arXiv subjects

Jiahong Chen

Publications and source records attributed to Jiahong Chen.

At least 19 recordsLinked to original sources

arXiv2026

SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models

Vision-Language Models (VLMs) perform well on commonsense reasoning tasks but struggle with visual spatial reasoning. Most existing solutions introduce extra 3D prior inputs or external spatial encoders, which increase complexity and degrade the underlying VLMs' general-purpose capabilities after spatial fine-tuning. To this end, we propose a parameter-efficient \textit{\textbf{Spatio}-vision \textbf{L}anguage \textbf{M}odels (SpatioLM)}, that enhances spatial intelligence without extra 3D prior inputs or third-party spatial encoders. Concretely, we design a plug-and-play and non-invasive spatio-vision module that elicits the spatial knowledge inherent in VLMs. Furthermore, we innovatively leverage pseudo depth and camera information as supervision to guide the model in learning physically coherent representations. Extensive experiments show that SpatioLM achieves significant improvements in diverse tasks, including spatial perception and understanding while effectively limiting the degradation of general capabilities. Notably, the model achieves an impressive score of 71.6 on the VSI-Bench (the first model to surpass 70). In addition, it attains competitive performance when transferred to embodied manipulation tasks. Code is available at \href{https://github.com/xiaomi-research/spatio-lm}{\faGithub~spatio-lm}.

cs.CV↗

arXiv2026

Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimation

Single-reference unseen object 6D pose estimation reduces object onboarding by estimating poses of arbitrary novel objects from only one reference view. Recent correspondence-based pipelines have achieved robust performance with vision foundation model (VFM) features. However, they typically treat these features as intra-view descriptors, leaving dense visual-semantic cues, including appearance, structure, and context, insufficiently exchanged across views before geometric decoding. Consequently, the decoded point features may lack joint semantic and geometric discriminability, making correspondence estimation still difficult in challenging cases. Instead of processing features independently, we build the correspondence pipeline around an early cross-view semantic prior. Specifically, cross-view semantic interaction (CVSI) enables dense query and reference VFM tokens to exchange semantic context and form a cross-view prior. Nevertheless, direct CVSI may disturb the VFM token structure, while the resulting semantic prior still needs 3D representation consistency for rigid correspondence. To make this CVSI prior reliable for 3D correspondence learning, we introduce two complementary training-time constraints: the intra-view structure preservation (IVSP) loss preserves the original intra-view token affinity structure during interaction, while the reference-anchored geometric consistency (RAGC) loss enforces spatial representation consistency of decoded point features. The final pose is recovered from learned correspondences through weighted SVD. We further construct a challenging view-pair protocol from the BOP Challenge datasets YCB-V and TUD-L to evaluate robustness in difficult matching scenarios. Extensive experiments on six benchmarks under different view-pair settings show that our method achieves state-of-the-art performance while maintaining comparable inference speed.

cs.CV↗

arXiv2025

Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation

Recent work on latent diffusion models (LDMs) has focused almost exclusively on generative tasks, leaving their potential for discriminative transfer largely unexplored. We introduce Discriminative Vicinity Diffusion (DVD), a novel LDM-based framework for a more practical variant of source-free domain adaptation (SFDA): the source provider may share not only a pre-trained classifier but also an auxiliary latent diffusion module, trained once on the source data and never exposing raw source samples. DVD encodes each source feature's label information into its latent vicinity by fitting a Gaussian prior over its k-nearest neighbors and training the diffusion network to drift noisy samples back to label-consistent representations. During adaptation, we sample from each target feature's latent vicinity, apply the frozen diffusion module to generate source-like cues, and use a simple InfoNCE loss to align the target encoder to these cues, explicitly transferring decision boundaries without source access. Across standard SFDA benchmarks, DVD outperforms state-of-the-art methods. We further show that the same latent diffusion module enhances the source classifier's accuracy on in-domain data and boosts performance in supervised classification and domain generalization experiments. DVD thus reinterprets LDMs as practical, privacy-preserving bridges for explicit knowledge transfer, addressing a core challenge in source-free domain adaptation that prior methods have yet to solve.

cs.LG↗

arXiv2025

NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies

Vision-language-action (VLA) models have significantly advanced robotic manipulation by integrating vision-language models (VLMs), and action decoders into a unified architecture. However, their deployment on resource-constrained edge devices, such as mobile robots or embedded systems (e.g., Jetson Orin Nano), remains challenging due to high computational demands, especially in real-world scenarios where power, latency, and computational resources are critical. To close this gap, we introduce Nano-scale Vision-Language Action (NanoVLA), a family of lightweight VLA architectures that achieve high performance with minimal resources. Our core innovations include: (1) vision-language decoupling that moves conventional early vision and language inputs fusion in VLM to late stage, achieving better performance while enabling caching and reduce inference overhead and latency; (2) long-short action chunking to ensure smooth, coherent multi-step planning without sacrificing real-time responsiveness; (3) dynamic routing that adaptively assigns lightweight or heavy backbones based on task complexity, further optimizing inference efficiency. Experimental results on several benchmarks, as well as real-world deployments, demonstrate that NanoVLA achieves up to 52x faster inference on edge devices compared to previous state-of-the-art VLA models, with 98% less parameters while maintaining or surpassing their task accuracy and generalization. Ablation studies confirm that our decoupling strategy preserves cross-task transferability, and the routing module enhances cost-performance trade-offs, enabling practical, high-precision robotic manipulation on resource-constrained hardware.

cs.RO↗

arXiv2025

Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI

Hallucination in generative AI is often treated as a technical failure to produce factually correct output. Yet this framing underrepresents the broader significance of hallucinated content in language models, which may appear fluent, persuasive, and contextually appropriate while conveying distortions that escape conventional accuracy checks. This paper critically examines how regulatory and evaluation frameworks have inherited a narrow view of hallucination, one that prioritises surface verifiability over deeper questions of meaning, influence, and impact. We propose a layered approach to understanding hallucination risks, encompassing epistemic instability, user misdirection, and social-scale effects. Drawing on interdisciplinary sources and examining instruments such as the EU AI Act and the GDPR, we show that current governance models struggle to address hallucination when it manifests as ambiguity, bias reinforcement, or normative convergence. Rather than improving factual precision alone, we argue for regulatory responses that account for languages generative nature, the asymmetries between system and user, and the shifting boundaries between information, persuasion, and harm.

cs.CY↗

arXiv2025

DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objects

6D pose estimation of textureless objects is valuable for industrial robotic applications, yet remains challenging due to the frequent loss of depth information. Current multi-view methods either rely on depth data or insufficiently exploit multi-view geometric cues, limiting their performance. In this paper, we propose DKPMV, a pipeline that achieves dense keypoint-level fusion using only multi-view RGB images as input. We design a three-stage progressive pose optimization strategy that leverages dense multi-view keypoint geometry information. To enable effective dense keypoint fusion, we enhance the keypoint network with attentional aggregation and symmetry-aware training, improving prediction accuracy and resolving ambiguities on symmetric objects. Extensive experiments on the ROBI dataset demonstrate that DKPMV outperforms state-of-the-art multi-view RGB approaches and even surpasses the RGB-D methods in the majority of cases. The code will be available soon.

cs.CV↗

arXiv2025

Integrated Data Analysis of Plasma Electron Density Profile Tomography for HL-3 with Gaussian Process Regression

An integrated data analysis model based on Gaussian Process Regression is proposed for plasma electron density profile tomography in the HL-3 tokamak. The model combines line-integral measurements from the far-infrared laser interferometer with point measurements obtained via the frequency-modulated continuous wave reflectometry. By employing Gaussian Process Regression, the model effectively incorporates point measurements into 2D profile reconstructions, while coordinate mapping integrates magnetic equilibrium information. The average relative error of the reconstructed profile obtained by the integrated data analysis model with normalized magnetic flux is as low as 3.60*10^(-4). Additionally, sensitivity tests were conducted on the grid resolution, the standard deviation of diagnostic data, and noise levels, providing a robust foundation for the real application to experimental data.

cs.LG↗

arXiv2024

What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context

Source-free domain adaptation (SFDA) involves adapting a model originally trained using a labeled dataset ({\em source domain}) to perform effectively on an unlabeled dataset ({\em target domain}) without relying on any source data during adaptation. This adaptation is especially crucial when significant disparities in data distributions exist between the two domains and when there are privacy concerns regarding the source model's training data. The absence of access to source data during adaptation makes it challenging to analytically estimate the domain gap. To tackle this issue, various techniques have been proposed, such as unsupervised clustering, contrastive learning, and continual learning. In this paper, we first conduct an extensive theoretical analysis of SFDA based on contrastive learning, primarily because it has demonstrated superior performance compared to other techniques. Motivated by the obtained insights, we then introduce a straightforward yet highly effective latent augmentation method tailored for contrastive SFDA. This augmentation method leverages the dispersion of latent features within the neighborhood of the query sample, guided by the source pre-trained model, to enhance the informativeness of positive keys. Our approach, based on a single InfoNCE-based contrastive loss, outperforms state-of-the-art SFDA methods on widely recognized benchmark datasets.

cs.CV↗

arXiv2024

Contrastive Adversarial Training for Unsupervised Domain Adaptation

Domain adversarial training has shown its effective capability for finding domain invariant feature representations and been successfully adopted for various domain adaptation tasks. However, recent advances of large models (e.g., vision transformers) and emerging of complex adaptation scenarios (e.g., DomainNet) make adversarial training being easily biased towards source domain and hardly adapted to target domain. The reason is twofold: relying on large amount of labelled data from source domain for large model training and lacking of labelled data from target domain for fine-tuning. Existing approaches widely focused on either enhancing discriminator or improving the training stability for the backbone networks. Due to unbalanced competition between the feature extractor and the discriminator during the adversarial training, existing solutions fail to function well on complex datasets. To address this issue, we proposed a novel contrastive adversarial training (CAT) approach that leverages the labeled source domain samples to reinforce and regulate the feature generation for target domain. Typically, the regulation forces the target feature distribution being similar to the source feature distribution. CAT addressed three major challenges in adversarial learning: 1) ensure the feature distributions from two domains as indistinguishable as possible for the discriminator, resulting in a more robust domain-invariant feature generation; 2) encourage target samples moving closer to the source in the feature space, reducing the requirement for generalizing classifier trained on the labeled source domain to unlabeled target domain; 3) avoid directly aligning unpaired source and target samples within mini-batch. CAT can be easily plugged into existing models and exhibits significant performance improvements.

cs.LG↗

arXiv2024

From Brussels Effect to Gravity Assists: Understanding the Evolution of the GDPR-Inspired Personal Information Protection Law in China

This paper explores the evolution of China's Personal Information Protection Law (PIPL) and situates it within the context of global data protection development. It draws inspiration from the theory of 'Brussels Effect' and provides a critical account of its application in non-Western jurisdictions, taking China as a prime example. Our objective is not to provide a comparative commentary on China's legal development but to illuminate the intricate dynamics between the Chinese law and the EU's GDPR. We argue that the trajectory of China's Personal Information Protection Law calls into question the applicability of the Brussels Effect: while the GDPR's imprint on the PIPL is evident, a deeper analysis unveils China's nuanced, non-linear adoption that diverges from many assumptions of the Brussels Effect and similar theories. The evolution of the GDPR-inspired PIPL is not as a straightforward outcome of the Brussels Effect but as a nuanced, intricate interplay of external influence and domestic dynamics. We introduce a complementary theory of 'gravity assist', which portrays China's strategic instrumentalisation of the GDPR as a template to shape its unique data protection landscape. Our theoretical framework highlights how China navigates through a patchwork of internal considerations, international standards, and strategic choices, ultimately sculpting a data protection regime that has a similar appearance to the GDPR but aligns with its distinct political, cultural and legal landscape. With a detailed historical and policy analysis of the PIPL, coupled with reasonable speculations on its future avenues, our analysis presents a pragmatic, culturally congruent approach to legal development in China. It signals a trajectory that, while potentially converging at a principled level, is likely to diverge significantly in practice [...]

cs.CY↗

arXiv2024

An Efficient Implicit Neural Representation Image Codec Based on Mixed Autoregressive Model for Low-Complexity Decoding

Displaying high-quality images on edge devices, such as augmented reality devices, is essential for enhancing the user experience. However, these devices often face power consumption and computing resource limitations, making it challenging to apply many deep learning-based image compression algorithms in this field. Implicit Neural Representation (INR) for image compression is an emerging technology that offers two key benefits compared to cutting-edge autoencoder models: low computational complexity and parameter-free decoding. It also outperforms many traditional and early neural compression methods in terms of quality. In this study, we introduce a new Mixed AutoRegressive Model (MARM) to significantly reduce the decoding time for the current INR codec, along with a new synthesis network to enhance reconstruction quality. MARM includes our proposed AutoRegressive Upsampler (ARU) blocks, which are highly computationally efficient, and ARM from previous work to balance decoding time and reconstruction quality. We also propose enhancing ARU's performance using a checkerboard two-stage decoding strategy. Moreover, the ratio of different modules can be adjusted to maintain a balance between quality and speed. Comprehensive experiments demonstrate that our method significantly improves computational efficiency while preserving image quality. With different parameter settings, our method can achieve over a magnitude acceleration in decoding time without industrial level optimization, or achieve state-of-the-art reconstruction quality compared with other INR codecs. To the best of our knowledge, our method is the first INR-based codec comparable with Hyperprior in both decoding speed and quality while maintaining low complexity.

eess.IV↗

arXiv2024

Accuracy of training data and model outputs in Generative AI: CREATe Response to the Information Commissioner Office Consultation

The accuracy of Generative AI is increasingly critical as Large Language Models become more widely adopted. Due to potential flaws in training data and hallucination in outputs, inaccuracy can significantly impact individuals interests by distorting perceptions and leading to decisions based on flawed information. Therefore, ensuring these models accuracy is not only a technical necessity but also a regulatory imperative. ICO call for evidence on the accuracy of Generative AI marks a timely effort in ensuring responsible Generative AI development and use. CREATe, as the Centre for Regulation of the Creative Economy based at the University of Glasgow, has conducted relevant research involving intellectual property, competition, information and technology law. We welcome the ICO call for evidence on the accuracy of Generative AI, and we are happy to highlight aspects of data protection law and AI regulation that we believe should receive attention.

cs.CY↗

arXiv2022

Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation

Recognizing human locomotion intent and activities is important for controlling the wearable robots while walking in complex environments. However, human-robot interface signals are usually user-dependent, which causes that the classifier trained on source subjects performs poorly on new subjects. To address this issue, this paper designs the ensemble diverse hypotheses and knowledge distillation (EDHKD) method to realize unsupervised cross-subject adaptation. EDH mitigates the divergence between labeled data of source subjects and unlabeled data of target subjects to accurately classify the locomotion modes of target subjects without labeling data. Compared to previous domain adaptation methods based on the single learner, which may only learn a subset of features from input signals, EDH can learn diverse features by incorporating multiple diverse feature generators and thus increases the accuracy and decreases the variance of classifying target data, but it sacrifices the efficiency. To solve this problem, EDHKD (student) distills the knowledge from the EDH (teacher) to a single network to remain efficient and accurate. The performance of the EDHKD is theoretically proved and experimentally validated on a 2D moon dataset and two public human locomotion datasets. Experimental results show that the EDHKD outperforms all other methods. The EDHKD can classify target data with 96.9%, 94.4%, and 97.4% average accuracy on the above three datasets with a short computing time (1 ms). Compared to a benchmark (BM) method, the EDHKD increases 1.3% and 7.1% average accuracy for classifying the locomotion modes of target subjects. The EDHKD also stabilizes the learning curves. Therefore, the EDHKD is significant for increasing the generalization ability and efficiency of the human intent prediction and human activity recognition system, which will improve human-robot interactions.

cs.RO↗

arXiv2022

Human-centred home network security

This chapter draws from across the foregoing chapters discussing many core HDI approaches and disciplinary perspectives to consider the specific application of HDI in home network security. While much work has considered the challenges of securing in home IoT devices and their communications, especially for those with limited power or computational capacity, scant attention has been paid by the research community to home network security, and its acceptability and usability, from the viewpoint of ordinary citizens. It will be clear that we need a radical transformation in our approach to designing domestic networking infrastructure to guard against widespread cyber-attacks that threaten to counter the benefits of the IoT. Our aim has to be to defend against enemies inside the walls, to protect critical functionality in the home against rogue devices and prevent the proliferation of disruptive wide-scale IoT DDOS attacks that are already occurring [1].

cs.CR↗

arXiv2022

Preserving Domain Private Representation via Mutual Information Maximization

Recent advances in unsupervised domain adaptation have shown that mitigating the domain divergence by extracting the domain-invariant representation could significantly improve the generalization of a model to an unlabeled data domain. Nevertheless, the existing methods fail to effectively preserve the representation that is private to the label-missing domain, which could adversely affect the generalization. In this paper, we propose an approach to preserve such representation so that the latent distribution of the unlabeled domain could represent both the domain-invariant features and the individual characteristics that are private to the unlabeled domain. In particular, we demonstrate that maximizing the mutual information between the unlabeled domain and its latent space while mitigating the domain divergence can achieve such preservation. We also theoretically and empirically validate that preserving the representation that is private to the unlabeled domain is important and of necessity for the cross-domain generalization. Our approach outperforms state-of-the-art methods on several public datasets.

cs.LG↗

arXiv2022

Data-driven Sensor Deployment for Spatiotemporal Field Reconstruction

This paper concerns the data-driven sensor deployment problem in large spatiotemporal fields. Traditionally, sensor deployment strategies have been heavily dependent on model-based planning approaches. However, model-based approaches do not typically maximize the information gain in the field, which tends to generate less effective sampling locations and lead to high reconstruction error. In the present paper, a data-driven approach is developed to overcome the drawbacks of the model-based approach and improve the spatiotemporal field reconstruction accuracy. The proposed method can select the most informative sampling locations to represent the entire spatiotemporal field. To this end, the proposed method decomposes the spatiotemporal field using principal component analysis (PCA) and finds the top r essential entities of the principal basis. The corresponding sampling locations of the selected entities are regarded as the sensor deployment locations. The observations collected at the selected sensor deployment locations can then be used to reconstruct the spatiotemporal field, accurately. Results are demonstrated using a National Oceanic and Atmospheric Administration sea surface temperature dataset. In the present study, the proposed method achieved the lowest reconstruction error among all methods.

eess.SP↗

arXiv2021

'They're all about pushing the products and shiny things rather than fundamental security' Mapping Socio-technical Challenges in Securing the Smart Home

Insecure connected devices can cause serious threats not just to smart home owners, but also the underlying infrastructural network as well. There has been increasing academic and regulatory interest in addressing cybersecurity risks from both the standpoint of Internet of Things (IoT) vendors and that of end-users. In addition to the current data protection and network security legal frameworks, for example, the UK government has initiated the 'Secure by Design' campaign. While there has been work on how organisations and individuals manage their own cybersecurity risks, it remains unclear to what extent IoT vendors are supporting end-users to perform day-to-day management of such risks in a usable way, and what is stopping the vendors from improving such support. We interviewed 13 experts in the field of IoT and identified three main categories of barriers to making IoT products usably secure: technical, legal and organisational. In this paper we further discuss the policymaking implications of these findings and make some recommendations.

cs.CR↗

arXiv2020

Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment

In this study, we focus on the unsupervised domain adaptation problem where an approximate inference model is to be learned from a labeled data domain and expected to generalize well to an unlabeled data domain. The success of unsupervised domain adaptation largely relies on the cross-domain feature alignment. Previous work has attempted to directly align latent features by the classifier-induced discrepancies. Nevertheless, a common feature space cannot always be learned via this direct feature alignment especially when a large domain gap exists. To solve this problem, we introduce a Gaussian-guided latent alignment approach to align the latent feature distributions of the two domains under the guidance of the prior distribution. In such an indirect way, the distributions over the samples from the two domains will be constructed on a common feature space, i.e., the space of the prior, which promotes better feature alignment. To effectively align the target latent distribution with this prior distribution, we also propose a novel unpaired L1-distance by taking advantage of the formulation of the encoder-decoder. The extensive evaluations on nine benchmark datasets validate the superior knowledge transferability through outperforming state-of-the-art methods and the versatility of the proposed method by improving the existing work significantly.

cs.CV↗