arXiv subjects

Xin Lin

Publications and source records attributed to Xin Lin.

At least 91 records · Page 5Linked to original sources

arXiv2024

DOP: Diagnostic-Oriented Prompting for Large Language Models in Mathematical Correction

Math world problems correction(MWPC) is a novel task dedicated to rectifying reasoning errors in the process of solving mathematical problems. In this paper, leveraging the advancements in large language models (LLMs), we address two key objectives:(1) Distinguishing between mathematical reasoning and error correction; (2) Exploring strategies to enhance the error correction capabilities of LLMs in mathematics to solve MWPC task. We noticed that, in real-time education,assisting students in recognizing their mistakes is more crucial than simply providing correct answers. However, current research tends to prioritize obtaining accurate solutions to math problems rather than correcting potentially incorrect ones. Therefore, we modify the research paradigm, demonstrating that improving mathematical reasoning abilities does not equate to mastery in error correction. Meanwhile, we propose a novel method called diagnostic-oriented promping(DOP) aimed at facilitating LLMs to excel in error correction. In experiments, DOP has shown outstanding performance, highlighting its significant impact. We argue that in mathematical education, the demand for outstanding correctors surpasses that for proficient reasoners. Codes and data are available on https://github.com/ChenhaoEcnuCS/Reason-Correct.

cs.CL↗

arXiv2024

Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience

Large Language Models (LLMs) have exhibited remarkable performance across various downstream tasks, but they may generate inaccurate or false information with a confident tone. One of the possible solutions is to empower the LLM confidence expression capability, in which the confidence expressed can be well-aligned with the true probability of the generated answer being correct. However, leveraging the intrinsic ability of LLMs or the signals from the output logits of answers proves challenging in accurately capturing the response uncertainty in LLMs. Therefore, drawing inspiration from cognitive diagnostics, we propose a method of Learning from Past experience (LePe) to enhance the capability for confidence expression. Specifically, we first identify three key problems: (1) How to capture the inherent confidence of the LLM? (2) How to teach the LLM to express confidence? (3) How to evaluate the confidence expression of the LLM? Then we devise three stages in LePe to deal with these problems. Besides, to accurately capture the confidence of an LLM when constructing the training data, we design a complete pipeline including question preparation and answer sampling. We also conduct experiments using the Llama family of LLMs to verify the effectiveness of our proposed method on four datasets.

cs.CL↗

arXiv2024

Towards a MATLAB Toolbox to compute backstepping kernels using the power series method

In this paper, we extend our previous work on the power series method for computing backstepping kernels. Our first contribution is the development of initial steps towards a MATLAB toolbox dedicated to backstepping kernel computation. This toolbox would exploit MATLAB's linear algebra and sparse matrix manipulation features for enhanced efficiency; our initial findings show considerable improvements in computational speed with respect to the use of symbolical software without loss of precision at high orders. Additionally, we tackle limitations observed in our earlier work, such as slow convergence (due to oscillatory behaviors) and non-converging series (due to loss of analiticity at some singular points). To overcome these challenges, we introduce a technique that mitigates this behaviour by computing the expansion at different points, denoted as localized power series. This approach effectively navigates around singularities, and can also accelerates convergence by using more local approximations. Basic examples are provided to demonstrate these enhancements. Although this research is still ongoing, the significant potential and simplicity of the method already establish the power series approach as a viable and versatile solution for solving backstepping kernel equations, benefiting both novel and experienced practitioners in the field. We anticipate that these developments will be particularly beneficial in training the recently introduced neural operators that approximate backstepping kernels and gains.

eess.SY↗

arXiv2024

Zero-shot Explainable Mental Health Analysis on Social Media by Incorporating Mental Scales

Traditional discriminative approaches in mental health analysis are known for their strong capacity but lack interpretability and demand large-scale annotated data. The generative approaches, such as those based on large language models (LLMs), have the potential to get rid of heavy annotations and provide explanations but their capabilities still fall short compared to discriminative approaches, and their explanations may be unreliable due to the fact that the generation of explanation is a black-box process. Inspired by the psychological assessment practice of using scales to evaluate mental states, our method which is called Mental Analysis by Incorporating Mental Scales (MAIMS), incorporates two procedures via LLMs. First, the patient completes mental scales, and second, the psychologist interprets the collected information from the mental scales and makes informed decisions. Experimental results show that MAIMS outperforms other zero-shot methods. MAIMS can generate more rigorous explanation based on the outputs of mental scales

cs.CL↗

arXiv2024

TINA: Think, Interaction, and Action Framework for Zero-Shot Vision Language Navigation

Zero-shot navigation is a critical challenge in Vision-Language Navigation (VLN) tasks, where the ability to adapt to unfamiliar instructions and to act in unknown environments is essential. Existing supervised learning-based models, trained using annotated data through reinforcement learning, exhibit limitations in generalization capabilities. Large Language Models (LLMs), with their extensive knowledge and emergent reasoning abilities, present a potential pathway for achieving zero-shot navigation. This paper presents a VLN agent based on LLMs, exploring approaches to the zero-shot navigation problem. To compensate for the shortcomings of LLMs in environmental perception, we propose the Thinking, Interacting, and Action (TINA) framework. TINA enables the agent to scrutinize perceptual information and autonomously query key clues within the environment through an introduced question-answering module, thereby aligning instructions with specific perceptual data. The navigation agent's perceptual abilities are enhanced through the TINA framework, while the explicit thought and query processes also improve the navigational procedure's explainability and transparency. We evaluate the performance of our method on the Room-to-Room dataset. The experiment results indicate that our approach improves the navigation performance of LLM-based agents. Our approach also outperformed some supervised learning-based methods, highlighting its efficacy in zero-shot navigation.

cs.CV↗

arXiv2024

A Two-Field-Scan Harmonic Hall Voltage Analysis For Fast, Accurate Quantification Of Spin-Orbit Torques In Magnetic Heterostructures

The efficiencies of the spin-orbit torques (SOTs) play a key role in the determination of the power consumption, integration density, and endurance of SOT-driven devices. Accurate and time-efficient determination of the SOT efficiencies is of great importance not only for evaluating the practical potential of SOT devices but also for developing new mechanisms for enhancing the SOT efficiencies. Here, we develop a "two-field-scan" harmonic Hall voltage (HHV) analysis that collects the second HHV as a function of a swept in-plane magnetic field at 45° and 0° relative to the excitation current. We demonstrate that this two-field-scan analysis is as accurate as the well-established but time-consuming angle-scan HHV analysis even in the presence of considerable thermoelectric effects but takes more than a factor of 7 less measurement time. We also show that the 3-parameter fit of the HHV data from a single field scan at 0°, which is commonly employed in the literature, is not reliable because the employment of too many free parameters in the fitting of the very slowly varying HHV signal allows unrealistic pseudo-solution and thus erroneous conclusion about the SOT efficiencies.

cond-mat.mes-hall↗

arXiv2024

A Knowledge-Injected Curriculum Pretraining Framework for Question Answering

Knowledge-based question answering (KBQA) is a key task in NLP research, and also an approach to access the web data and knowledge, which requires exploiting knowledge graphs (KGs) for reasoning. In the literature, one promising solution for KBQA is to incorporate the pretrained language model (LM) with KGs by generating KG-centered pretraining corpus, which has shown its superiority. However, these methods often depend on specific techniques and resources to work, which may not always be available and restrict its application. Moreover, existing methods focus more on improving language understanding with KGs, while neglect the more important human-like complex reasoning. To this end, in this paper, we propose a general Knowledge-Injected Curriculum Pretraining framework (KICP) to achieve comprehensive KG learning and exploitation for KBQA tasks, which is composed of knowledge injection (KI), knowledge adaptation (KA) and curriculum reasoning (CR). Specifically, the KI module first injects knowledge into the LM by generating KG-centered pretraining corpus, and generalizes the process into three key steps that could work with different implementations for flexible application. Next, the KA module learns knowledge from the generated corpus with LM equipped with an adapter as well as keeps its original natural language understanding ability to reduce the negative impacts of the difference between the generated and natural corpus. Last, to enable the LM with complex reasoning, the CR module follows human reasoning patterns to construct three corpora with increasing difficulties of reasoning, and further trains the LM from easy to hard in a curriculum manner. We provide an implementation of the general framework, and evaluate the proposed KICP on four real-word datasets. The results demonstrate that our framework can achieve higher performances.

cs.CL↗

arXiv2024

BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind

As a foundational component of cognitive intelligence, theory of mind (ToM) can make AI more closely resemble human thought processes, thereby enhancing their interaction and collaboration with human. In particular, it can significantly improve a model's comprehension of videos in complex scenes. However, current video question answer (VideoQA) datasets focus on studying causal reasoning within events few of them genuinely incorporating human ToM. Consequently, there is a lack of development in ToM reasoning tasks within the area of VideoQA. This paper presents BDIQA, the first benchmark to explore the cognitive reasoning capabilities of VideoQA models in the context of ToM. BDIQA is inspired by the cognitive development of children's ToM and addresses the current deficiencies in machine ToM within datasets and tasks. Specifically, it offers tasks at two difficulty levels, assessing Belief, Desire and Intention (BDI) reasoning in both simple and complex scenarios. We conduct evaluations on several mainstream methods of VideoQA and diagnose their capabilities with zero shot, few shot and supervised learning. We find that the performance of pre-trained models on cognitive reasoning tasks remains unsatisfactory. To counter this challenge, we undertake thorough analysis and experimentation, ultimately presenting two guidelines to enhance cognitive reasoning derived from ablation analysis.

cs.MM↗

arXiv2024

TD^2-Net: Toward Denoising and Debiasing for Dynamic Scene Graph Generation

Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might contain occluded and blurred objects. 2) Label bias, primarily due to the high imbalance between a few positive relationship samples and numerous negative ones. Additionally, the distribution of relationships exhibits a long-tailed pattern. To address the above problems, in this paper, we introduce a network named TD$^2$-Net that aims at denoising and debiasing for dynamic SGG. Specifically, we first propose a denoising spatio-temporal transformer module that enhances object representation with robust contextual information. This is achieved by designing a differentiable Top-K object selector that utilizes the gumbel-softmax sampling strategy to select the relevant neighborhood for each object. Second, we introduce an asymmetrical reweighting loss to relieve the issue of label bias. This loss function integrates asymmetry focusing factors and the volume of samples to adjust the weights assigned to individual samples. Systematic experimental results demonstrate the superiority of our proposed TD$^2$-Net over existing state-of-the-art approaches on Action Genome databases. In more detail, TD$^2$-Net outperforms the second-best competitors by 12.7 \% on mean-Recall@10 for predicate classification.

cs.CV↗

arXiv2023

3D Multiple Object Tracking on Autonomous Driving: A Literature Review

3D multi-object tracking (3D MOT) stands as a pivotal domain within autonomous driving, experiencing a surge in scholarly interest and commercial promise over recent years. Despite its paramount significance, 3D MOT confronts a myriad of formidable challenges, encompassing abrupt alterations in object appearances, pervasive occlusion, the presence of diminutive targets, data sparsity, missed detections, and the unpredictable initiation and termination of object motion trajectories. Countless methodologies have emerged to grapple with these issues, yet 3D MOT endures as a formidable problem that warrants further exploration. This paper undertakes a comprehensive examination, assessment, and synthesis of the research landscape in this domain, remaining attuned to the latest developments in 3D MOT while suggesting prospective avenues for future investigation. Our exploration commences with a systematic exposition of key facets of 3D MOT and its associated domains, including problem delineation, classification, methodological approaches, fundamental principles, and empirical investigations. Subsequently, we categorize these methodologies into distinct groups, dissecting each group meticulously with regard to its challenges, underlying rationale, progress, merits, and demerits. Furthermore, we present a concise recapitulation of experimental metrics and offer an overview of prevalent datasets, facilitating a quantitative comparison for a more intuitive assessment. Lastly, our deliberations culminate in a discussion of the prevailing research landscape, highlighting extant challenges and charting possible directions for 3D MOT research. We present a structured and lucid road-map to guide forthcoming endeavors in this field.

cs.CV↗

arXiv2023

Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion

The recent success of text-to-image generation diffusion models has also revolutionized semantic image editing, enabling the manipulation of images based on query/target texts. Despite these advancements, a significant challenge lies in the potential introduction of contextual prior bias in pre-trained models during image editing, e.g., making unexpected modifications to inappropriate regions. To address this issue, we present a novel approach called Dual-Cycle Diffusion, which generates an unbiased mask to guide image editing. The proposed model incorporates a Bias Elimination Cycle that consists of both a forward path and an inverted path, each featuring a Structural Consistency Cycle to ensure the preservation of image content during the editing process. The forward path utilizes the pre-trained model to produce the edited image, while the inverted path converts the result back to the source image. The unbiased mask is generated by comparing differences between the processed source image and the edited image to ensure that both conform to the same distribution. Our experiments demonstrate the effectiveness of the proposed method, as it significantly improves the D-CLIP score from 0.272 to 0.283. The code will be available at https://github.com/JohnDreamer/DualCycleDiffsion.

cs.CV↗

arXiv2023

Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches

Deep learning methods have shown remarkable performance in image denoising, particularly when trained on large-scale paired datasets. However, acquiring such paired datasets for real-world scenarios poses a significant challenge. Although unsupervised approaches based on generative adversarial networks offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers. To address this problem, we propose a SC strategy for multiple denoisers. This strategy can achieve significant performance improvement without increasing the inference complexity of the GAN-based denoising framework. Its basic idea is to iteratively replace the previous less powerful denoiser in the filter-guided noise extraction module with the current powerful denoiser. This process generates better synthetic clean-noisy image pairs, leading to a more powerful denoiser for the next iteration. This baseline ensures the stability and effectiveness of the training network. The experimental results demonstrate the superiority of our method over state-of-the-art unsupervised methods.

eess.IV↗

arXiv2023

Giant coercivity, resistivity upturn, and anomalous Hall effect in ferrimagnetic FeTb

Despite the blooming interest, the transition-metal rare-earth ferrimagnets have not been comprehensively understood in terms of their coercivity and transport properties. Here, we report a systematic study of the magnetic and transport properties of ferrimagnetic FeTb alloy by varying the layer thickness and temperature. The FeTb is tuned from the Tb-dominated regime to the Fe-dominated regime via the layer thickness, without varying the composition. The coercivity closely follows the $1/\cosθ_H$ scaling (where $θ_H$ is the polar angle of the external magnetic field) and increases quasi-exponentially upon cooling (exceeding 90 kOe at low temperatures), revealing that the nature of the coercivity is the thermally-assisted domain wall depinning field. The resistivity exhibits a quasi-linear upturn upon cooling possibly due to thermal vibrations of the structure factor of the amorphous alloy. The existing scaling laws of the anomalous Hall effect in the literature break down for the amorphous FeTb that are either Fe- or Tb-dominated. These findings should advance the understanding of the transition-metal-rare-earth ferrimagnets and the associated ferrimagnetic phenomena in spintronics.

cond-mat.mtrl-sci↗

arXiv2023

Magnetization Switching in van der Waals Systems by Spin-Orbit Torque

Electrical switching of magnetization via spin-orbit torque (SOT) is of great potential in fast, dense, energy-efficient nonvolatile magnetic memory and logic technologies. Recently, enormous efforts have been stimulated to investigate switching of perpendicular magnetization in van der Waals systems that have unique, strong tunability and spin-orbit coupling effect compared to conventional metals. In this review, we first give a brief, generalized introduction to the spin-orbit torque and van der Waals materials. We will then discuss the recent advances in magnetization switching by the spin current generated from van der Waals materials and summary the progress in the switching of Van der Waals magnetization by the spin current.

cond-mat.mtrl-sci↗

arXiv2023

Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense

While having achieved great success in rich real-life applications, deep neural network (DNN) models have long been criticized for their vulnerability to adversarial attacks. Tremendous research efforts have been dedicated to mitigating the threats of adversarial attacks, but the essential trait of adversarial examples is not yet clear, and most existing methods are yet vulnerable to hybrid attacks and suffer from counterattacks. In light of this, in this paper, we first reveal a gradient-based correlation between sensitivity analysis-based DNN interpreters and the generation process of adversarial examples, which indicates the Achilles's heel of adversarial attacks and sheds light on linking together the two long-standing challenges of DNN: fragility and unexplainability. We then propose an interpreter-based ensemble framework called X-Ensemble for robust adversary defense. X-Ensemble adopts a novel detection-rectification process and features in building multiple sub-detectors and a rectifier upon various types of interpretation information toward target classifiers. Moreover, X-Ensemble employs the Random Forests (RF) model to combine sub-detectors into an ensemble detector for adversarial hybrid attacks defense. The non-differentiable property of RF further makes it a precious choice against the counterattack of adversaries. Extensive experiments under various types of state-of-the-art attacks and diverse attack scenarios demonstrate the advantages of X-Ensemble to competitive baseline methods.

cs.LG↗

arXiv2023

A Review on Machine Theory of Mind

Theory of Mind (ToM) is the ability to attribute mental states to others, the basis of human cognition. At present, there has been growing interest in the AI with cognitive abilities, for example in healthcare and the motoring industry. Beliefs, desires, and intentions are the early abilities of infants and the foundation of human cognitive ability, as well as for machine with ToM. In this paper, we review recent progress in machine ToM on beliefs, desires, and intentions. And we shall introduce the experiments, datasets and methods of machine ToM on these three aspects, summarize the development of different tasks and datasets in recent years, and compare well-behaved models in aspects of advantages, limitations and applicable conditions, hoping that this study can guide researchers to quickly keep up with latest trend in this field. Unlike other domains with a specific task and resolution framework, machine ToM lacks a unified instruction and a series of standard evaluation tasks, which make it difficult to formally compare the proposed models. We argue that, one method to address this difficulty is now to present a standard assessment criteria and dataset, better a large-scale dataset covered multiple aspects of ToM.

cs.AI↗

arXiv2023

Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-training

Understanding mathematical questions effectively is a crucial task, which can benefit many applications, such as difficulty estimation. Researchers have drawn much attention to designing pre-training models for question representations due to the scarcity of human annotations (e.g., labeling difficulty). However, unlike general free-format texts (e.g., user comments), mathematical questions are generally designed with explicit purposes and mathematical logic, and usually consist of more complex content, such as formulas, and related mathematical knowledge (e.g., Function). Therefore, the problem of holistically representing mathematical questions remains underexplored. To this end, in this paper, we propose a novel contrastive pre-training approach for mathematical question representations, namely QuesCo, which attempts to bring questions with more similar purposes closer. Specifically, we first design two-level question augmentations, including content-level and structure-level, which generate literally diverse question pairs with similar purposes. Then, to fully exploit hierarchical information of knowledge concepts, we propose a knowledge hierarchy-aware rank strategy (KHAR), which ranks the similarities between questions in a fine-grained manner. Next, we adopt a ranking contrastive learning task to optimize our model based on the augmented and ranked questions. We conduct extensive experiments on two real-world mathematical datasets. The experimental results demonstrate the effectiveness of our model.

cs.CL↗

arXiv2023

On inverted Kloosterman sums over finite fields

The classical $n$-variable Kloosterman sums over finite fields are well understood by Deligne's theorem from complex point of view and by Sperber's theorem from $p$-adic point of view. In this paper, we study the complex and $p$-adic estimates of inverted $n$-variable Kloosterman sums, addressing a question of N. Katz (1995). We shall give two complex estimates. The first one is elementary based on Gauss sums. The second estimate is deeper, depending on the cohomological results of Adolphson-Sperber, Denef-Loeser and Fu for twisted toric exponential sums. This deeper result assumes that the characteristic $p$ does not divide $n+1$. Combining with Dwork's $p$-adic theory, we also determine the exact $p$-adic valuations for zeros and poles of the L-function associated to inverted $n$-variable Kloosterman sums in the case $p \equiv 1 \mod (n+1)$. As we shall see, the inverted $n$-variable Kloosterman sum is more complicated than the classical $n$-variable Kloosterman sum in all aspects in the sense that our understanding is less complete, partly because the Hodge numbers are now mostly $2$ instead of $1$.

math.NT↗