arXiv subjects

Jia Liu

Publications and source records attributed to Jia Liu.

At least 163 records · Page 9Linked to original sources

arXiv2024

FaGeL: Fabric LLMs Agent empowered Embodied Intelligence Evolution with Autonomous Human-Machine Collaboration

Recent advancements in Large Language Models (LLMs) have enhanced the reasoning capabilities of embodied agents, driving progress toward AGI-powered robotics. While LLMs have been applied to tasks like semantic reasoning and task generalization, their potential in open physical space exploration remains underexplored. This paper introduces FaGeL (Fabric aGent empowered by embodied intelligence with LLMs), an embodied agent integrating smart fabric technology for seamless, non-intrusive human-agent interaction. FaGeL autonomously generates tasks using multimodal data from wearable and ambient sensors, refining its behavior based on implicit human feedback in generated text, without explicit ratings or preferences. We also introduce a token-level saliency map to visualize LLM fine-tuning, enhancing the interpretability of token-level alignment. The system leverages dual feedback mechanisms to improve token-level alignment and addresses challenges in non-intrusive human-machine interaction and cognition evolution. Our contributions include FaGeL's development, the DualCUT algorithm for AI alignment, and experimental validation in cooperative tasks, demonstrating FaGeL's ability to adapt and evolve autonomously through implicit feedback. In the future, we plan to explore FaGeL's scalability in dynamic environments and its integration with other AI systems to develop AGI agents that adapt seamlessly to diverse human needs.

cs.HC↗

arXiv2024

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the learned reward via offline RL. However, accurately modeling step-wise rewards from trajectory-level preference feedback presents inherent challenges. The reward bias introduced, particularly the overestimation of predicted rewards, leads to optimistic trajectory stitching, which undermines the pessimism mechanism critical to the offline RL phase. To address this challenge, we propose In-Dataset Trajectory Return Regularization (DTR) for offline PbRL, which leverages conditional sequence modeling to mitigate the risk of learning inaccurate trajectory stitching under reward bias. Specifically, DTR employs Decision Transformer and TD-Learning to strike a balance between maintaining fidelity to the behavior policy with high in-dataset trajectory returns and selecting optimal actions based on high reward labels. Additionally, we introduce an ensemble normalization technique that effectively integrates multiple reward models, balancing the tradeoff between reward differentiation and accuracy. Empirical evaluations on various benchmarks demonstrate the superiority of DTR over other state-of-the-art baselines.

cs.AI↗

arXiv2024

Learning complexity of gradient descent and conjugate gradient algorithms

Gradient Descent (GD) and Conjugate Gradient (CG) methods are among the most effective iterative algorithms for solving unconstrained optimization problems, particularly in machine learning and statistical modeling, where they are employed to minimize cost functions. In these algorithms, tunable parameters, such as step sizes or conjugate parameters, play a crucial role in determining key performance metrics, like runtime and solution quality. In this work, we introduce a framework that models algorithm selection as a statistical learning problem, and thus learning complexity can be estimated by the pseudo-dimension of the algorithm group. We first propose a new cost measure for unconstrained optimization algorithms, inspired by the concept of primal-dual integral in mixed-integer linear programming. Based on the new cost measure, we derive an improved upper bound for the pseudo-dimension of gradient descent algorithm group by discretizing the set of step size configurations. Moreover, we generalize our findings from gradient descent algorithm to the conjugate gradient algorithm group for the first time, and prove the existence a learning algorithm capable of probabilistically identifying the optimal algorithm with a sufficiently large sample size.

math.OC↗

arXiv2024

PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimization

Multi-objective optimization (MOO) lies at the core of many machine learning (ML) applications that involve multiple, potentially conflicting objectives (e.g., multi-task learning, multi-objective reinforcement learning, among many others). Despite the long history of MOO, recent years have witnessed a surge in interest within the ML community in the development of gradient manipulation algorithms for MOO, thanks to the availability of gradient information in many ML problems. However, existing gradient manipulation methods for MOO often suffer from long training times, primarily due to the need for computing dynamic weights by solving an additional optimization problem to determine a common descent direction that can decrease all objectives simultaneously. To address this challenge, we propose a new and efficient algorithm called Periodic Stochastic Multi-Gradient Descent (PSMGD) to accelerate MOO. PSMGD is motivated by the key observation that dynamic weights across objectives exhibit small changes under minor updates over short intervals during the optimization process. Consequently, our PSMGD algorithm is designed to periodically compute these dynamic weights and utilizes them repeatedly, thereby effectively reducing the computational overload. Theoretically, we prove that PSMGD can achieve state-of-the-art convergence rates for strongly-convex, general convex, and non-convex functions. Additionally, we introduce a new computational complexity measure, termed backpropagation complexity, and demonstrate that PSMGD could achieve an objective-independent backpropagation complexity. Through extensive experiments, we verify that PSMGD can provide comparable or superior performance to state-of-the-art MOO algorithms while significantly reducing training time.

cs.LG↗

arXiv2024

Prolonging Carrier Lifetime in P-type 4H-SiC Epilayer by Thermal Oxidation and Hydrogen Annealing

A minority carrier lifetime of 25.46 $μ$s in a P-type 4H-SiC epilayer has been attained through sequential thermal oxidation and hydrogen annealing. Thermal oxidation can enhance the minority carrier lifetime in the 4H-SiC epilayer by reducing carbon vacancies. However, this process also generates carbon clusters with limited diffusivity and contributes to the enlargement of surface pits on the 4H-SiC. High-temperature hydrogen annealing effectively reduces stacking fault and dislocation density. Moreover, electron spin resonance analysis indicates a significant reduction in carbon vacancy defects after hydrogen annealing. The mechanisms of the elimination of carbon vacancies by hydrogen annealing include the decomposition of carbon clusters formed during thermal oxidation and the low-pressure selective etching by hydrogen, which increases the carbon content on the 4H-SiC surface and facilitates carbon diffusion. Consequently, the combination of thermal oxidation and hydrogen annealing eliminates carbon vacancies more effectively, substantially enhancing the minority carrier lifetime in P-type 4H-SiC. This improvement is advantageous for the application of high-voltage SiC bipolar devices.

cond-mat.mtrl-sci↗

arXiv2024

Redefining Crowdsourced Test Report Prioritization: An Innovative Approach with Large Language Model

Context: Crowdsourced testing has gained popularity in software testing, especially for mobile app testing, due to its ability to bring diversity and tackle fragmentation issues. However, the openness of crowdsourced testing presents challenges, particularly in the manual review of numerous test reports, which is time-consuming and labor-intensive. Objective: The primary goal of this research is to improve the efficiency of review processes in crowdsourced testing. Traditional approaches to test report prioritization lack a deep understanding of semantic information in textual descriptions of these reports. This paper introduces LLMPrior, a novel approach for prioritizing crowdsourced test reports using large language models (LLMs). Method: LLMPrior leverages LLMs for the analysis and clustering of crowdsourced test reports based on the types of bugs revealed in their textual descriptions. This involves using prompt engineering techniques to enhance the performance of LLMs. Following the clustering, a recurrent selection algorithm is applied to prioritize the reports. Results: Empirical experiments are conducted to evaluate the effectiveness of LLMPrior. The findings indicate that LLMPrior not only surpasses current state-of-the-art approaches in terms of performance but also proves to be more feasible, efficient, and reliable. This success is attributed to the use of prompt engineering techniques and the cluster-based prioritization strategy. Conclusion: LLMPrior represents a significant advancement in crowdsourced test report prioritization. By effectively utilizing large language models and a cluster-based strategy, it addresses the challenges in traditional prioritization approaches, offering a more efficient and reliable solution for app developers dealing with crowdsourced test reports.

cs.SE↗

arXiv2024

Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Training

One-shot voice conversion(VC) aims to change the timbre of any source speech to match that of the target speaker with only one speech sample. Existing style transfer-based VC methods relied on speech representation disentanglement and suffered from accurately and independently encoding each speech component and recomposing back to converted speech effectively. To tackle this, we proposed Pureformer-VC, which utilizes Conformer blocks to build a disentangled encoder, and Zipformer blocks to build a style transfer decoder as the generator. In the decoder, we used effective styleformer blocks to integrate speaker characteristics effectively into the generated speech. The models used the generative VAE loss for encoding components and triplet loss for unsupervised discriminative training. We applied the styleformer method to Zipformer's shared weights for style transfer. The experimental results show that the proposed model achieves comparable subjective scores and exhibits improvements in objective metrics compared to existing methods in a one-shot voice conversion scenario.

cs.SD↗

arXiv2024

Particle Conversions Beyond the WKB Approximation and Solar-Induced Gravitational Waves from Dark Photon Dark Matter

We investigate the conversion of kinetic mixing dark photon dark matter into gravitational waves within the magnetic field of the Sun. Our study reveals that the WKB approximation is invalid in this scenario. We derive an analytic solution for the conversion probability with unitary evolution feature. This solution aligns in form with previous studies on photon-gravitational wave conversion. Interestingly, it is applicable in situations where the WKB approximation fails. We extend the unitary evolution solution to other conversion processes, such as axion-photon and dark photon-photon conversions. When the WKB approximation conditions are met, this solution reduces to the WKB result. We compute the characteristic strain of gravitational waves resulting from dark photon conversion in the solar magnetic field, spanning frequencies from $10^{-5}$ Hz to $10^6$ Hz. Our findings indicate that the characteristic strain derived from the unitary evolution solution differs significantly from that of the WKB solution. The resulting strain signal is far below the sensitivity of current gravitational wave interferometers. Nevertheless, we have proposed an exotic gravitational wave source, which could be useful in non-minimal dark sector models.

hep-ph↗

arXiv2024

DFT: A Dual-branch Framework of Fluctuation and Trend for Stock Price Prediction

Stock price prediction is of significant importance in quantitative investment. Existing approaches encounter two primary issues: First, they often overlook the crucial role of capturing short-term stock fluctuations for predicting high-volatility returns. Second, mainstream methods, relying on graphs or attention mechanisms, inadequately explore the temporal relationships among stocks, often blurring distinctions in their characteristics over time and the causal relationships before and after. However, the high volatility of stocks and the intricate market correlations are crucial to accurately predicting stock prices. To address these challenges, we propose a Dual-branch Framework of Fluctuation and Trend (DFT), which decomposes stocks into trend and fluctuation components. By employing a carefully design decomposition module, DFT effectively extracts short-term fluctuations and trend information from stocks while explicitly modeling temporal variations and causal correlations. Our extensive experiments demonstrate that DFT outperforms existing methods across multiple metrics, including a 300% improvement in ranking metrics and a 400% improvement in portfolio-based indicators. Through detailed experiments, we provide valuable insights into different roles of trends and fluctuations in stock price prediction.

cs.CE↗

arXiv2024

Pro-PRIME: A general Temperature-Guided Language model to engineer enhanced Stability and Activity in Proteins

Designing protein mutants of both high stability and activity is a critical yet challenging task in protein engineering. Here, we introduce PRIME, a deep learning model, which can suggest protein mutants of improved stability and activity without any prior experimental mutagenesis data of the specified protein. Leveraging temperature-aware language modeling, PRIME demonstrated superior predictive power compared to current state-of-the-art models on the public mutagenesis dataset over 283 protein assays. Furthermore, we validated PRIME's predictions on five proteins, examining the top 30-45 single-site mutations' impact on various protein properties, including thermal stability, antigen-antibody binding affinity, and the ability to polymerize non-natural nucleic acid or resilience to extreme alkaline conditions. Remarkably, over 30% of the AI-recommended mutants exhibited superior performance compared to their pre-mutation counterparts across all proteins and desired properties. Moreover, we have developed an efficient, and successful method based on PRIME to rapidly obtain multi-site mutants with enhanced activity and stability. Hence, PRIME demonstrates the general applicability in protein engineering.

q-bio.BM↗

arXiv2024

Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning

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

cs.SD↗

arXiv2024

Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition

Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the model training and private data provider are always separated, some security threats that make deep neural networks (DNNs) abnormal deserve to be researched. In recent years, the typical backdoor attacks have been researched in speech recognition systems. The existing backdoor methods are based on data poisoning. The attacker adds some incorporated changes to benign speech spectrograms or changes the speech components, such as pitch and timbre. As a result, the poisoned data can be detected by human hearing or automatic deep algorithms. To improve the stealthiness of data poisoning, we propose a non-neural and fast algorithm called Random Spectrogram Rhythm Transformation (RSRT) in this paper. The algorithm combines four steps to generate stealthy poisoned utterances. From the perspective of rhythm component transformation, our proposed trigger stretches or squeezes the mel spectrograms and recovers them back to signals. The operation keeps timbre and content unchanged for good stealthiness. Our experiments are conducted on two kinds of speech recognition tasks, including testing the stealthiness of poisoned samples by speaker verification and automatic speech recognition. The results show that our method has excellent effectiveness and stealthiness. The rhythm trigger needs a low poisoning rate and gets a very high attack success rate.

cs.SD↗

arXiv2024

Revisiting for maximal flavor violating $Z^{'}_{eμ}$ and its phenomenology constraints

Lepton flavor violation (LFV), observed conclusively in neutrino oscillations, remains a pivotal area of investigation due to its absence in the Standard Model (SM). Beyond the Standard Model (BSM) physics explores charged lepton flavor violation (CLFV), particularly through new particle candidates such as the $Z'$. This article focuses on maximal LFV interactions facilitated by the $Z'$ boson, specifically targeting its off-diagonal interactions with the first and second generations of charged and neutral leptons. In our ultraviolet (UV) model for the origin of the $Z'$, inspired by the work of [R.Foot \textit{et al.,}, Phys.Rev. D50 (1994) 4571-4580], we utilize the discrete $Z_2$ symmetry to investigate the maximal LFV mediated by the $Z'$ between the muon ($μ$) and electron ($e$) arising from the additional scalars. This symmetry prohibits flavor-conserving interactions between $Z'$ and $μ^+μ^-,\, e^+e^-$. In conjunction with collider, $(g-2)_μ, (g-2)_e$, inverse $μ$ decay, Muonium-to-Antimuonium conversion and LFV decay constraints, we provide forecasts for anticipated limits derived from processes such as $ν_μN \to ν_e μ^+ e^- N$ in neutrino trident experiments like the DUNE search at the first time. These limits highlight the prospective scope and significance of LFV investigations within these experimental frameworks. Within the mass range of 0.01 GeV to 10 GeV, the most stringent limit arises from $\it{B} (μ\to e + X + γ)$ when $M_{Z'} < m_μ$, while $Δa_e$ provides effective constraints as $M_{Z'}$ approaches 10 GeV. Looking ahead, the proposed Muonium-to-Antimuonium Conversion Experiment (MACE) is expected to impose the most stringent constraints on Muonium-to-Antimuonium oscillation, improving sensitivity by about one order of magnitude against $Δa_e$.

hep-ph↗

arXiv2024

A Robo-Advisor System: expected utility modeling via pairwise comparisons

We introduce a robo-advisor system that recommends customized investment portfolios to users using an expected utility model elicited from pairwise comparison questionnaires. The robo-advisor system comprises three fundamental components. First, we employ a static preference questionnaire approach to generate questionnaires consisting of pairwise item comparisons. Next, we design three optimization-based preference elicitation approaches to estimate the nominal utility function pessimistically, optimistically, and neutrally. Finally, we compute portfolios based on the nominal utility using an expected utility maximization optimization model. We conduct a series of numerical tests on a simulated user and a number of human users to evaluate the efficiency of the proposed model.

math.OC↗

arXiv2024

StegaINR4MIH: steganography by implicit neural representation for multi-image hiding

Multi-image hiding, which embeds multiple secret images into a cover image and is able to recover these images with high quality, has gradually become a research hotspot in the field of image steganography. However, due to the need to embed a large amount of data in a limited cover image space, issues such as contour shadowing or color distortion often arise, posing significant challenges for multi-image hiding. In this paper, we propose StegaINR4MIH, a novel implicit neural representation steganography framework that enables the hiding of multiple images within a single implicit representation function. In contrast to traditional methods that use multiple encoders to achieve multi-image embedding, our approach leverages the redundancy of implicit representation function parameters and employs magnitude-based weight selection and secret weight substitution on pre-trained cover image functions to effectively hide and independently extract multiple secret images. We conduct experiments on images with a resolution of from three different datasets: CelebA-HQ, COCO, and DIV2K. When hiding two secret images, the PSNR values of both the secret images and the stego images exceed 42. When hiding five secret images, the PSNR values of both the secret images and the stego images exceed 39. Extensive experiments demonstrate the superior performance of the proposed method in terms of visual quality and undetectability.

cs.CV↗

arXiv2024

Significance of void shape: Neutrino mass from Voronoi void halos?

Massive neutrinos suppress the growth of cosmic structure on nonlinear scales, motivating the use of information beyond the power spectrum to tighten constraints on the neutrino mass, for example by considering cosmic voids. It was recently proposed that constraints on neutrino mass from the halo mass function (HMF) can be improved by considering only the halos that reside within voids -- the void-halo mass function (VHMF). We extend this analysis, which made spherical assumptions about the shape of voids, to take into account the non-spherical nature of voids as defined by the Voronoi-tessellation-based void finder, VIDE. In turn, after accounting for one spurious non-spherical void, we find no evidence that the VHMF contains information beyond the HMF. Given this finding, we then introduce a novel summary statistic by splitting halos according to the emptiness of their individual environments, defined by the Voronoi cell volume each halo resides in, and combining the mass functions from each split. We name the corresponding statistic the VorHMF and find that it could provide information regarding neutrino mass beyond the HMF. Our work thus motivates the importance of accounting for the full shape of voids in future analyses, both in terms of removing outliers to achieve robust results and as an additional source of cosmological information.

astro-ph.CO↗

arXiv2024

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering

Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries. While iterative retrieval methods improve performance by gathering additional information, current approaches often rely on multiple calls of large language models (LLMs). In this paper, we introduce EfficientRAG, an efficient retriever for multi-hop question answering. EfficientRAG iteratively generates new queries without the need for LLM calls at each iteration and filters out irrelevant information. Experimental results demonstrate that EfficientRAG surpasses existing RAG methods on three open-domain multi-hop question-answering datasets.

cs.CL↗

arXiv2024

AToM-Bot: Embodied Fulfillment of Unspoken Human Needs with Affective Theory of Mind

We propose AToM-Bot, a novel task generation and execution framework for proactive robot-human interaction, which leverages the human mental and physical state inference capabilities of the Vision Language Model (VLM) prompted by the Affective Theory of Mind (AToM). Without requiring explicit commands by humans, AToM-Bot proactively generates and follows feasible tasks to improve general human well-being. When around humans, AToM-Bot first detects current human needs based on inferred human states and observations of the surrounding environment. It then generates tasks to fulfill these needs, taking into account its embodied constraints. We designed 16 daily life scenarios spanning 4 common scenes and tasked the same visual stimulus to 59 human subjects and our robot. We used the similarity between human open-ended answers and robot output, and the human satisfaction scores to metric robot performance. AToM-Bot received high human evaluations in need detection (6.42/7, 91.7%), embodied solution (6.15/7, 87.8%) and task execution (6.17/7, 88.1%). We show that AToM-Bot excels in generating and executing feasible plans to fulfill unspoken human needs. Videos and code are available at https://affective-tom-bot.github.io.

cs.RO↗