

Image Signal Processors (ISPs) convert raw sensor signals into digital images, which significantly influence the image quality and the performance of downstream computer vision tasks. Designing ISP pipeline and tuning ISP parameters are two key steps for building an imaging and vision system. To find optimal ISP configurations, recent works use deep neural networks as a proxy to search for ISP parameters or ISP pipelines. However, these methods are primarily designed to maximize the image quality, which are sub-optimal in the performance of high-level computer vision tasks such as detection, recognition, and tracking. Moreover, after training, the learned ISP pipelines are mostly fixed at the inference time, whose performance degrades in dynamic scenes. To jointly optimize ISP structures and parameters, we propose AdaptiveISP, a task-driven and scene-adaptive ISP. One key observation is that for the majority of input images, only a few processing modules are needed to improve the performance of downstream recognition tasks, and only a few inputs require more processing. Based on this, AdaptiveISP utilizes deep reinforcement learning to automatically generate an optimal ISP pipeline and the associated ISP parameters to maximize the detection performance. Experimental results show that AdaptiveISP not only surpasses the prior state-of-the-art methods for object detection but also dynamically manages the trade-off between detection performance and computational cost, especially suitable for scenes with large dynamic range variations. Project website: https://openimaginglab.github.io/AdaptiveISP/., Comment: Accepted at NeurIPS2024

Quantum error correction (QEC) is a crucial prerequisite for future large-scale quantum computation. Finding and analyzing new QEC codes, along with efficient decoding and fault-tolerance protocols, is central to this effort. Holographic codes are a recent class of QEC subsystem codes derived from holographic bulk/boundary dualities. In addition to exploring the physics of such dualities, these codes possess useful QEC properties such as tunable encoding rates, distance scaling competitive with topological codes, and excellent recovery thresholds. To allow for a comprehensive analysis of holographic code constructions, we introduce LEGO_HQEC, a software package utilizing the quantum LEGO formalism. This package constructs holographic codes on regular hyperbolic tilings and generates their stabilizer generators and logical operators for a specified number of seed codes and layers. Three decoders are included: an erasure decoder based on Gaussian elimination; an integer-optimization decoder; and a tensor-network decoder. With these tools, LEGO_HQEC thus enables future systematic studies regarding the utility of holographic codes for practical quantum computing.

Workplace meetings are vital to organizational collaboration, yet a large percentage of meetings are rated as ineffective. To help improve meeting effectiveness by understanding if the conversation is on topic, we create a comprehensive Topic-Conversation Relevance (TCR) dataset that covers a variety of domains and meeting styles. The TCR dataset includes 1,500 unique meetings, 22 million words in transcripts, and over 15,000 meeting topics, sourced from both newly collected Speech Interruption Meeting (SIM) data and existing public datasets. Along with the text data, we also open source scripts to generate synthetic meetings or create augmented meetings from the TCR dataset to enhance data diversity. For each data source, benchmarks are created using GPT-4 to evaluate the model accuracy in understanding transcription-topic relevance., Comment: To be published in 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks

The fast development of location-based social networks (LBSNs) has led to significant changes in society, resulting in popular studies of using LBSN data for socioeconomic prediction, e.g., regional population and commercial activity estimation. Existing studies design various graphs to model heterogeneous LBSN data, and further apply graph representation learning methods for socioeconomic prediction. However, these approaches heavily rely on heuristic ideas and expertise to extract task-relevant knowledge from diverse data, which may not be optimal for specific tasks. Additionally, they tend to overlook the inherent relationships between different indicators, limiting the prediction accuracy. Motivated by the remarkable abilities of large language models (LLMs) in commonsense reasoning, embedding, and multi-agent collaboration, in this work, we synergize LLM agents and knowledge graph for socioeconomic prediction. We first construct a location-based knowledge graph (LBKG) to integrate multi-sourced LBSN data. Then we leverage the reasoning power of LLM agent to identify relevant meta-paths in the LBKG for each type of socioeconomic prediction task, and design a semantic-guided attention module for knowledge fusion with meta-paths. Moreover, we introduce a cross-task communication mechanism to further enhance performance by enabling knowledge sharing across tasks at both LLM agent and KG levels. On the one hand, the LLM agents for different tasks collaborate to generate more diverse and comprehensive meta-paths. On the other hand, the embeddings from different tasks are adaptively merged for better socioeconomic prediction. Experiments on two datasets demonstrate the effectiveness of the synergistic design between LLM and KG, providing insights for information sharing across socioeconomic prediction tasks.

Using $(10087\pm44)\times 10^{6}$ $J/\psi$ decays collected by the BESIII detector at the BEPCII collider, we search for baryon number violation via $\Lambda-\bar{\Lambda}$ oscillation in the decay $J/\psi \to \Lambda \bar{\Lambda}$. No evidence for $\Lambda-\bar\Lambda$ oscillation is observed. The upper limit on the time-integrated probability of $\Lambda-\bar{\Lambda}$ oscillation is estimated to be $1.4\times 10^{-6}$, corresponding to an oscillation parameter less than $2.1\times 10^{-18}~\mathrm{GeV}$ at $90\%$ confidence level., Comment: 8 pages, 2 figures

Laryngo-pharyngeal cancer (LPC) is a highly lethal malignancy in the head and neck region. Recent advancements in tumor detection, particularly through dual-branch network architectures, have significantly improved diagnostic accuracy by integrating global and local feature extraction. However, challenges remain in accurately localizing lesions and fully capitalizing on the complementary nature of features within these branches. To address these issues, we propose SAM-Swin, an innovative SAM-driven Dual-Swin Transformer for laryngo-pharyngeal tumor detection. This model leverages the robust segmentation capabilities of the Segment Anything Model 2 (SAM2) to achieve precise lesion segmentation. Meanwhile, we present a multi-scale lesion-aware enhancement module (MS-LAEM) designed to adaptively enhance the learning of nuanced complementary features across various scales, improving the quality of feature extraction and representation. Furthermore, we implement a multi-scale class-aware guidance (CAG) loss that delivers multi-scale targeted supervision, thereby enhancing the model's capacity to extract class-specific features. To validate our approach, we compiled three LPC datasets from the First Affiliated Hospital (FAHSYSU), the Sixth Affiliated Hospital (SAHSYSU) of Sun Yat-sen University, and Nanfang Hospital of Southern Medical University (NHSMU). The FAHSYSU dataset is utilized for internal training, while the SAHSYSU and NHSMU datasets serve for external evaluation. Extensive experiments demonstrate that SAM-Swin outperforms state-of-the-art methods, showcasing its potential for advancing LPC detection and improving patient outcomes. The source code of SAM-Swin is available at the URL of \href{https://github.com/VVJia/SAM-Swin}{https://github.com/VVJia/SAM-Swin}.

Very-high-energy (0.1-100 TeV) gamma-ray emission was observed in HAWC data from the lobes of the microquasar SS 433, making them the first set of astrophysical jets that were resolved at TeV energies. In this work, we update the analysis of SS 433 using 2,565 days of data from the High Altitude Water Cherenkov (HAWC) observatory. Our analysis reports the detection of a point-like source in the east lobe at a significance of $6.6\,\sigma$ and in the west lobe at a significance of $8.2\,\sigma$. For each jet lobe, we localize the gamma-ray emission and identify a best-fit position. The locations are close to the X-ray emission sites "e1" and "w1" for the east and west lobes, respectively. We analyze the spectral energy distributions and find that the energy spectra of the lobes are consistent with a simple power-law $\text{d}N/\text{d}E\propto E^{\alpha}$ with $\alpha = -2.44^{+0.13+0.04}_{-0.12-0.04}$ and $\alpha = -2.35^{+0.12+0.03}_{-0.11-0.03}$ for the east and west lobes, respectively. The maximum energy of photons from the east and west lobes reaches 56 TeV and 123 TeV, respectively. We compare our observations to various models and conclude that the very-high-energy gamma-ray emission can be produced by a population of electrons that were efficiently accelerated.

Graph clustering is an essential aspect of network analysis that involves grouping nodes into separate clusters. Recent developments in deep learning have resulted in advanced deep graph clustering techniques, which have proven effective in many applications. Nonetheless, these methods often encounter difficulties when dealing with the complexities of real-world graphs, particularly in the presence of noisy edges. Additionally, many denoising graph clustering strategies tend to suffer from lower performance compared to their non-denoised counterparts, training instability, and challenges in scaling to large datasets. To tackle these issues, we introduce a new framework called the Dual Adaptive Assignment Approach for Robust Graph-Based Clustering (RDSA). RDSA consists of three key components: (i) a node embedding module that effectively integrates the graph's topological features and node attributes; (ii) a structure-based soft assignment module that improves graph modularity by utilizing an affinity matrix for node assignments; and (iii) a node-based soft assignment module that identifies community landmarks and refines node assignments to enhance the model's robustness. We assess RDSA on various real-world datasets, demonstrating its superior performance relative to existing state-of-the-art methods. Our findings indicate that RDSA provides robust clustering across different graph types, excelling in clustering effectiveness and robustness, including adaptability to noise, stability, and scalability.

Diffusion models (DMs) have become the dominant paradigm of generative modeling in a variety of domains by learning stochastic processes from noise to data. Recently, diffusion denoising bridge models (DDBMs), a new formulation of generative modeling that builds stochastic processes between fixed data endpoints based on a reference diffusion process, have achieved empirical success across tasks with coupled data distribution, such as image-to-image translation. However, DDBM's sampling process typically requires hundreds of network evaluations to achieve decent performance, which may impede their practical deployment due to high computational demands. In this work, inspired by the recent advance of consistency models in DMs, we tackle this problem by learning the consistency function of the probability-flow ordinary differential equation (PF-ODE) of DDBMs, which directly predicts the solution at a starting step given any point on the ODE trajectory. Based on a dedicated general-form ODE solver, we propose two paradigms: consistency bridge distillation and consistency bridge training, which is flexible to apply on DDBMs with broad design choices. Experimental results show that our proposed method could sample $4\times$ to $50\times$ faster than the base DDBM and produce better visual quality given the same step in various tasks with pixel resolution ranging from $64 \times 64$ to $256 \times 256$, as well as supporting downstream tasks such as semantic interpolation in the data space., Comment: NeurIPS 2024

Current reinforcement-learning methods are unable to directly learn policies that solve the minimum cost reach-avoid problem to minimize cumulative costs subject to the constraints of reaching the goal and avoiding unsafe states, as the structure of this new optimization problem is incompatible with current methods. Instead, a surrogate problem is solved where all objectives are combined with a weighted sum. However, this surrogate objective results in suboptimal policies that do not directly minimize the cumulative cost. In this work, we propose RC-PPO, a reinforcement-learning-based method for solving the minimum-cost reach-avoid problem by using connections to Hamilton-Jacobi reachability. Empirical results demonstrate that RC-PPO learns policies with comparable goal-reaching rates to while achieving up to 57% lower cumulative costs compared to existing methods on a suite of minimum-cost reach-avoid benchmarks on the Mujoco simulator. The project page can be found at https://oswinso.xyz/rcppo., Comment: Accepted to NeurIPS 2024

Brain imaging studies have demonstrated that diffusion MRI tractography geometric shape descriptors can inform the study of the brain's white matter pathways and their relationship to brain function. In this work, we investigate the possibility of utilizing a deep learning model to compute shape measures of the brain's white matter connections. We introduce a novel framework, TractShapeNet, that leverages a point cloud representation of tractography to compute five shape measures: length, span, volume, total surface area, and irregularity. We assess the performance of the method on a large dataset including 1065 healthy young adults. Experiments for shape measure computation demonstrate that our proposed TractShapeNet outperforms other point cloud-based neural network models in both the Pearson correlation coefficient and normalized error metrics. We compare the inference runtime results with the conventional shape computation tool DSI-Studio. Our results demonstrate that a deep learning approach enables faster and more efficient shape measure computation. We also conduct experiments on two downstream language cognition prediction tasks, showing that shape measures from TractShapeNet perform similarly to those computed by DSI-Studio. Our code will be available at: https://github.com/SlicerDMRI/TractShapeNet., Comment: 10 pages, 2 figures, 4 tables. This work has been submitted to the IEEE for possible publication

In this paper, we study the self-normalized Cram\'er-type moderate deviation of the empirical measure of the stochastic gradient Langevin dynamics (SGLD). Consequently, we also derive the Berry-Esseen bound for SGLD. Our approach is by constructing a stochastic differential equation (SDE) to approximate the SGLD and then applying Stein's method as developed in [9,19], to decompose the empirical measure into a martingale difference series sum and a negligible remainder term.

We focus on two hypergraph Ramsey problems. First, we consider the Erd\H{o}s-Hajnal function $r_k(k+1,t;n)$. In 1972, Erd\H{o}s and Hajnal conjectured that the tower growth rate of $r_k(k+1,t;n)$ is $t-1$ for each $2\le t\le k$. To finish this conjecture, it remains to show that the tower growth rate of $r_4(5,4;n)$ is three. We prove a superexponential lower bound for $r_4(5,4;n)$, which improves the previous best lower bound $r_4(5,4;n)\geq 2^{\Omega(n^2)}$ from Mubayi and Suk (\emph{J. Eur. Math. Soc., 2020}). Second, we prove an upper bound for the hypergraph Erd\H{o}s-Rogers function $f^{(k)}_{k+1,k+2}(N)$ that is an iterated $(k-3)$-fold logarithm in $N$ for each $k\geq 5$. This improves the previous upper bound that is an iterated $(k-13)$-fold logarithm in $N$ for $k\ge14$ due to Mubayi and Suk (\emph{J. London Math. Soc., 2018}), in which they conjectured that $f^{(k)}_{k+1,k+2}(N)$ is an iterated $(k-2)$-fold logarithm in $N$ for each $k\ge3$., Comment: 18 pages

Recent advancements in character video synthesis still depend on extensive fine-tuning or complex 3D modeling processes, which can restrict accessibility and hinder real-time applicability. To address these challenges, we propose a simple yet effective tuning-free framework for character video synthesis, named MovieCharacter, designed to streamline the synthesis process while ensuring high-quality outcomes. Our framework decomposes the synthesis task into distinct, manageable modules: character segmentation and tracking, video object removal, character motion imitation, and video composition. This modular design not only facilitates flexible customization but also ensures that each component operates collaboratively to effectively meet user needs. By leveraging existing open-source models and integrating well-established techniques, MovieCharacter achieves impressive synthesis results without necessitating substantial resources or proprietary datasets. Experimental results demonstrate that our framework enhances the efficiency, accessibility, and adaptability of character video synthesis, paving the way for broader creative and interactive applications.

Autoformalization, the task of automatically translating natural language descriptions into a formal language, poses a significant challenge across various domains, especially in mathematics. Recent advancements in large language models (LLMs) have unveiled their promising capabilities to formalize even competition-level math problems. However, we observe a considerable discrepancy between pass@1 and pass@k accuracies in LLM-generated formalizations. To address this gap, we introduce a novel framework that scores and selects the best result from k autoformalization candidates based on two complementary self-consistency methods: symbolic equivalence and semantic consistency. Elaborately, symbolic equivalence identifies the logical homogeneity among autoformalization candidates using automated theorem provers, and semantic consistency evaluates the preservation of the original meaning by informalizing the candidates and computing the similarity between the embeddings of the original and informalized texts. Our extensive experiments on the MATH and miniF2F datasets demonstrate that our approach significantly enhances autoformalization accuracy, achieving up to 0.22-1.35x relative improvements across various LLMs and baseline methods., Comment: Published as a conference paper at NeurIPS 2024. Code is available at [this https URL](https://github.com/Miracle-Messi/Isa-AutoFormal)

Consider a market where a seller owns an item for sale and a buyer wants to purchase it. Each player has private information, known as their type. It can be costly and difficult for the players to reach an agreement through direct communication. However, with a mediator as a trusted third party, both players can communicate privately with the mediator without worrying about leaking too much or too little information. The mediator can design and commit to a multi-round communication protocol for both players, in which they update their beliefs about the other player's type. The mediator cannot force the players to trade but can influence their behaviors by sending messages to them. We study the problem of designing revenue-maximizing mechanisms for the mediator. We show that the mediator can, without loss of generality, focus on a set of direct and incentive-compatible mechanisms. We then formulate this problem as a mathematical program and provide an optimal solution in closed form under a regularity condition. Our mechanism is simple and has a threshold structure. Additionally, we extend our results to general cases by utilizing a variant version of the ironing technique. In the end, we discuss some interesting properties revealed from the optimal mechanism, such as, in the optimal mechanism, the mediator may even lose money in some cases.

Hu and Ye conjectured that for a $k$-th order and $n$-dimensional tensor $\mathcal{A}$ with an eigenvalue $\lambda$ and the corresponding eigenvariety $\mathcal{V}_\lambda(\mathcal{A})$, $$\mathrm{am}(\lambda) \ge \sum_{i=1}^\kappa \mathrm{dim}(V_i)(k-1)^{\mathrm{dim}(V_i)-1},$$ where $\mathrm{am}(\lambda)$ is the algebraic multiplicity of $\lambda$, and $V_1,\ldots,V_\kappa$ are all irreducible components of $\mathcal{V}_\lambda(\mathcal{A})$. In this paper, we prove that if $\mathcal{A}$ is a nonnegative weakly irreducible tensor with spectral radius $\rho$, then $\mathrm{am}(\lambda) \ge |\mathbb{V}_\lambda(\mathcal{A})|$ for all eigenvalues $\lambda$ of $\mathcal{A}$ with modulus $\rho$, where $\mathbb{V}_\lambda(\mathcal{A})$ is the projective eigenvariety of $\mathcal{A}$ associated with $\lambda$. Consequently we confirm Hu-Ye's conjecture for the above eigenvalues $\lambda$ of $\mathcal{A}$ and the least H-eigenvalue of a weakly irreducible $Z$-tensor. We prove the equality case in Hu-Ye's conjecture for some eigenvalues of the adjacency tensor or Laplacian tensor of several classes of hypergraphs.

Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular ways to predict deformations for Gaussian-based dynamic scene rendering models. However, plane-based methods rely on the inappropriate low-rank assumption and excessively decompose the space-time 4D encoding, resulting in overmuch feature overlap and unsatisfactory rendering quality. To tackle these problems, we propose Grid4D, a dynamic scene rendering model based on Gaussian splatting and employing a novel explicit encoding method for the 4D input through the hash encoding. Different from plane-based explicit representations, we decompose the 4D encoding into one spatial and three temporal 3D hash encodings without the low-rank assumption. Additionally, we design a novel attention module that generates the attention scores in a directional range to aggregate the spatial and temporal features. The directional attention enables Grid4D to more accurately fit the diverse deformations across distinct scene components based on the spatial encoded features. Moreover, to mitigate the inherent lack of smoothness in explicit representation methods, we introduce a smooth regularization term that keeps our model from the chaos of deformation prediction. Our experiments demonstrate that Grid4D significantly outperforms the state-of-the-art models in visual quality and rendering speed., Comment: Accepted by NeurIPS 2024

The goal of the acoustic scene classification (ASC) task is to classify recordings into one of the predefined acoustic scene classes. However, in real-world scenarios, ASC systems often encounter challenges such as recording device mismatch, low-complexity constraints, and the limited availability of labeled data. To alleviate these issues, in this paper, a data-efficient and low-complexity ASC system is built with a new model architecture and better training strategies. Specifically, we firstly design a new low-complexity architecture named Rep-Mobile by integrating multi-convolution branches which can be reparameterized at inference. Compared to other models, it achieves better performance and less computational complexity. Then we apply the knowledge distillation strategy and provide a comparison of the data efficiency of the teacher model with different architectures. Finally, we propose a progressive pruning strategy, which involves pruning the model multiple times in small amounts, resulting in better performance compared to a single step pruning. Experiments are conducted on the TAU dataset. With Rep-Mobile and these training strategies, our proposed ASC system achieves the state-of-the-art (SOTA) results so far, while also winning the first place with a significant advantage over others in the DCASE2024 Challenge., Comment: submitted to ICASSP 2025

To identify security vulnerabilities in Android applications, numerous static application security testing (SAST) tools have been proposed. However, it poses significant challenges to assess their overall performance on diverse vulnerability types. The task is non-trivial and poses considerable challenges. {Firstly, the absence of a unified evaluation platform for defining and describing tools' supported vulnerability types, coupled with the lack of normalization for the intricate and varied reports generated by different tools, significantly adds to the complexity.} Secondly, there is a scarcity of adequate benchmarks, particularly those derived from real-world scenarios. To address these problems, we are the first to propose a unified platform named VulsTotal, supporting various vulnerability types, enabling comprehensive and versatile analysis across diverse SAST tools. Specifically, we begin by meticulously selecting 11 free and open-sourced SAST tools from a pool of 97 existing options, adhering to clearly defined criteria. After that, we invest significant efforts in comprehending the detection rules of each tool, subsequently unifying 67 general/common vulnerability types for {Android} SAST tools. We also redefine and implement a standardized reporting format, ensuring uniformity in presenting results across all tools. Additionally, to mitigate the problem of benchmarks, we conducted a manual analysis of huge amounts of CVEs to construct a new CVE-based benchmark based on our comprehension of Android app vulnerabilities. Leveraging the evaluation platform, which integrates both existing synthetic benchmarks and newly constructed CVE-based benchmarks from this study, we conducted a comprehensive analysis to evaluate and compare these selected tools from various perspectives, such as general vulnerability type coverage, type consistency, tool effectiveness, and time performance., Comment: Accepted by TSE

The Einstein Probe (EP) satellite, dedicated at time-domain high-energy astrophysics and multi-messenger astronomy, was recently launched and successfully put into operation. The wide-field X-ray telescope (WXT, 0.5-4 keV) onboard has identified multiple gamma-ray burst (GRB) events, with an average duration of approximately 100 seconds. This duration is several times longer than the average duration of long gamma-ray bursts (LGRBs) detected by the Neil Gehrels Swift Observatory, which typically stands at around 20 seconds. Additionally, EP has detected some unknown X-ray transients whose connection to GRBs is uncertain, due to the absence of gamma-ray counterparts and efficient follow-up observation at multi-wavelengths. It is urgent to understand the physical origin of the intriguing EP GRBs. Inspired by studies of GRB 170817A, we suggest that EP GRBs may primarily consist of off-axis viewed bursts, forming a unique population among the GRB zoo. Based on LGRBs' statistical properties during the prompt phase, we explore observable properties of on-axis and off-axis LGRBs in the soft X-ray band. We predict the characteristics of several observables for these GRBs, including the duration, energy fluence, low-energy spectral index, and the slopes of Amati and Yonetoku relations, which could be tested with a larger sample of GRB events detected by EP in the future., Comment: 19 pages, 10 figures