arXiv subjects

Wei Yang

Publications and source records attributed to Wei Yang.

At least 253 records · Page 14Linked to original sources

arXiv2024

Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model

The essence of multi-modal fusion lies in exploiting the complementary information inherent in diverse modalities. However, prevalent fusion methods rely on traditional neural architectures and are inadequately equipped to capture the dynamics of interactions across modalities, particularly in presence of complex intra- and inter-modality correlations. Recent advancements in State Space Models (SSMs), notably exemplified by the Mamba model, have emerged as promising contenders. Particularly, its state evolving process implies stronger modality fusion paradigm, making multi-modal fusion on SSMs an appealing direction. However, fusing multiple modalities is challenging for SSMs due to its hardware-aware parallelism designs. To this end, this paper proposes the Coupled SSM model, for coupling state chains of multiple modalities while maintaining independence of intra-modality state processes. Specifically, in our coupled scheme, we devise an inter-modal hidden states transition scheme, in which the current state is dependent on the states of its own chain and that of the neighbouring chains at the previous time-step. To fully comply with the hardware-aware parallelism, we devise an expedite coupled state transition scheme and derive its corresponding global convolution kernel for parallelism. Extensive experiments on CMU-MOSEI, CH-SIMS, CH-SIMSV2 through multi-domain input verify the effectiveness of our model compared to current state-of-the-art methods, improved F1-Score by 0.4\%, 0.9\%, and 2.3\% on the three datasets respectively, 49\% faster inference and 83.7\% GPU memory save. The results demonstrate that Coupled Mamba model is capable of enhanced multi-modal fusion.

cs.AI↗

arXiv2024

LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models

In this paper, we make the first attempt to understand and test potential computation efficiency robustness in state-of-the-art LLMs. By analyzing the working mechanism and implementation of 20,543 public-accessible LLMs, we observe a fundamental property in LLMs that could be manipulated in an adversarial manner to reduce computation efficiency significantly. Our key motivation is to generate test inputs that could sufficiently delay the generation of EOS such that LLMs would have to go through enough iterations to satisfy the pre-configured threshold. We present \tool, which can work under both white-box setting and black-box setting. In the white-box scenario, \tool develops a gradient-guided technique that searches for a minimal and unnoticeable perturbation at character-level, token-level, and structure-level. In the black-box scenario, \tool employs a causal inference-based approach to find critical tokens and similarly applies three levels of imperceptible perturbation to them. Both the white-box and black-box settings effectively delay the appearance of EOS, compelling these inputs to reach the naturally-unreachable threshold. To demonstrate the effectiveness of \tool, we conduct a systematic evaluation on nine public-available LLMs: Google T5, AllenAI WMT14, Helsinki-NLP translator, Facebook FairSeq, UNICAMP-DL translator, MarianMT, Google FLAN-T5, MBZUAI LaMini-GPT and Salesforce CodeGen. Experimental results show that \tool can increase on average LLMs' response latency and energy consumption by 325\% to 3244\% and 344\% to 3616\%, respectively, by perturbing just one character or token in the input sentence.

cs.CL↗

arXiv2024

Correlated Charge Density Wave Insulators in Chirally Twisted Triple Bilayer Graphene

Electrons residing in flat-band system can play a vital role in triggering spectacular phenomenology due to relatively large interactions and spontaneous breaking of different degeneracies. In this work we demonstrate chirally twisted triple bilayer graphene, a new moiré structure formed by three pieces of helically stacked Bernal bilayer graphene, as a highly tunable flat-band system. In addition to the correlated insulators showing at integer moiré fillings, commonly attributed to interaction induced symmetry broken isospin flavors in graphene, we observe abundant insulating states at half-integer moiré fillings, suggesting a longer-range interaction and the formation of charge density wave insulators which spontaneously break the moiré translation symmetry. With weak out-of-plane magnetic field applied, as observed half-integer filling states are enhanced and more quarter-integer filling states appear, pointing towards further quadrupling moiré unit cells. The insulating states at fractional fillings combined with Hartree-Fock calculations demonstrate the observation of a new type of correlated charge density wave insulators in graphene and points to a new accessible twist manner engineering correlated moiré electronics.

cond-mat.mes-hall↗

arXiv2024

AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System

Vision-based teleoperation offers the possibility to endow robots with human-level intelligence to physically interact with the environment, while only requiring low-cost camera sensors. However, current vision-based teleoperation systems are designed and engineered towards a particular robot model and deploy environment, which scales poorly as the pool of the robot models expands and the variety of the operating environment increases. In this paper, we propose AnyTeleop, a unified and general teleoperation system to support multiple different arms, hands, realities, and camera configurations within a single system. Although being designed to provide great flexibility to the choice of simulators and real hardware, our system can still achieve great performance. For real-world experiments, AnyTeleop can outperform a previous system that was designed for a specific robot hardware with a higher success rate, using the same robot. For teleoperation in simulation, AnyTeleop leads to better imitation learning performance, compared with a previous system that is particularly designed for that simulator. Project page: https://yzqin.github.io/anyteleop/.

cs.RO↗

arXiv2024

Sifting out communities in large sparse networks

Research data sets are growing to unprecedented sizes and network modeling is commonly used to extract complex relationships in diverse domains, such as genetic interactions involved in disease, logistics, and social communities. As the number of nodes increases in a network, an increasing sparsity of edges is a practical limitation due to memory restrictions. Moreover, many of these sparse networks exhibit very large numbers of nodes with no adjacent edges, as well as disjoint components of nodes with no edges connecting them. A prevalent aim in network modeling is the identification of clusters, or communities, of nodes that are highly interrelated. Several definitions of strong community structure have been introduced to facilitate this task, each with inherent assumptions and biases. We introduce an intuitive objective function for quantifying the quality of clustering results in large sparse networks. We utilize a two-step method for identifying communities which is especially well-suited for this domain as the first step efficiently divides the network into the disjoint components, while the second step optimizes clustering of the produced components based on the new objective. Using simulated networks, optimization based on the new objective function consistently yields significantly higher accuracy than those based on the modularity function, with the widest gaps appearing for the noisiest networks. Additionally, applications to benchmark problems illustrate the intuitive correctness of our approach. Finally, the practicality of our approach is demonstrated in real-world data in which we identify complex genetic interactions in large-scale networks comprised of tens of thousands of nodes. Based on these three different types of trials, our results clearly demonstrate the usefulness of our two-step procedure and the accuracy of our simple objective.

cs.SI↗

arXiv2024

A Basis-preserving Algorithm for Computing the Bezout Matrix of Newton Polynomials

This paper tackles the problem of constructing Bezout matrices for Newton polynomials in a basis-preserving approach that operates directly with the given Newton basis, thus avoiding the need for transformation from Newton basis to monomial basis. This approach significantly reduces the computational cost and also mitigates numerical instability caused by basis transformation. For this purpose, we investigate the internal structure of Bezout matrices in Newton basis and design a basis-preserving algorithm that generates the Bezout matrix in the specified basis used to formulate the input polynomials. Furthermore, we show an application of the proposed algorithm on constructing confederate resultant matrices for Newton polynomials. Experimental results demonstrate that the proposed methods perform superior to the basis-transformation-based ones.

cs.SC↗

arXiv2024

PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning

Centralized Training with Decentralized Execution (CTDE) has emerged as a widely adopted paradigm in multi-agent reinforcement learning, emphasizing the utilization of global information for learning an enhanced joint $Q$-function or centralized critic. In contrast, our investigation delves into harnessing global information to directly enhance individual $Q$-functions or individual actors. Notably, we discover that applying identical global information universally across all agents proves insufficient for optimal performance. Consequently, we advocate for the customization of global information tailored to each agent, creating agent-personalized global information to bolster overall performance. Furthermore, we introduce a novel paradigm named Personalized Training with Distilled Execution (PTDE), wherein agent-personalized global information is distilled into the agent's local information. This distilled information is then utilized during decentralized execution, resulting in minimal performance degradation. PTDE can be seamlessly integrated with state-of-the-art algorithms, leading to notable performance enhancements across diverse benchmarks, including the SMAC benchmark, Google Research Football (GRF) benchmark, and Learning to Rank (LTR) task.

cs.AI↗

arXiv2024

EfficientGS: Streamlining Gaussian Splatting for Large-Scale High-Resolution Scene Representation

In the domain of 3D scene representation, 3D Gaussian Splatting (3DGS) has emerged as a pivotal technology. However, its application to large-scale, high-resolution scenes (exceeding 4k$\times$4k pixels) is hindered by the excessive computational requirements for managing a large number of Gaussians. Addressing this, we introduce 'EfficientGS', an advanced approach that optimizes 3DGS for high-resolution, large-scale scenes. We analyze the densification process in 3DGS and identify areas of Gaussian over-proliferation. We propose a selective strategy, limiting Gaussian increase to key primitives, thereby enhancing the representational efficiency. Additionally, we develop a pruning mechanism to remove redundant Gaussians, those that are merely auxiliary to adjacent ones. For further enhancement, we integrate a sparse order increment for Spherical Harmonics (SH), designed to alleviate storage constraints and reduce training overhead. Our empirical evaluations, conducted on a range of datasets including extensive 4K+ aerial images, demonstrate that 'EfficientGS' not only expedites training and rendering times but also achieves this with a model size approximately tenfold smaller than conventional 3DGS while maintaining high rendering fidelity.

cs.CV↗

arXiv2024

Unsourced Random Access in MIMO Quasi-Static Rayleigh Fading Channels with Finite Blocklength

This paper explores the fundamental limits of unsourced random access (URA) with a random and unknown number ${\rm{K}}_a$ of active users in MIMO quasi-static Rayleigh fading channels. First, we derive an upper bound on the probability of incorrectly estimating the number of active users. We prove that it exponentially decays with the number of receive antennas and eventually vanishes, whereas reaches a plateau as the power and blocklength increase. Then, we derive non-asymptotic achievability and converse bounds on the minimum energy-per-bit required by each active user to reliably transmit $J$ bits with blocklength $n$. Numerical results verify the tightness of our bounds, suggesting that they provide benchmarks to evaluate existing schemes. The extra required energy-per-bit due to the uncertainty of the number of active users decreases as $\mathbb{E}[{\rm{K}}_a]$ increases. Compared to random access with individual codebooks, the URA paradigm achieves higher spectral and energy efficiency. Moreover, using codewords distributed on a sphere is shown to outperform the Gaussian random coding scheme in the non-asymptotic regime.

cs.IT↗

arXiv2024

DoseDiff: Distance-aware Diffusion Model for Dose Prediction in Radiotherapy

Treatment planning, which is a critical component of the radiotherapy workflow, is typically carried out by a medical physicist in a time-consuming trial-and-error manner. Previous studies have proposed knowledge-based or deep-learning-based methods for predicting dose distribution maps to assist medical physicists in improving the efficiency of treatment planning. However, these dose prediction methods usually fail to effectively utilize distance information between surrounding tissues and targets or organs-at-risk (OARs). Moreover, they are poor at maintaining the distribution characteristics of ray paths in the predicted dose distribution maps, resulting in a loss of valuable information. In this paper, we propose a distance-aware diffusion model (DoseDiff) for precise prediction of dose distribution. We define dose prediction as a sequence of denoising steps, wherein the predicted dose distribution map is generated with the conditions of the computed tomography (CT) image and signed distance maps (SDMs). The SDMs are obtained by distance transformation from the masks of targets or OARs, which provide the distance from each pixel in the image to the outline of the targets or OARs. We further propose a multi-encoder and multi-scale fusion network (MMFNet) that incorporates multi-scale and transformer-based fusion modules to enhance information fusion between the CT image and SDMs at the feature level. We evaluate our model on two in-house datasets and a public dataset, respectively. The results demonstrate that our DoseDiff method outperforms state-of-the-art dose prediction methods in terms of both quantitative performance and visual quality.

eess.IV↗

arXiv2024

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning, as long as its CAD model is given, or a small number of reference images are captured. We bridge the gap between these two setups with a neural implicit representation that allows for effective novel view synthesis, keeping the downstream pose estimation modules invariant under the same unified framework. Strong generalizability is achieved via large-scale synthetic training, aided by a large language model (LLM), a novel transformer-based architecture, and contrastive learning formulation. Extensive evaluation on multiple public datasets involving challenging scenarios and objects indicate our unified approach outperforms existing methods specialized for each task by a large margin. In addition, it even achieves comparable results to instance-level methods despite the reduced assumptions. Project page: https://nvlabs.github.io/FoundationPose/

cs.CV↗

arXiv2024

RISAR: RIS-assisted Human Activity Recognition with Commercial Wi-Fi Devices

Human activity recognition (HAR) holds significant importance in smart homes, security, and healthcare. Existing systems face limitations because of the insufficient spatial diversity provided by a limited number of antennas. Furthermore, inefficiencies in noise reduction and feature extraction from sensing data pose challenges to recognition performance. This study presents a reconfigurable intelligent surface (RIS)-assisted passive human activity recognition (RISAR) method, compatible with commercial Wi-Fi devices. RISAR leverages a RIS to enhance the spatial diversity of Wi-Fi signals, effectively capturing a wider range of information distributed across the spatial domain. A novel high-dimensional factor model based on random matrix theory is proposed to address noise reduction and feature extraction in the temporal domain. A dual-stream spatial-temporal attention network model is developed to assign variable weights to different characteristics and sequences, mimicking human cognitive processes in prioritizing essential information. Experimental analysis shows that RISAR significantly outperforms existing HAR methods in accuracy and efficiency, achieving an average accuracy of 97.26%. These findings underscore RISAR's adaptability and potential as a robust activity recognition solution in real environments.

eess.SY↗

arXiv2024

HateModerate: Testing Hate Speech Detectors against Content Moderation Policies

To protect users from massive hateful content, existing works studied automated hate speech detection. Despite the existing efforts, one question remains: do automated hate speech detectors conform to social media content policies? A platform's content policies are a checklist of content moderated by the social media platform. Because content moderation rules are often uniquely defined, existing hate speech datasets cannot directly answer this question. This work seeks to answer this question by creating HateModerate, a dataset for testing the behaviors of automated content moderators against content policies. First, we engage 28 annotators and GPT in a six-step annotation process, resulting in a list of hateful and non-hateful test suites matching each of Facebook's 41 hate speech policies. Second, we test the performance of state-of-the-art hate speech detectors against HateModerate, revealing substantial failures these models have in their conformity to the policies. Third, using HateModerate, we augment the training data of a top-downloaded hate detector on HuggingFace. We observe significant improvement in the models' conformity to content policies while having comparable scores on the original test data. Our dataset and code can be found in the attachment.

cs.SE↗

arXiv2024

Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields

Generalizable NeRF can directly synthesize novel views across new scenes, eliminating the need for scene-specific retraining in vanilla NeRF. A critical enabling factor in these approaches is the extraction of a generalizable 3D representation by aggregating source-view features. In this paper, we propose an Entangled View-Epipolar Information Aggregation method dubbed EVE-NeRF. Different from existing methods that consider cross-view and along-epipolar information independently, EVE-NeRF conducts the view-epipolar feature aggregation in an entangled manner by injecting the scene-invariant appearance continuity and geometry consistency priors to the aggregation process. Our approach effectively mitigates the potential lack of inherent geometric and appearance constraint resulting from one-dimensional interactions, thus further boosting the 3D representation generalizablity. EVE-NeRF attains state-of-the-art performance across various evaluation scenarios. Extensive experiments demonstate that, compared to prevailing single-dimensional aggregation, the entangled network excels in the accuracy of 3D scene geometry and appearance reconstruction. Our code is publicly available at https://github.com/tatakai1/EVENeRF.

cs.CV↗

arXiv2024

Attacking Transformers with Feature Diversity Adversarial Perturbation

Understanding the mechanisms behind Vision Transformer (ViT), particularly its vulnerability to adversarial perturba tions, is crucial for addressing challenges in its real-world applications. Existing ViT adversarial attackers rely on la bels to calculate the gradient for perturbation, and exhibit low transferability to other structures and tasks. In this paper, we present a label-free white-box attack approach for ViT-based models that exhibits strong transferability to various black box models, including most ViT variants, CNNs, and MLPs, even for models developed for other modalities. Our inspira tion comes from the feature collapse phenomenon in ViTs, where the critical attention mechanism overly depends on the low-frequency component of features, causing the features in middle-to-end layers to become increasingly similar and eventually collapse. We propose the feature diversity attacker to naturally accelerate this process and achieve remarkable performance and transferability.

cs.CR↗

arXiv2024

Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization

Contemporary weakly-supervised object localization (WSOL) methods have primarily focused on addressing the challenge of localizing the most discriminative region while largely overlooking the relatively less explored issue of biased activation -- incorrectly spotlighting co-occurring background with the foreground feature. In this paper, we conduct a thorough causal analysis to investigate the origins of biased activation. Based on our analysis, we attribute this phenomenon to the presence of co-occurring background confounders. Building upon this profound insight, we introduce a pioneering paradigm known as Counterfactual Co-occurring Learning (CCL), meticulously engendering counterfactual representations by adeptly disentangling the foreground from the co-occurring background elements. Furthermore, we propose an innovative network architecture known as Counterfactual-CAM. This architecture seamlessly incorporates a perturbation mechanism for counterfactual representations into the vanilla CAM-based model. By training the WSOL model with these perturbed representations, we guide the model to prioritize the consistent foreground content while concurrently reducing the influence of distracting co-occurring backgrounds. To the best of our knowledge, this study represents the initial exploration of this research direction. Our extensive experiments conducted across multiple benchmarks validate the effectiveness of the proposed Counterfactual-CAM in mitigating biased activation.

cs.CV↗

arXiv2024

Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination

Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However, current cooperative multi-agent reinforcement learning (MARL) methods usually do not explicitly take consensus into consideration, which may cause miscoordination problem. In this paper, we propose a model-based consensus mechanism to explicitly coordinate multiple agents. The proposed Multi-agent Goal Imagination (MAGI) framework guides agents to reach consensus with an Imagined common goal. The common goal is an achievable state with high value, which is obtained by sampling from the distribution of future states. We directly model this distribution with a self-supervised generative model, thus alleviating the "curse of dimensinality" problem induced by multi-agent multi-step policy rollout commonly used in model-based methods. We show that such efficient consensus mechanism can guide all agents cooperatively reaching valuable future states. Results on Multi-agent Particle-Environments and Google Research Football environment demonstrate the superiority of MAGI in both sample efficiency and performance.

cs.AI↗

arXiv2024

DiffusionTrack: Diffusion Model For Multi-Object Tracking

Multi-object tracking (MOT) is a challenging vision task that aims to detect individual objects within a single frame and associate them across multiple frames. Recent MOT approaches can be categorized into two-stage tracking-by-detection (TBD) methods and one-stage joint detection and tracking (JDT) methods. Despite the success of these approaches, they also suffer from common problems, such as harmful global or local inconsistency, poor trade-off between robustness and model complexity, and lack of flexibility in different scenes within the same video. In this paper we propose a simple but robust framework that formulates object detection and association jointly as a consistent denoising diffusion process from paired noise boxes to paired ground-truth boxes. This novel progressive denoising diffusion strategy substantially augments the tracker's effectiveness, enabling it to discriminate between various objects. During the training stage, paired object boxes diffuse from paired ground-truth boxes to random distribution, and the model learns detection and tracking simultaneously by reversing this noising process. In inference, the model refines a set of paired randomly generated boxes to the detection and tracking results in a flexible one-step or multi-step denoising diffusion process. Extensive experiments on three widely used MOT benchmarks, including MOT17, MOT20, and Dancetrack, demonstrate that our approach achieves competitive performance compared to the current state-of-the-art methods.

cs.CV↗