arXiv subjects

Hongyu Wang

Publications and source records attributed to Hongyu Wang.

At least 73 records · Page 4Linked to original sources

arXiv2025

GARAD-SLAM: 3D GAussian splatting for Real-time Anti Dynamic SLAM

The 3D Gaussian Splatting (3DGS)-based SLAM system has garnered widespread attention due to its excellent performance in real-time high-fidelity rendering. However, in real-world environments with dynamic objects, existing 3DGS-based SLAM systems often face mapping errors and tracking drift issues. To address these problems, we propose GARAD-SLAM, a real-time 3DGS-based SLAM system tailored for dynamic scenes. In terms of tracking, unlike traditional methods, we directly perform dynamic segmentation on Gaussians and map them back to the front-end to obtain dynamic point labels through a Gaussian pyramid network, achieving precise dynamic removal and robust tracking. For mapping, we impose rendering penalties on dynamically labeled Gaussians, which are updated through the network, to avoid irreversible erroneous removal caused by simple pruning. Our results on real-world datasets demonstrate that our method is competitive in tracking compared to baseline methods, generating fewer artifacts and higher-quality reconstructions in rendering.

cs.RO↗

arXiv2025

Bitnet.cpp: Efficient Edge Inference for Ternary LLMs

The advent of 1-bit large language models (LLMs), led by BitNet b1.58, has spurred interest in ternary LLMs. Despite this, research and practical applications focusing on efficient edge inference for ternary LLMs remain scarce. To bridge this gap, we introduce Bitnet.cpp, an inference system optimized for BitNet b1.58 and ternary LLMs. Given that mixed-precision matrix multiplication (mpGEMM) constitutes the bulk of inference time in ternary LLMs, Bitnet.cpp incorporates a novel mpGEMM library to facilitate sub-2-bits-per-weight, efficient and lossless inference. The library features two core solutions: Ternary Lookup Table (TL), which addresses spatial inefficiencies of previous bit-wise methods, and Int2 with a Scale (I2_S), which ensures lossless edge inference, both enabling high-speed inference. Our experiments show that Bitnet.cpp achieves up to a 6.25x increase in speed over full-precision baselines and up to 2.32x over low-bit baselines, setting new benchmarks in the field. Additionally, we expand TL to element-wise lookup table (ELUT) for low-bit LLMs in the appendix, presenting both theoretical and empirical evidence of its considerable potential. Bitnet.cpp is publicly available at https://github.com/microsoft/BitNet/tree/paper , offering a sophisticated solution for the efficient and practical deployment of edge LLMs.

cs.LG↗

arXiv2025

An Experimental Study of Noise Reduction in Wind Turbine Airfoils with Serrated Trailing Edges

This study explores the noise reduction achieved by airfoils with serrated trailing edges in a low turbulence wind tunnel, focusing on acoustic spectral characteristics and wake flow field measurements. We analyze the effects of various factors, including Reynolds number, angle of attack, serration parameters, and model type, on sound power levels and far-field radiation patterns. Our findings reveal that serrated trailing edges significantly reduce blunt vortex shedding noise and laminar separation bubble noise across a broader frequency range, particularly in the mid-to-high frequency range, with reductions delineated by two boundaries. Interestingly, the serration geometry exhibits minimal impact on noise reduction, which varies with the angle of attack and airfoil profile across all tested conditions. Additionally, while serrations effectively lower noise levels, especially at higher frequencies, they do not significantly alter the airfoil's acoustic directivity patterns. Measurements of wake flow velocity spectra demonstrate a clear correlation between reduced wake turbulence and noise reduction, as serrated edges decrease the power spectral density of turbulent velocity fluctuations, effectively disrupting larger vortex structures responsible for noise generation. These valuable insights contribute to understanding the acoustic benefits of serrated trailing edges.

physics.flu-dyn↗

arXiv2025

Detecting and Understanding the Promotion of Illicit Goods and Services on Twitter

In this study, we reveal, for the first time, popular online social networks (especially Twitter) are being extensively abused by miscreants to promote illicit goods and services of diverse categories. This study is made possible by multiple machine learning tools that are designed to detect and analyze Posts of Illicit Promotion (PIPs) as well as revealing their underlying promotion campaigns. Particularly, we observe that PIPs are prevalent on Twitter, along with extensive visibility on other three popular OSNs including YouTube, Facebook, and TikTok. For instance, applying our PIP hunter to the Twitter platform for 6 months has led to the discovery of 12 million distinct PIPs which are widely distributed in 5 major natural languages and 10 illicit categories, e.g., drugs, data leakage, gambling, and weapon sales. Along the discovery of PIPs are 580K Twitter accounts publishing PIPs as well as 37K distinct instant messaging accounts that are embedded in PIPs and serve as next hops of communication with prospective customers. Also, an arms race between Twitter and illicit promotion operators is also observed. Especially, 90% PIPs can survice the first two months since getting published on Twitter, which is likely due to the diverse evasion tactics adopted by miscreants to masquerade PIPs.

cs.CR↗

arXiv2025

CIBPU: A Conflict-Invisible Secure Branch Prediction Unit

Previous schemes for designing secure branch prediction unit (SBPU) based on physical isolation can only offer limited security and significantly affect BPU's prediction capability, leading to prominent performance degradation. Moreover, encryption-based SBPU schemes based on periodic key re-randomization have the risk of being compromised by advanced attack algorithms, and the performance overhead is also considerable. To this end, this paper proposes a conflict-invisible SBPU (CIBPU). CIBPU employs redundant storage design, load-aware indexing, and replacement design, as well as an encryption mechanism without requiring periodic key updates, to prevent attackers' perception of branch conflicts. We provide a thorough security analysis, which shows that CIBPU achieves strong security throughout the BPU's lifecycle. We implement CIBPU in a RISC-V core model in gem5. The experimental results show that CIBPU causes an average performance overhead of only 1.12%-2.20% with acceptable hardware storage overhead, which is the lowest among the state-of-the-art SBPU schemes. CIBPU has also been implemented in the open-source RISC-V core, SonicBOOM, which is then burned onto an FPGA board. The evaluation based on the board shows an average performance degradation of 2.01%, which is approximately consistent with the result obtained in gem5.

cs.CR↗

arXiv2025

Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation

Zero-shot generalization across various robots, tasks and environments remains a significant challenge in robotic manipulation. Policy code generation methods use executable code to connect high-level task descriptions and low-level action sequences, leveraging the generalization capabilities of large language models and atomic skill libraries. In this work, we propose Robotic Programmer (RoboPro), a robotic foundation model, enabling the capability of perceiving visual information and following free-form instructions to perform robotic manipulation with policy code in a zero-shot manner. To address low efficiency and high cost in collecting runtime code data for robotic tasks, we devise Video2Code to synthesize executable code from extensive videos in-the-wild with off-the-shelf vision-language model and code-domain large language model. Extensive experiments show that RoboPro achieves the state-of-the-art zero-shot performance on robotic manipulation in both simulators and real-world environments. Specifically, the zero-shot success rate of RoboPro on RLBench surpasses the state-of-the-art model GPT-4o by 11.6%, which is even comparable to a strong supervised training baseline. Furthermore, RoboPro is robust to variations on API formats and skill sets.

cs.RO↗

arXiv2024

MTS-UNMixers: Multivariate Time Series Forecasting via Channel-Time Dual Unmixing

Multivariate time series data provide a robust framework for future predictions by leveraging information across multiple dimensions, ensuring broad applicability in practical scenarios. However, their high dimensionality and mixing patterns pose significant challenges in establishing an interpretable and explicit mapping between historical and future series, as well as extracting long-range feature dependencies. To address these challenges, we propose a channel-time dual unmixing network for multivariate time series forecasting (named MTS-UNMixer), which decomposes the entire series into critical bases and coefficients across both the time and channel dimensions. This approach establishes a robust sharing mechanism between historical and future series, enabling accurate representation and enhancing physical interpretability. Specifically, MTS-UNMixers represent sequences over time as a mixture of multiple trends and cycles, with the time-correlated representation coefficients shared across both historical and future time periods. In contrast, sequence over channels can be decomposed into multiple tick-wise bases, which characterize the channel correlations and are shared across the whole series. To estimate the shared time-dependent coefficients, a vanilla Mamba network is employed, leveraging its alignment with directional causality. Conversely, a bidirectional Mamba network is utilized to model the shared channel-correlated bases, accommodating noncausal relationships. Experimental results show that MTS-UNMixers significantly outperform existing methods on multiple benchmark datasets. The code is available at https://github.com/ZHU-0108/MTS-UNMixers.

cs.LG↗

arXiv2024

SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM

We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural implicit SLAM systems in high-quality rendering, scene understanding, and object-level geometry. We introduce a unique semantic feature loss that effectively compensates for the shortcomings of traditional depth and color losses in object optimization. Through a semantic-guided keyframe selection strategy, we prevent erroneous reconstructions caused by cumulative errors. Extensive experiments demonstrate that SGS-SLAM delivers state-of-the-art performance in camera pose estimation, map reconstruction, precise semantic segmentation, and object-level geometric accuracy, while ensuring real-time rendering capabilities.

cs.CV↗

arXiv2024

BitNet a4.8: 4-bit Activations for 1-bit LLMs

Recent research on the 1-bit Large Language Models (LLMs), such as BitNet b1.58, presents a promising direction for reducing the inference cost of LLMs while maintaining their performance. In this work, we introduce BitNet a4.8, enabling 4-bit activations for 1-bit LLMs. BitNet a4.8 employs a hybrid quantization and sparsification strategy to mitigate the quantization errors introduced by the outlier channels. Specifically, we utilize 4-bit activations for inputs to the attention and feed-forward network layers, while sparsifying intermediate states followed with 8-bit quantization. Extensive experiments demonstrate that BitNet a4.8 achieves performance comparable to BitNet b1.58 with equivalent training costs, while being faster in inference with enabling 4-bit (INT4/FP4) kernels. Additionally, BitNet a4.8 activates only 55% of parameters and supports 3-bit KV cache, further enhancing the efficiency of large-scale LLM deployment and inference.

cs.CL↗

arXiv2024

1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs

Recent advances in 1-bit Large Language Models (LLMs), such as BitNet and BitNet b1.58, present a promising approach to enhancing the efficiency of LLMs in terms of speed and energy consumption. These developments also enable local LLM deployment across a broad range of devices. In this work, we introduce bitnet.cpp, a tailored software stack designed to unlock the full potential of 1-bit LLMs. Specifically, we develop a set of kernels to support fast and lossless inference of ternary BitNet b1.58 LLMs on CPUs. Extensive experiments demonstrate that bitnet.cpp achieves significant speedups, ranging from 2.37x to 6.17x on x86 CPUs and from 1.37x to 5.07x on ARM CPUs, across various model sizes. The code is available at https://github.com/microsoft/BitNet.

cs.CL↗

arXiv2024

Faber-Krahn type inequality for supertrees

The Faber-Krahn inequality states that the first Dirichlet eigenvalue among all bounded domains is no less than a Euclidean ball with the same volume in $\mathbb{R}^n$ \cite{Chavel FB}. Bıyıkoğlu and Leydold (J. Comb. Theory, Ser. B., 2007) demonstrated that the Faber-Krahn inequality also holds for the class of trees with boundary with the same degree sequence and characterized the unique extremal tree. Bıyıkoğlu and Leydold (2007) also posed a question as follows: Give a characterization of all graphs in a given class $\mathcal{C}$ with the Faber-Krahn property. In this paper, we address this question specifically for $k$-uniform supertrees with boundary. We introduce a spiral-like ordering (SLO-ordering) of vertices for supertrees, an extension of the SLO-ordering for trees initially proposed by Pruss [ Duke Math. J., 1998], and prove that the SLO-supertree has the Faber-Krahn property among all supertrees with a given degree sequence. Furthermore, among degree sequences that have a minimum degree $d$ for interior vertices, the SLO-supertree with degree sequence $(d,\ldots,d, d', 1, \dots, 1)$ possesses the Faber-Krahn property.

math.CO↗

arXiv2024

Real-Time and Accurate: Zero-shot High-Fidelity Singing Voice Conversion with Multi-Condition Flow Synthesis

Singing voice conversion is to convert the source singing voice into the target singing voice except for the content. Currently, flow-based models can complete the task of voice conversion, but they struggle to effectively extract latent variables in the more rhythmically rich and emotionally expressive task of singing voice conversion, while also facing issues with low efficiency in speech processing. In this paper, we propose a high-fidelity flow-based model based on multi-decoupling feature constraints called RASVC, which enhances the capture of vocal details by integrating multiple latent attribute encoders. We also use Multi-stream inverse short-time Fourier transform(MS-iSTFT) to enhance the speed of speech processing by skipping some complicated decoder processing steps. We compare the synthesized singing voice with other models from multiple dimensions, and our proposed model is highly consistent with the current state-of-the-art, with the demo which is available at \url{https://lazycat1119.github.io/RASVC-demo/}.

eess.AS↗

arXiv2024

A New Perspective on Speaker Verification: Joint Modeling with DFSMN and Transformer

Speaker verification is to judge the similarity between two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small intra-speaker distances and large inter-speaker distances. We propose Voice Transformer (VOT), a novel model for speaker verification, which integrates parallel transformers at multiple scales. A deep feedforward sequential memory network (DFSMN) is incorporated into the attention part of these transformers to increase feature granularity. The attentive statistics pooling layer is added to focus on important frames and form utterance-level features. We propose Additive Angular Margin Focal Loss (AAMF) to address the hard samples problem. We evaluate the proposed approach on the VoxCeleb1 and CN-Celeb2 datasets, demonstrating that VOT surpasses most mainstream models. The code is available on GitHub\footnote{\url{https://github.com/luckyerr/Voice-Transformer_Speaker-Verification}}.

eess.AS↗

arXiv2024

Cross Fusion RGB-T Tracking with Bi-directional Adapter

Many state-of-the-art RGB-T trackers have achieved remarkable results through modality fusion. However, these trackers often either overlook temporal information or fail to fully utilize it, resulting in an ineffective balance between multi-modal and temporal information. To address this issue, we propose a novel Cross Fusion RGB-T Tracking architecture (CFBT) that ensures the full participation of multiple modalities in tracking while dynamically fusing temporal information. The effectiveness of CFBT relies on three newly designed cross spatio-temporal information fusion modules: Cross Spatio-Temporal Augmentation Fusion (CSTAF), Cross Spatio-Temporal Complementarity Fusion (CSTCF), and Dual-Stream Spatio-Temporal Adapter (DSTA). CSTAF employs a cross-attention mechanism to enhance the feature representation of the template comprehensively. CSTCF utilizes complementary information between different branches to enhance target features and suppress background features. DSTA adopts the adapter concept to adaptively fuse complementary information from multiple branches within the transformer layer, using the RGB modality as a medium. These ingenious fusions of multiple perspectives introduce only less than 0.3\% of the total modal parameters, but they indeed enable an efficient balance between multi-modal and temporal information. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate that our method achieves new state-of-the-art performance.

cs.CV↗

arXiv2024

Exploring the Impact of Passthrough on VR Exergaming in Public Environments: A Field Study

Sedentary behavior is becoming increasingly prevalent in daily work and study environments. VR exergaming has emerged as a promising solution in these places of work and study. However, private spaces in these environments are not easy, and engaging in VR exergaming in public settings presents its own set of challenges (e.g., safety, social acceptance, isolation, and privacy protection). The recent development of Passthrough functionality in VR headsets allows users to maintain awareness of their surroundings, enhancing safety and convenience. Despite its potential benefits, little is known about how Passthrough could affect user performance and experience and solve the challenges of playing VR exergames in real-world public environments. To our knowledge, this work is the first to conduct a field study in an underground passageway on a university campus to explore the use of Passthrough in a real-world public environment, with a disturbance-free closed room as a baseline. Results indicate that enabling Passthrough in a public environment improves performance without compromising presence. Moreover, Passthrough can increase social acceptance, especially among individuals with higher levels of self-consciousness. These findings highlight Passthrough's potential to encourage VR exergaming adoption in public environments, with promising implications for overall health and well-being.

cs.HC↗

arXiv2024

Enhancement of Co-located Shared VR Experiences: Representing Non-HMD Observers on Both HMD and 2D Screen

Virtual reality (VR) not only allows head-mounted display (HMD) users to immerse themselves in virtual worlds but also to share them with others. When designed correctly, this shared experience can be enjoyable. However, in typical scenarios, HMD users are isolated by their devices, and non-HMD observers lack connection with the virtual world. To address this, our research investigates visually representing observers on both HMD and 2D screens to enhance shared experiences. The study, including five representation conditions, reveals that incorporating observer representation positively impacts both HMD users and observers. For how to design and represent them, our work shows that HMD users prefer methods displaying real-world visuals, while observers exhibit diverse preferences regarding being represented with real or virtual images. We provide design guidelines tailored to both displays, offering valuable insights to enhance co-located shared VR experiences for HMD users and non-HMD observers.

cs.HC↗

arXiv2024

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated

We introduce, Q-Sparse, a simple yet effective approach to training sparsely-activated large language models (LLMs). Q-Sparse enables full sparsity of activations in LLMs which can bring significant efficiency gains in inference. This is achieved by applying top-K sparsification to the activations and the straight-through-estimator to the training. We also introduce Block Q-Sparse for batch training and inference. The key results from this work are, (1) Q-Sparse can achieve results comparable to those of baseline LLMs while being much more efficient at inference time; (2) We present an inference-optimal scaling law for sparsely-activated LLMs; (3) Q-Sparse is effective in different settings, including training-from-scratch, continue-training of off-the-shelf LLMs, and finetuning; (4) Q-Sparse works for both full-precision and 1-bit LLMs (e.g., BitNet b1.58). Particularly, the synergy of BitNet b1.58 and Q-Sparse (can be equipped with MoE) provides the cornerstone and a clear path to revolutionize the efficiency, including cost and energy consumption, of future LLMs.

cs.CL↗

arXiv2024

HTD-Mamba: Efficient Hyperspectral Target Detection with Pyramid State Space Model

Hyperspectral target detection (HTD) identifies objects of interest from complex backgrounds at the pixel level, playing a vital role in Earth observation. However, HTD faces challenges due to limited prior knowledge and spectral variation, leading to underfitting models and unreliable performance. To address these challenges, this paper proposes an efficient self-supervised HTD method with a pyramid state space model (SSM), named HTD-Mamba, which employs spectrally contrastive learning to distinguish between target and background based on the similarity measurement of intrinsic features. Specifically, to obtain sufficient training samples and leverage spatial contextual information, we propose a spatial-encoded spectral augmentation technique that encodes all surrounding pixels within a patch into a transformed view of the center pixel. Additionally, to explore global band correlations, we divide pixels into continuous group-wise spectral embeddings and introduce Mamba to HTD for the first time to model long-range dependencies of the spectral sequence with linear complexity. Furthermore, to alleviate spectral variation and enhance robust representation, we propose a pyramid SSM as a backbone to capture and fuse multiresolution spectral-wise intrinsic features. Extensive experiments conducted on four public datasets demonstrate that the proposed method outperforms state-of-the-art methods in both quantitative and qualitative evaluations. Code is available at \url{https://github.com/shendb2022/HTD-Mamba}.

cs.CV↗