arXiv subjects

He Huang

Publications and source records attributed to He Huang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Evolution of the early universe in Einstein-Cartan theory

Einstein--Cartan theory is a generalization of general relativity that introduces spacetime torsion. In this paper, we perform phase space analysis to investigate the evolution of the early universe in Einstein--Cartan theory. By studying the stability of critical points in the dynamical system, we find that there exist two stable critical points which represent an Einstein static solution and an expanding solution, respectively. After analyzing the phase diagram of the dynamical system, we find that the early universe may exhibit an Einstein static state, an oscillating state, or a bouncing state. By assuming the equation of state $ω$ can decrease over time $t$, the universe can depart from the initial Einstein static state, oscillating state, or bouncing state and then evolve into an inflationary phase. Then, we analyze four different inflationary evolution cases in Einstein--Cartan theory and find that a time-variable equation of state $ω$ cannot yield values of $n_{s}$ and $r$ consistent with observations, while a time-invariant equation of state $ω$ is supported by the Planck 2018 results. Thus, in Einstein--Cartan theory, the universe likely originates from a bouncing state rather than an Einstein static state or an oscillating state.

gr-qc↗

arXiv2025

UFO2: The Desktop AgentOS

Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual prototypes, hindered by shallow OS integration, fragile screenshot-based interaction, and disruptive execution. We present UFO2, a multiagent AgentOS for Windows desktops that elevates CUAs into practical, system-level automation. UFO2 features a centralized HostAgent for task decomposition and coordination, alongside a collection of application-specialized AppAgent equipped with native APIs, domain-specific knowledge, and a unified GUI--API action layer. This architecture enables robust task execution while preserving modularity and extensibility. A hybrid control detection pipeline fuses Windows UI Automation (UIA) with vision-based parsing to support diverse interface styles. Runtime efficiency is further enhanced through speculative multi-action planning, reducing per-step LLM overhead. Finally, a Picture-in-Picture (PiP) interface enables automation within an isolated virtual desktop, allowing agents and users to operate concurrently without interference. We evaluate UFO2 across over 20 real-world Windows applications, demonstrating substantial improvements in robustness and execution accuracy over prior CUAs. Our results show that deep OS integration unlocks a scalable path toward reliable, user-aligned desktop automation.

cs.AI↗

arXiv2025

PA-Boot: A Formally Verified Authentication Protocol for Multiprocessor Secure Boot

Hardware supply-chain attacks are raising significant security threats to the boot process of multiprocessor systems. This paper identifies a new, prevalent hardware supply-chain attack surface that can bypass multiprocessor secure boot due to the absence of processor-authentication mechanisms. To defend against such attacks, we present PA-Boot, the first formally verified processor-authentication protocol for secure boot in multiprocessor systems. PA-Boot is proved functionally correct and is guaranteed to detect multiple adversarial behaviors, e.g., processor replacements, man-in-the-middle attacks, and tampering with certificates. The fine-grained formalization of PA-Boot and its fully mechanized security proofs are carried out in the Isabelle/HOL theorem prover with 306 lemmas/theorems and ~7,100 LoC. Experiments on a proof-of-concept implementation indicate that PA-Boot can effectively identify boot-process attacks with a considerably minor overhead and thereby improve the security of multiprocessor systems.

cs.CR↗

arXiv2025

Degradation Alchemy: Self-Supervised Unknown-to-Known Transformation for Blind Hyperspectral Image Fusion

Hyperspectral image (HSI) fusion is an efficient technique that combines low-resolution HSI (LR-HSI) and high-resolution multispectral images (HR-MSI) to generate high-resolution HSI (HR-HSI). Existing supervised learning methods (SLMs) can yield promising results when test data degradation matches the training ones, but they face challenges in generalizing to unknown degradations. To unleash the potential and generalization ability of SLMs, we propose a novel self-supervised unknown-to-known degradation transformation framework (U2K) for blind HSI fusion, which adaptively transforms unknown degradation into the same type of degradation as those handled by pre-trained SLMs. Specifically, the proposed U2K framework consists of: (1) spatial and spectral Degradation Wrapping (DW) modules that map HR-HSI to unknown degraded HR-MSI and LR-HSI, and (2) Degradation Transformation (DT) modules that convert these wrapped data into predefined degradation patterns. The transformed HR-MSI and LR-HSI pairs are then processed by a pre-trained network to reconstruct the target HR-HSI. We train the U2K framework in a self-supervised manner using consistency loss and greedy alternating optimization, significantly improving the flexibility of blind HSI fusion. Extensive experiments confirm the effectiveness of our proposed U2K framework in boosting the adaptability of five existing SLMs under various degradation settings and surpassing state-of-the-art blind methods.

eess.IV↗

arXiv2025

A Hierarchical Compression Technique for 3D Gaussian Splatting Compression

3D Gaussian Splatting (GS) demonstrates excellent rendering quality and generation speed in novel view synthesis. However, substantial data size poses challenges for storage and transmission, making 3D GS compression an essential technology. Current 3D GS compression research primarily focuses on developing more compact scene representations, such as converting explicit 3D GS data into implicit forms. In contrast, compression of the GS data itself has hardly been explored. To address this gap, we propose a Hierarchical GS Compression (HGSC) technique. Initially, we prune unimportant Gaussians based on importance scores derived from both global and local significance, effectively reducing redundancy while maintaining visual quality. An Octree structure is used to compress 3D positions. Based on the 3D GS Octree, we implement a hierarchical attribute compression strategy by employing a KD-tree to partition the 3D GS into multiple blocks. We apply farthest point sampling to select anchor primitives within each block and others as non-anchor primitives with varying Levels of Details (LoDs). Anchor primitives serve as reference points for predicting non-anchor primitives across different LoDs to reduce spatial redundancy. For anchor primitives, we use the region adaptive hierarchical transform to achieve near-lossless compression of various attributes. For non-anchor primitives, each is predicted based on the k-nearest anchor primitives. To further minimize prediction errors, the reconstructed LoD and anchor primitives are combined to form new anchor primitives to predict the next LoD. Our method notably achieves superior compression quality and a significant data size reduction of over 4.5 times compared to the state-of-the-art compression method on small scenes datasets.

cs.CV↗

arXiv2025

Mobility-Aware Multi-Task Decentralized Federated Learning for Vehicular Networks: Modeling, Analysis, and Optimization

Federated learning (FL) is a promising paradigm that can enable collaborative model training between vehicles while protecting data privacy, thereby significantly improving the performance of intelligent transportation systems (ITSs). In vehicular networks, due to mobility, resource constraints, and the concurrent execution of multiple training tasks, how to allocate limited resources effectively to achieve optimal model training of multiple tasks is an extremely challenging issue. In this paper, we propose a mobility-aware multi-task decentralized federated learning (MMFL) framework for vehicular networks. By this framework, we address task scheduling, subcarrier allocation, and leader selection, as a joint optimization problem, termed as TSLP. For the case with a single FL task, we derive the convergence bound of model training. For general cases, we first model TSLP as a resource allocation game, and prove the existence of a Nash equilibrium (NE). Then, based on this proof, we reformulate the game as a decentralized partially observable Markov decision process (DEC-POMDP), and develop an algorithm based on heterogeneous-agent proximal policy optimization (HAPPO) to solve DEC-POMDP. Finally, numerical results are used to demonstrate the effectiveness of the proposed algorithm.

cs.NI↗

arXiv2025

WECAR: An End-Edge Collaborative Inference and Training Framework for WiFi-Based Continuous Human Activity Recognition

WiFi-based human activity recognition (HAR) holds significant promise for ubiquitous sensing in smart environments. A critical challenge lies in enabling systems to dynamically adapt to evolving scenarios, learning new activities without catastrophic forgetting of prior knowledge, while adhering to the stringent computational constraints of edge devices. Current approaches struggle to reconcile these requirements due to prohibitive storage demands for retaining historical data and inefficient parameter utilization. We propose WECAR, an end-edge collaborative inference and training framework for WiFi-based continuous HAR, which decouples computational workloads to overcome these limitations. In this framework, edge devices handle model training, lightweight optimization, and updates, while end devices perform efficient inference. WECAR introduces two key innovations, i.e., dynamic continual learning with parameter efficiency and hierarchical distillation for end deployment. For the former, we propose a transformer-based architecture enhanced by task-specific dynamic model expansion and stability-aware selective retraining. For the latter, we propose a dual-phase distillation mechanism that includes multi-head self-attention relation distillation and prefix relation distillation. We implement WECAR based on heterogeneous hardware using Jetson Nano as edge devices and the ESP32 as end devices, respectively. Our experiments across three public WiFi datasets reveal that WECAR not only outperforms several state-of-the-art methods in performance and parameter efficiency, but also achieves a substantial reduction in the model's parameter count post-optimization without sacrificing accuracy. This validates its practicality for resource-constrained environments.

cs.LG↗

arXiv2025

Holographic inflation and holographic dark energy from entropy of the anti-de Sitter black hole

Based on the entropy of anti-de Sitter black hole, a new holographic dark energy model has been proposed. When the Hubble horizon and particle horizon are chosen as the IR cutoff, the late-time accelerated expansion of universe is realized. In this paper, we consider the Hubble horizon as the IR cutoff to investigate holographic inflation and slow-roll inflation in this model. We find that slow-roll inflation with the chaotic potential $V_{0}ϕ^{n}$ is favored by Planck results for some special cases, such as $n=1/3$ and $n=1/2$, while holographic inflation is not supported by Planck results. Then, we analyze the reheating temperature and the number of reheating e-folds in this model, and we find that the results favor the cases $n=1/3$ and $n=1/2$. Finally, we use the dynamical analysis method, statefinder diagnostic pairs, and the Hubble diagram to analyze this model. Our results indicate that when $b^{2}$ takes a small value, this model cannot be distinguished from the standard $Λ$CDM model and can serve as an alternative to it.

gr-qc↗

arXiv2025

VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning

Recent studies have augmented large language models (LLMs) with speech capabilities, leading to the development of speech language models (SpeechLMs). Earlier SpeechLMs focused on single-turn speech-based question answering (QA), where user input comprised a speech context and a text question. More recent studies have extended this to multi-turn conversations, though they often require complex, multi-stage supervised fine-tuning (SFT) with diverse data. Another critical challenge with SpeechLMs is catastrophic forgetting, where models optimized for speech tasks suffer significant degradation in text-only performance. To mitigate these issues, we propose a novel single-stage joint speech-text SFT approach on the low-rank adaptation (LoRA) of the LLM backbone. Our joint SFT combines text-only SFT data with three types of speech-related data: speech recognition and translation, speech-based QA, and mixed-modal SFT. Compared to previous SpeechLMs with 7B or 13B parameters, our 3B model demonstrates superior performance across various speech benchmarks while preserving the original capabilities on text-only tasks. Furthermore, our model shows emergent abilities of effectively handling previously unseen prompts and tasks, including multi-turn, mixed-modal inputs.

cs.CL↗

arXiv2025

NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally expensive. In this paper, we propose a simplified and more efficient self-supervised learning framework termed as NeMo Encoder for Speech Tasks (NEST). Specifically, we adopt the FastConformer architecture with 8x sub-sampling rate, which is faster than Transformer or Conformer architectures. Instead of clustering-based quantization, we use fixed random projection for its simplicity and effectiveness. We also implement a generalized noisy speech augmentation that teaches the model to disentangle the main speaker from noise or other speakers. Experiments show that \model improves over existing self-supervised models and achieves new state-of-the-art performance on a variety of speech processing tasks, such as speech recognition/translation, speaker diarization, spoken language understanding, etc. Code and checkpoints are publicly available via NVIDIA NeMo framework.

cs.SD↗

arXiv2024

Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR

Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi-speaker ASR remains a challenging task for these models due to data scarcity and sparsity. In this paper, we present approaches to enable speech foundation models to process and understand multi-speaker speech with limited training data. Specifically, we adapt a speech foundation model for the multi-speaker ASR task using only telephonic data. Remarkably, the adapted model also performs well on meeting data without any fine-tuning, demonstrating the generalization ability of our approach. We conduct several ablation studies to analyze the impact of different parameters and strategies on model performance. Our findings highlight the effectiveness of our methods. Results show that less parameters give better overall cpWER, which, although counter-intuitive, provides insights into adapting speech foundation models for multi-speaker ASR tasks with minimal annotated data.

eess.AS↗

arXiv2024

Inter-Frame Coding for Dynamic Meshes via Coarse-to-Fine Anchor Mesh Generation

In the current Video-based Dynamic Mesh Coding (V-DMC) standard, inter-frame coding is restricted to mesh frames with constant topology. Consequently, temporal redundancy is not fully leveraged, resulting in suboptimal compression efficacy. To address this limitation, this paper introduces a novel coarse-to-fine scheme to generate anchor meshes for frames with time-varying topology. Initially, we generate a coarse anchor mesh using an octree-based nearest neighbor search. Motion estimation compensates for regions with significant motion changes during this process. However, the quality of the coarse mesh is low due to its suboptimal vertices. To enhance details, the fine anchor mesh is further optimized using the Quadric Error Metrics (QEM) algorithm to calculate more precise anchor points. The inter-frame anchor mesh generated herein retains the connectivity of the reference base mesh, while concurrently preserving superior quality. Experimental results show that our method achieves 7.2% ~ 10.3% BD-rate gain compared to the existing V-DMC test model version 7.

cs.MM↗

arXiv2024

AdaPose: Towards Cross-Site Device-Free Human Pose Estimation with Commodity WiFi

WiFi-based pose estimation is a technology with great potential for the development of smart homes and metaverse avatar generation. However, current WiFi-based pose estimation methods are predominantly evaluated under controlled laboratory conditions with sophisticated vision models to acquire accurately labeled data. Furthermore, WiFi CSI is highly sensitive to environmental variables, and direct application of a pre-trained model to a new environment may yield suboptimal results due to domain shift. In this paper, we proposes a domain adaptation algorithm, AdaPose, designed specifically for weakly-supervised WiFi-based pose estimation. The proposed method aims to identify consistent human poses that are highly resistant to environmental dynamics. To achieve this goal, we introduce a Mapping Consistency Loss that aligns the domain discrepancy of source and target domains based on inner consistency between input and output at the mapping level. We conduct extensive experiments on domain adaptation in two different scenes using our self-collected pose estimation dataset containing WiFi CSI frames. The results demonstrate the effectiveness and robustness of AdaPose in eliminating domain shift, thereby facilitating the widespread application of WiFi-based pose estimation in smart cities.

cs.CV↗

arXiv2024

META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR

We propose a novel end-to-end multi-talker automatic speech recognition (ASR) framework that enables both multi-speaker (MS) ASR and target-speaker (TS) ASR. Our proposed model is trained in a fully end-to-end manner, incorporating speaker supervision from a pre-trained speaker diarization module. We introduce an intuitive yet effective method for masking ASR encoder activations using output from the speaker supervision module, a technique we term Meta-Cat (meta-information concatenation), that can be applied to both MS-ASR and TS-ASR. Our results demonstrate that the proposed architecture achieves competitive performance in both MS-ASR and TS-ASR tasks, without the need for traditional methods, such as neural mask estimation or masking at the audio or feature level. Furthermore, we demonstrate a glimpse of a unified dual-task model which can efficiently handle both MS-ASR and TS-ASR tasks. Thus, this work illustrates that a robust end-to-end multi-talker ASR framework can be implemented with a streamlined architecture, obviating the need for the complex speaker filtering mechanisms employed in previous studies.

eess.AS↗

arXiv2024

A Trustworthy AIoT-enabled Localization System via Federated Learning and Blockchain

There is a significant demand for indoor localization technology in smart buildings, and the most promising solution in this field is using RF sensors and fingerprinting-based methods that employ machine learning models trained on crowd-sourced user data gathered from IoT devices. However, this raises security and privacy issues in practice. Some researchers propose to use federated learning to partially overcome privacy problems, but there still remain security concerns, e.g., single-point failure and malicious attacks. In this paper, we propose a framework named DFLoc to achieve precise 3D localization tasks while considering the following two security concerns. Particularly, we design a specialized blockchain to decentralize the framework by distributing the tasks such as model distribution and aggregation which are handled by a central server to all clients in most previous works, to address the issue of the single-point failure for a reliable and accurate indoor localization system. Moreover, we introduce an updated model verification mechanism within the blockchain to alleviate the concern of malicious node attacks. Experimental results substantiate the framework's capacity to deliver accurate 3D location predictions and its superior resistance to the impacts of single-point failure and malicious attacks when compared to conventional centralized federated learning systems.

cs.CR↗

arXiv2024

DCI: An Accurate Quality Assessment Criteria for Protein Complex Structure Models

The structure of proteins is the basis for studying protein function and drug design. The emergence of AlphaFold 2 has greatly promoted the prediction of protein 3D structures, and it is of great significance to give an overall and accurate evaluation of the predicted models, especially the complex models. Among the existing methods for evaluating multimer structures, DockQ is the most commonly used. However, as a more suitable metric for complex docking, DockQ cannot provide a unique and accurate evaluation in the non-docking situation. Therefore, it is necessary to propose an evaluation strategy that can directly evaluate the whole complex without limitation and achieve good results. In this work, we proposed DCI score, a new evaluation strategy for protein complex structure models, which only bases on distance map and CI (contact-interface) map, DCI focuses on the prediction accuracy of the contact interface based on the overall evaluation of complex structure, is not inferior to DockQ in the evaluation accuracy according to CAPRI classification, and is able to handle the non-docking situation better than DockQ. Besides, we calculated DCI score on CASP datasets and compared it with CASP official assessment, which obtained good results. In addition, we found that DCI can better evaluate the overall structure deviation caused by interface prediction errors in the case of multi-chains. Our DCI is available at \url{https://gitee.com/WendaWang/DCI-score.git}, and the online-server is available at \url{http://mialab.ruc.edu.cn/DCIServer/}.

q-bio.BM↗

arXiv2024

Less is More: Accurate Speech Recognition & Translation without Web-Scale Data

Recent advances in speech recognition and translation rely on hundreds of thousands of hours of Internet speech data. We argue that state-of-the art accuracy can be reached without relying on web-scale data. Canary - multilingual ASR and speech translation model, outperforms current state-of-the-art models - Whisper, OWSM, and Seamless-M4T on English, French, Spanish, and German languages, while being trained on an order of magnitude less data than these models. Three key factors enables such data-efficient model: (1) a FastConformer-based attention encoder-decoder architecture (2) training on synthetic data generated with machine translation and (3) advanced training techniques: data-balancing, dynamic data blending, dynamic bucketing and noise-robust fine-tuning. The model, weights, and training code will be open-sourced.

cs.CL↗

arXiv2024

BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5

Incorporating speech understanding capabilities into pretrained large-language models has become a vital research direction (SpeechLLM). The previous architectures can be categorized as: i) GPT-style, prepend speech prompts to the text prompts as a sequence of LLM inputs like a decoder-only model; ii) T5-style, introduce speech cross-attention to each layer of the pretrained LLMs. We propose BESTOW architecture to bring the BESt features from TwO Worlds into a single model that is highly efficient and has strong multitask capabilities. Moreover, there is no clear streaming solution for either style, especially considering the solution should generalize to speech multitask. We reformulate streamable SpeechLLM as a read-write policy problem and unifies the offline and streaming research with BESTOW architecture. Hence we demonstrate the first open-source SpeechLLM solution that enables Streaming and Multitask at scale (beyond ASR) at the same time. This streamable solution achieves very strong performance on a wide range of speech tasks (ASR, AST, SQA, unseen DynamicSuperb). It is end-to-end optimizable, with lower training/inference cost, and demonstrates LLM knowledge transferability to speech.

cs.CL↗