Search

Due to the impressive capabilities of multimodal large language models (MLLMs), recent works have focused on employing MLLM-based agents for autonomous driving in large-scale and dynamic environments. However, prevalent approaches often directly translate high-level instructions into low-level vehicle control signals, which deviates from the inherent language generation paradigm of MLLMs and fails to fully harness their emergent powers. As a result, the generalizability of these methods is highly restricted by autonomous driving datasets used during fine-tuning. To tackle this challenge, we propose to connect high-level instructions and low-level control signals with mid-level language-driven commands, which are more fine-grained than high-level instructions but more universal and explainable than control signals, and thus can effectively bridge the gap in between. We implement this idea through a hierarchical multi-agent driving system named AD-H, including a MLLM planner for high-level reasoning and a lightweight controller for low-level execution. The hierarchical design liberates the MLLM from low-level control signal decoding and therefore fully releases their emergent capability in high-level perception, reasoning, and planning. We build a new dataset with action hierarchy annotations. Comprehensive closed-loop evaluations demonstrate several key advantages of our proposed AD-H system. First, AD-H can notably outperform state-of-the-art methods in achieving exceptional driving performance, even exhibiting self-correction capabilities during vehicle operation, a scenario not encountered in the training dataset. Second, AD-H demonstrates superior generalization under long-horizon instructions and novel environmental conditions, significantly surpassing current state-of-the-art methods. We will make our data and code publicly accessible at https://github.com/zhangzaibin/AD-H

Room acoustic parameters (RAPs) and room physical parameters ( RPPs) are essential metrics for parameterizing the room acoustical characteristics (RAC) of a sound field around a listener's local environment, offering comprehensive indications for various applications. The current RAPs and RPPs estimation methods either fall short of covering broad real-world acoustic environments in the context of real background noise or lack universal frameworks for blindly estimating RAPs and RPPs from noisy single-channel speech signals, particularly sound source distances, direction-of-arrival (DOA) of sound sources, and occupancy levels. On the other hand, in this paper, we propose a novel universal blind estimation framework called the blind estimator of room acoustical and physical parameters (BERP), by introducing a new stochastic room impulse response (RIR) model, namely, the sparse stochastic impulse response (SSIR) model, and endowing the BERP with a unified encoder and multiple separate predictors to estimate RPPs and SSIR parameters in parallel. This estimation framework enables the computationally efficient and universal estimation of room parameters by solely using noisy single-channel speech signals. Finally, all the RAPs can be simultaneously derived from the RIRs synthesized from SSIR model with the estimated parameters. To evaluate the effectiveness of the proposed BERP and SSIR models, we compile a task-specific dataset from several publicly available datasets. The results reveal that the BERP achieves state-of-the-art (SOTA) performance. Moreover, the evaluation results pertaining to the SSIR RIR model also demonstrated its efficacy. The code is available on GitHub., Comment: 13-page, Submitted to IEEE/ACM Transaction on Audio Speech and Language Processing (TASLP)

The formation of protostellar disks is still a mystery, largely due to the difficulties in observations that can constrain theories. For example, the 3D alignment between the rotation of the disk and the magnetic fields (B-fields) in the formation environment is critical in some models, but so far impossible to observe. Here, we study the possibility of probing the alignment between B-field and disk rotation using ``polarization holes'' (PHs). PHs are widely observed and are caused by unresolved B-field structures. With ideal magnetohydrodynamic (MHD) simulations, we demonstrate that different initial alignments between B-field and angular momentum (AM) can result in B-field structures that are distinct enough to produce distinguishable PHs. Thus PHs can potentially serve as probes for alignments between B-field and AM in disk formation., Comment: accepted by The Astrophysical Journal

Multimodal Large Language Model (MLLMs) leverages Large Language Models as a cognitive framework for diverse visual-language tasks. Recent efforts have been made to equip MLLMs with visual perceiving and grounding capabilities. However, there still remains a gap in providing fine-grained pixel-level perceptions and extending interactions beyond text-specific inputs. In this work, we propose {\bf{AnyRef}}, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references, such as texts, boxes, images, or audio. This innovation empowers users with greater flexibility to engage with the model beyond textual and regional prompts, without modality-specific designs. Through our proposed refocusing mechanism, the generated grounding output is guided to better focus on the referenced object, implicitly incorporating additional pixel-level supervision. This simple modification utilizes attention scores generated during the inference of LLM, eliminating the need for extra computations while exhibiting performance enhancements in both grounding masks and referring expressions. With only publicly available training data, our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation., Comment: CVPR 2024

In order to solve the problems of long training time, large consumption of computing resources and huge parameter amount of GAN network in image generation, this paper proposes an improved GAN network model, which is named Faster Projected GAN, based on Projected GAN. The proposed network is mainly focuses on the improvement of generator of Projected GAN. By introducing depth separable convolution (DSC), the number of parameters of the Projected GAN is reduced, the training speed is accelerated, and memory is saved. Experimental results show that on ffhq-1k, art-painting, Landscape and other few-shot image datasets, a 20% speed increase and a 15% memory saving are achieved. At the same time, FID loss is less or no loss, and the amount of model parameters is better controlled. At the same time, significant training speed improvement has been achieved in the small sample image generation task of special scenes such as earthquake scenes with few public datasets., Comment: 9 pages,7 figures,4 tables

Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound capabilities in collective intelligence. However, the potential misuse of this intelligence for malicious purposes presents significant risks. To date, comprehensive research on the safety issues associated with multi-agent systems remains limited. In this paper, we explore these concerns through the innovative lens of agent psychology, revealing that the dark psychological states of agents constitute a significant threat to safety. To tackle these concerns, we propose a comprehensive framework (PsySafe) grounded in agent psychology, focusing on three key areas: firstly, identifying how dark personality traits in agents can lead to risky behaviors; secondly, evaluating the safety of multi-agent systems from the psychological and behavioral perspectives, and thirdly, devising effective strategies to mitigate these risks. Our experiments reveal several intriguing phenomena, such as the collective dangerous behaviors among agents, agents' self-reflection when engaging in dangerous behavior, and the correlation between agents' psychological assessments and dangerous behaviors. We anticipate that our framework and observations will provide valuable insights for further research into the safety of multi-agent systems. We will make our data and code publicly accessible at https://github.com/AI4Good24/PsySafe.

A univariate continuous function can always be decomposed as the sum of a non-increasing function and a non-decreasing one. Based on this property, we propose a non-parametric regression method that combines two spline-fitted monotone curves. We demonstrate by extensive simulations that, compared to standard spline-fitting methods, the proposed approach is particularly advantageous in high-noise scenarios. Several theoretical guarantees are established for the proposed approach. Additionally, we present statistics to test the monotonicity of a function based on monotone decomposition, which can better control Type I error and achieve comparable (if not always higher) power compared to existing methods. Finally, we apply the proposed fitting and testing approaches to analyze the single-cell pseudotime trajectory datasets, identifying significant biological insights for non-monotonically expressed genes through Gene Ontology enrichment analysis. The source code implementing the methodology and producing all results is accessible at https://github.com/szcf-weiya/MonotoneDecomposition.jl.

We propose an efficient deterministic method to calculate the full configuration interaction (FCI) ground state energy. This method leverages the sparseness of the Lanczos basis vectors that span the Krylov subspace associated with the Hamiltonian to rapidly calculate the lowest eigenvalue of the effective Hamiltonian formed in this basis. By iteratively performing the spanning and diagonalization steps, this method is capable of rapidly reaching chemical accuracy for a variety of strongly correlated molecules, including stretched N$_2$ and C$_2$, in merely several tens of iterations. To accelerate our algorithm, we implement parallelized sparse matrix-sparse vector multiplication, which features a novel hashing method that establishes a one-to-one correspondence between the set of full configuration Slater determinants and a set of consecutive integers. A near-linear acceleration was observed., Comment: Added references and corrected typos

Model degrees of freedom ($\df$) is a fundamental concept in statistics because it quantifies the flexibility of a fitting procedure and is indispensable in model selection. The $\df$ is often intuitively equated with the number of independent variables in the fitting procedure. But for adaptive regressions that perform variable selection (e.g., the best subset regressions), the model $\df$ is larger than the number of selected variables. The excess part has been defined as the \emph{search degrees of freedom} ($\sdf$) to account for model selection. However, this definition is limited since it does not consider fitting procedures in augmented space, such as splines and regression trees; and it does not use the same fitting procedure for $\sdf$ and $\df$. For example, the lasso's $\sdf$ is defined through the \emph{relaxed} lasso's $\df$ instead of the lasso's $\df$. Here we propose a \emph{modified search degrees of freedom} ($\msdf$) to directly account for the cost of searching in the original or augmented space. Since many fitting procedures can be characterized by a linear operator, we define the search cost as the effort to determine such a linear operator. When we construct a linear operator for the lasso via the iterative ridge regression, $\msdf$ offers a new perspective for its search cost. For some complex procedures such as the multivariate adaptive regression splines (MARS), the search cost needs to be pre-determined to serve as a tuning parameter for the procedure itself, but it might be inaccurate. To investigate the inaccurate pre-determined search cost, we develop two concepts, \emph{nominal} $\df$ and \emph{actual} $\df$, and formulate a property named \emph{self-consistency} when there is no gap between the \emph{nominal} $\df$ and the \emph{actual} $\df$.

Recent leading zero-shot video object segmentation (ZVOS) works devote to integrating appearance and motion information by elaborately designing feature fusion modules and identically applying them in multiple feature stages. Our preliminary experiments show that with the strong long-range dependency modeling capacity of Transformer, simply concatenating the two modality features and feeding them to vanilla Transformers for feature fusion can distinctly benefit the performance but at a cost of heavy computation. Through further empirical analysis, we find that attention dependencies learned in Transformer in different stages exhibit completely different properties: global query-independent dependency in the low-level stages and semantic-specific dependency in the high-level stages. Motivated by the observations, we propose two Transformer variants: i) Context-Sharing Transformer (CST) that learns the global-shared contextual information within image frames with a lightweight computation. ii) Semantic Gathering-Scattering Transformer (SGST) that models the semantic correlation separately for the foreground and background and reduces the computation cost with a soft token merging mechanism. We apply CST and SGST for low-level and high-level feature fusions, respectively, formulating a level-isomerous Transformer framework for ZVOS task. Compared with the baseline that uses vanilla Transformers for multi-stage fusion, ours significantly increase the speed by 13 times and achieves new state-of-the-art ZVOS performance. Code is available at https://github.com/DLUT-yyc/Isomer., Comment: ICCV2023

Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly still treat it as two individual learning tasks, which limits their potential for exploring cross-domain information. We propose a deeply unified framework for depth-aware panoptic segmentation, which performs joint segmentation and depth estimation both in a per-segment manner with identical object queries. To narrow the gap between the two tasks, we further design a geometric query enhancement method, which is able to integrate scene geometry into object queries using latent representations. In addition, we propose a bi-directional guidance learning approach to facilitate cross-task feature learning by taking advantage of their mutual relations. Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets. Moreover, our guidance learning approach is shown to deliver performance improvement even under incomplete supervision labels., Comment: to be published in ICCV 2023

We present a method for fitting monotone curves using cubic B-splines, which is equivalent to putting a monotonicity constraint on the coefficients. We explore different ways of enforcing this constraint and analyze their theoretical and empirical properties. We propose two algorithms for solving the spline fitting problem: one that uses standard optimization techniques and one that trains a Multi-Layer Perceptrons (MLP) generator to approximate the solutions under various settings and perturbations. The generator approach can speed up the fitting process when we need to solve the problem repeatedly, such as when constructing confidence bands using bootstrap. We evaluate our method against several existing methods, some of which do not use the monotonicity constraint, on some monotone curves with varying noise levels. We demonstrate that our method outperforms the other methods, especially in high-noise scenarios. We also apply our method to analyze the polarization-hole phenomenon during star formation in astrophysics. The source code is accessible at \texttt{\url{https://github.com/szcf-weiya/MonotoneSplines.jl}}.

A popular approach for constructing bird's-eye-view (BEV) representation in 3D detection is to lift 2D image features onto the viewing frustum space based on explicitly predicted depth distribution. However, depth distribution can only characterize the 3D geometry of visible object surfaces but fails to capture their internal space and overall geometric structure, leading to sparse and unsatisfactory 3D representations. To mitigate this issue, we present BEV-IO, a new 3D detection paradigm to enhance BEV representation with instance occupancy information. At the core of our method is the newly-designed instance occupancy prediction (IOP) module, which aims to infer point-level occupancy status for each instance in the frustum space. To ensure training efficiency while maintaining representational flexibility, it is trained using the combination of both explicit and implicit supervision. With the predicted occupancy, we further design a geometry-aware feature propagation mechanism (GFP), which performs self-attention based on occupancy distribution along each ray in frustum and is able to enforce instance-level feature consistency. By integrating the IOP module with GFP mechanism, our BEV-IO detector is able to render highly informative 3D scene structures with more comprehensive BEV representations. Experimental results demonstrate that BEV-IO can outperform state-of-the-art methods while only adding a negligible increase in parameters (0.2%) and computational overhead (0.24%in GFLOPs)., Comment: v2

Over the past few decades, fiber-optic time synchronization (FOTS) has provided fundamental support for the efficient operation of modern society. Looking toward the future beyond fifth-generation/sixth-generation (B5G/6G) scenarios and very large radio telescope arrays, developing high-precision, low-complexity and scalable FOTS technology is crucial for building a large-scale time synchronization network. However, the traditional two-way FOTS method needs a data layer to exchange time delay information. This increases the complexity of system and makes it impossible to realize multiple-access time synchronization. In this paper, a time reversal enabled FOTS method is proposed. It measures the clock difference between two locations without involving a data layer, which can reduce the complexity of the system. Moreover, it can also achieve multiple-access time synchronization along the fiber link. Tests over a 230 km fiber link have been carried out to demonstrate the high performance of the proposed method.

Compared with traditional RGB-only visual tracking, few datasets have been constructed for RGB-D tracking. In this paper, we propose ARKitTrack, a new RGB-D tracking dataset for both static and dynamic scenes captured by consumer-grade LiDAR scanners equipped on Apple's iPhone and iPad. ARKitTrack contains 300 RGB-D sequences, 455 targets, and 229.7K video frames in total. Along with the bounding box annotations and frame-level attributes, we also annotate this dataset with 123.9K pixel-level target masks. Besides, the camera intrinsic and camera pose of each frame are provided for future developments. To demonstrate the potential usefulness of this dataset, we further present a unified baseline for both box-level and pixel-level tracking, which integrates RGB features with bird's-eye-view representations to better explore cross-modality 3D geometry. In-depth empirical analysis has verified that the ARKitTrack dataset can significantly facilitate RGB-D tracking and that the proposed baseline method compares favorably against the state of the arts. The code and dataset is available at https://arkittrack.github.io., Comment: Accepted by CVPR2023

The speech transmission index (STI) and room acoustic parameters (RAPs), which are derived from a room impulse response (RIR), such as reverberation time and early decay time, are essential to assess speech transmission and to predict the listening difficulty in a sound field. Since it is difficult to measure RIR in daily occupied spaces, simultaneous blind estimation of STI and RAPs must be resolved as it is an imperative and challenging issue. This paper proposes a deterministic method for blindly estimating STI and five RAPs on the basis of an RIR stochastic model that approximates an unknown RIR. The proposed method formulates a temporal power envelope of a reverberant speech signal to obtain the optimal parameters for the RIR model. Simulations were conducted to evaluate STI and RAPs from observed reverberant speech signals. The root-mean-square errors between the estimated and ground-truth results were used to comparatively evaluate the proposed method with the previous method. The results showed that the proposed method can estimate STI and RAPs effectively without any training., Comment: 5-pages, 3 figures, 2 tables

Time delay estimation (TDE) is an important step to identify and locate vibration source. The TDE result can be obtained by cross-correlation method through seeking the maximum correlation peak of two signals. However, the cross-correlation method will induce random error when dealing with the nonstationary signal. We propose a novel time shifting deviation (TSDEV) method to solve this problem, which has been proved to achieve ultrahigh precision localization result in the fiber vibration monitoring system. This paper compares TSDEV method with cross-correlation in detail by simulating TDE process in different conditions, such as signals with arbitrary intercepted length, nonstationary drift and correlated noise. Besides, experimental demonstration has been carried out on 60 km fiber to localize a wide band vibration signal. The typical localization error is 2 m with standard deviation of 21.4 m using TSDEV method. It stands in clear contrast to the result of cross-correlation method, whose localization error is 70 m and the standard deviation is 208.4 m. Compared with cross-correlation method, TSDEV has the same resistance to white noise, but has fewer boundary conditions and better suppression on linear drift or common noise, which leads to more precise TDE results., Comment: 7 pages, 6 figures, submitted to Journal of Lightwave Technology