arXiv subjects

Toan Nguyen

Publications and source records attributed to Toan Nguyen.

At least 37 records · Page 2Linked to original sources

arXiv2024

Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models

Recent advancements in large language models (LLMs) have underscored their importance in the evolution of artificial intelligence. However, despite extensive pretraining on multilingual datasets, available open-sourced LLMs exhibit limited effectiveness in processing Vietnamese. The challenge is exacerbated by the absence of systematic benchmark datasets and metrics tailored for Vietnamese LLM evaluation. To mitigate these issues, we have finetuned LLMs specifically for Vietnamese and developed a comprehensive evaluation framework encompassing 10 common tasks and 31 metrics. Our evaluation results reveal that the fine-tuned LLMs exhibit enhanced comprehension and generative capabilities in Vietnamese. Moreover, our analysis indicates that models with more parameters can introduce more biases and uncalibrated outputs and the key factor influencing LLM performance is the quality of the training or fine-tuning datasets. These insights underscore the significance of meticulous fine-tuning with high-quality datasets in enhancing LLM performance.

cs.CL↗

arXiv2023

Domain Generalisation via Risk Distribution Matching

We propose a novel approach for domain generalisation (DG) leveraging risk distributions to characterise domains, thereby achieving domain invariance. In our findings, risk distributions effectively highlight differences between training domains and reveal their inherent complexities. In testing, we may observe similar, or potentially intensifying in magnitude, divergences between risk distributions. Hence, we propose a compelling proposition: Minimising the divergences between risk distributions across training domains leads to robust invariance for DG. The key rationale behind this concept is that a model, trained on domain-invariant or stable features, may consistently produce similar risk distributions across various domains. Building upon this idea, we propose Risk Distribution Matching (RDM). Using the maximum mean discrepancy (MMD) distance, RDM aims to minimise the variance of risk distributions across training domains. However, when the number of domains increases, the direct optimisation of variance leads to linear growth in MMD computations, resulting in inefficiency. Instead, we propose an approximation that requires only one MMD computation, by aligning just two distributions: that of the worst-case domain and the aggregated distribution from all domains. Notably, this method empirically outperforms optimising distributional variance while being computationally more efficient. Unlike conventional DG matching algorithms, RDM stands out for its enhanced efficacy by concentrating on scalar risk distributions, sidestepping the pitfalls of high-dimensional challenges seen in feature or gradient matching. Our extensive experiments on standard benchmark datasets demonstrate that RDM shows superior generalisation capability over state-of-the-art DG methods.

cs.LG↗

arXiv2023

Language-Conditioned Affordance-Pose Detection in 3D Point Clouds

Affordance detection and pose estimation are of great importance in many robotic applications. Their combination helps the robot gain an enhanced manipulation capability, in which the generated pose can facilitate the corresponding affordance task. Previous methods for affodance-pose joint learning are limited to a predefined set of affordances, thus limiting the adaptability of robots in real-world environments. In this paper, we propose a new method for language-conditioned affordance-pose joint learning in 3D point clouds. Given a 3D point cloud object, our method detects the affordance region and generates appropriate 6-DoF poses for any unconstrained affordance label. Our method consists of an open-vocabulary affordance detection branch and a language-guided diffusion model that generates 6-DoF poses based on the affordance text. We also introduce a new high-quality dataset for the task of language-driven affordance-pose joint learning. Intensive experimental results demonstrate that our proposed method works effectively on a wide range of open-vocabulary affordances and outperforms other baselines by a large margin. In addition, we illustrate the usefulness of our method in real-world robotic applications. Our code and dataset are publicly available at https://3DAPNet.github.io

cs.RO↗

arXiv2023

Open-Vocabulary Affordance Detection using Knowledge Distillation and Text-Point Correlation

Affordance detection presents intricate challenges and has a wide range of robotic applications. Previous works have faced limitations such as the complexities of 3D object shapes, the wide range of potential affordances on real-world objects, and the lack of open-vocabulary support for affordance understanding. In this paper, we introduce a new open-vocabulary affordance detection method in 3D point clouds, leveraging knowledge distillation and text-point correlation. Our approach employs pre-trained 3D models through knowledge distillation to enhance feature extraction and semantic understanding in 3D point clouds. We further introduce a new text-point correlation method to learn the semantic links between point cloud features and open-vocabulary labels. The intensive experiments show that our approach outperforms previous works and adapts to new affordance labels and unseen objects. Notably, our method achieves the improvement of 7.96% mIOU score compared to the baselines. Furthermore, it offers real-time inference which is well-suitable for robotic manipulation applications.

cs.RO↗

arXiv2023

Open-Vocabulary Affordance Detection in 3D Point Clouds

Affordance detection is a challenging problem with a wide variety of robotic applications. Traditional affordance detection methods are limited to a predefined set of affordance labels, hence potentially restricting the adaptability of intelligent robots in complex and dynamic environments. In this paper, we present the Open-Vocabulary Affordance Detection (OpenAD) method, which is capable of detecting an unbounded number of affordances in 3D point clouds. By simultaneously learning the affordance text and the point feature, OpenAD successfully exploits the semantic relationships between affordances. Therefore, our proposed method enables zero-shot detection and can be able to detect previously unseen affordances without a single annotation example. Intensive experimental results show that OpenAD works effectively on a wide range of affordance detection setups and outperforms other baselines by a large margin. Additionally, we demonstrate the practicality of the proposed OpenAD in real-world robotic applications with a fast inference speed (~100ms). Our project is available at https://openad2023.github.io.

cs.RO↗

arXiv2023

Causal Inference via Style Transfer for Out-of-distribution Generalisation

Out-of-distribution (OOD) generalisation aims to build a model that can generalise well on an unseen target domain using knowledge from multiple source domains. To this end, the model should seek the causal dependence between inputs and labels, which may be determined by the semantics of inputs and remain invariant across domains. However, statistical or non-causal methods often cannot capture this dependence and perform poorly due to not considering spurious correlations learnt from model training via unobserved confounders. A well-known existing causal inference method like back-door adjustment cannot be applied to remove spurious correlations as it requires the observation of confounders. In this paper, we propose a novel method that effectively deals with hidden confounders by successfully implementing front-door adjustment (FA). FA requires the choice of a mediator, which we regard as the semantic information of images that helps access the causal mechanism without the need for observing confounders. Further, we propose to estimate the combination of the mediator with other observed images in the front-door formula via style transfer algorithms. Our use of style transfer to estimate FA is novel and sensible for OOD generalisation, which we justify by extensive experimental results on widely used benchmark datasets.

cs.CV↗

arXiv2023

Question-Context Alignment and Answer-Context Dependencies for Effective Answer Sentence Selection

Answer sentence selection (AS2) in open-domain question answering finds answer for a question by ranking candidate sentences extracted from web documents. Recent work exploits answer context, i.e., sentences around a candidate, by incorporating them as additional input string to the Transformer models to improve the correctness scoring. In this paper, we propose to improve the candidate scoring by explicitly incorporating the dependencies between question-context and answer-context into the final representation of a candidate. Specifically, we use Optimal Transport to compute the question-based dependencies among sentences in the passage where the answer is extracted from. We then represent these dependencies as edges in a graph and use Graph Convolutional Network to derive the representation of a candidate, a node in the graph. Our proposed model achieves significant improvements on popular AS2 benchmarks, i.e., WikiQA and WDRASS, obtaining new state-of-the-art on all benchmarks.

cs.CL↗

arXiv2022

Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddings

In practice, many medical datasets have an underlying taxonomy defined over the disease label space. However, existing classification algorithms for medical diagnoses often assume semantically independent labels. In this study, we aim to leverage class hierarchy with deep learning algorithms for more accurate and reliable skin lesion recognition. We propose a hyperbolic network to learn image embeddings and class prototypes jointly. The hyperbola provably provides a space for modeling hierarchical relations better than Euclidean geometry. Meanwhile, we restrict the distribution of hyperbolic prototypes with a distance matrix that is encoded from the class hierarchy. Accordingly, the learned prototypes preserve the semantic class relations in the embedding space and we can predict the label of an image by assigning its feature to the nearest hyperbolic class prototype. We use an in-house skin lesion dataset which consists of around 230k dermoscopic images on 65 skin diseases to verify our method. Extensive experiments provide evidence that our model can achieve higher accuracy with less severe classification errors than models without considering class relations.

cs.CV↗

arXiv2019

Neural Machine Translation of Text from Non-Native Speakers

Neural Machine Translation (NMT) systems are known to degrade when confronted with noisy data, especially when the system is trained only on clean data. In this paper, we show that augmenting training data with sentences containing artificially-introduced grammatical errors can make the system more robust to such errors. In combination with an automatic grammar error correction system, we can recover 1.5 BLEU out of 2.4 BLEU lost due to grammatical errors. We also present a set of Spanish translations of the JFLEG grammar error correction corpus, which allows for testing NMT robustness to real grammatical errors.

cs.CL↗

arXiv2018

Kid on The Phone! Toward Automatic Detection of Children on Mobile Devices

Studies have shown that children can be exposed to smart devices at a very early age. This has important implications on research in children-computer interaction, children online safety and early education. Many systems have been built based on such research. In this work, we present multiple techniques to automatically detect the presence of a child on a smart device, which could be used as the first step on such systems. Our methods distinguish children from adults based on behavioral differences while operating a touch-enabled modern computing device. Behavioral differences are extracted from data recorded by the touchscreen and built-in sensors. To evaluate the effectiveness of the proposed methods, a new data set has been created from 50 children and adults who interacted with off-the-shelf applications on smart phones. Results show that it is possible to achieve 99% accuracy and less than 0.5% error rate after 8 consecutive touch gestures using only touch information or 5 seconds of sensor reading. If information is used from multiple sensors, then only after 3 gestures, similar performance could be achieved.

cs.HC↗

arXiv2018

Tap-based User Authentication for Smartwatches

This paper presents TapMeIn, an eyes-free, two-factor authentication method for smartwatches. It allows users to tap a memorable melody (tap-password) of their choice anywhere on the touchscreen to unlock their watch. A user is verified based on the tap-password as well as her physiological and behavioral characteristics when tapping. Results from preliminary experiments with 41 participants show that TapMeIn could achieve an accuracy of 98.7% with a False Positive Rate of only 0.98%. In addition, TapMeIn retains its performance in different conditions such as sitting and walking. In terms of speed, TapMeIn has an average authentication time of 2 seconds. A user study with the System Usability Scale (SUS) tool suggests that TapMeIn has a high usability score.

cs.CR↗

arXiv2018

A Deep Learning Model with Hierarchical LSTMs and Supervised Attention for Anti-Phishing

Anti-phishing aims to detect phishing content/documents in a pool of textual data. This is an important problem in cybersecurity that can help to guard users from fraudulent information. Natural language processing (NLP) offers a natural solution for this problem as it is capable of analyzing the textual content to perform intelligent recognition. In this work, we investigate state-of-the-art techniques for text categorization in NLP to address the problem of anti-phishing for emails (i.e, predicting if an email is phishing or not). These techniques are based on deep learning models that have attracted much attention from the community recently. In particular, we present a framework with hierarchical long short-term memory networks (H-LSTMs) and attention mechanisms to model the emails simultaneously at the word and the sentence level. Our expectation is to produce an effective model for anti-phishing and demonstrate the effectiveness of deep learning for problems in cybersecurity.

cs.CR↗

arXiv2017

IllusionPIN: Shoulder-Surfing Resistant Authentication Using Hybrid Images

We address the problem of shoulder-surfing attacks on authentication schemes by proposing IllusionPIN (IPIN), a PIN-based authentication method that operates on touchscreen devices. IPIN uses the technique of hybrid images to blend two keypads with different digit orderings in such a way, that the user who is close to the device is seeing one keypad to enter her PIN, while the attacker who is looking at the device from a bigger distance is seeing only the other keypad. The user's keypad is shuffled in every authentication attempt since the attacker may memorize the spatial arrangement of the pressed digits. To reason about the security of IllusionPIN, we developed an algorithm which is based on human visual perception and estimates the minimum distance from which an observer is unable to interpret the keypad of the user. We tested our estimations with 84 simulated shoulder-surfing attacks from 21 different people. None of the attacks was successful against our estimations. In addition, we estimated the minimum distance from which a camera is unable to capture the visual information from the keypad of the user. Based on our analysis, it seems practically almost impossible for a surveillance camera to capture the PIN of a smartphone user when IPIN is in use.

cs.CR↗

arXiv2014

Spectral instability of symmetric shear flows in a two-dimensional channel

This paper concerns spectral instability of shear flows in the incompressible Navier-Stokes equations with sufficiently large Reynolds number: $R\to \infty$. It is well-documented in the physical literature, going back to Heisenberg, C.C. Lin, Tollmien, Drazin and Reid, that generic plane shear profiles other than the linear Couette flow are linearly unstable for sufficiently large Reynolds number. In this work, we provide a complete mathematical proof of these physical results. In the case of a symmetric channel flow, our analysis gives exact unstable eigenvalues and eigenfunctions, showing that the solution could grow slowly at the rate of $e^{t/\sqrt {αR}}$, where $α$ is the small spatial frequency that remains between lower and upper marginal stability curves: $α_\mathrm{low}(R) \approx R^{-1/7}$ and $α_\mathrm{up}(R) \approx R^{-1/11}$. We introduce a new, operator-based approach, which avoids to deal with matching inner and outer asymptotic expansions, but instead involves a careful study of singularity in the critical layers by deriving pointwise bounds on the Green function of the corresponding Rayleigh and Airy operators.

math.AP↗

arXiv2011

Stability analysis of collisionless plasmas with specularly reflecting boundary

In this paper we provide sharp criteria for linear stability or instability of equilibria of collisionless plasmas in the presence of boundaries. Specifically, we consider the relativistic Vlasov-Maxwell system with specular reflection at the boundary for the particles and with the perfectly conducting boundary condition for the electromagnetic field. Here we initiate our investigation in the simple geometry of radial and longitudinal symmetry.

math.AP↗

arXiv2011

Multi-dimensional stability of Lax shocks in hyperbolic-elliptic coupled systems

We study nonlinear time-asymptotic stability of small--amplitude planar Lax shocks in a model consisting of a system of multi--dimensional conservation laws coupled with an elliptic system. Such a model can be found in context of dynamics of a gas in presence of radiation. Our main result asserts that the standard uniform Evans stability condition implies nonlinear stability. The main analysis is based on the earlier developments by Zumbrun for multi-dimensional viscous shock waves and by Lattanzio-Mascia-Nguyen-Plaza-Zumbrun for one--dimensional radiative shock profiles.

math.AP↗

arXiv2011

Boundary layers interactions in the plane parallel incompressible flows

We study the inviscid limit problem of the incompressible flows in the presence of both impermeable regular boundaries and a hypersurface transversal to the boundary across which the inviscid flow has a discontinuity jump. In the former case, boundary layers have been introduced by Prandtl as correctors near the boundary between the inviscid and viscous flows. In the latter case, the viscosity smoothes out the discontinuity jump by creating a transition layer which has the same amplitude and thickness as the Prandtl layer. In the neighborhood of the intersection of the impermeable boundary and of the hypersurface, interactions between the boundary and the transition layers must then be considered. In this paper, we initiate a mathematical study of this interaction and carry out a strong convergence in the inviscid limit for the case of the plane parallel flows introduced by Di Perna and Majda in \cite{DM}.

math.AP↗

arXiv2011

Toward nonlinear stability of sources via a modified Burgers equation

Coherent structures are solutions to reaction-diffusion systems that are time-periodic in an appropriate moving frame and spatially asymptotic at $x=\pm\infty$ to spatially periodic travelling waves. This paper is concerned with sources which are coherent structures for which the group velocities in the far field point away from the core. Sources actively select wave numbers and therefore often organize the overall dynamics in a spatially extended system. Determining their nonlinear stability properties is challenging as localized perturbations may lead to a non-localized response even on the linear level due to the outward transport. Using a modified Burgers equation as a model problem that captures some of the essential features of coherent structures, we show how this phenomenon can be analysed and nonlinear stability be established in this simpler context.

math.AP↗