arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 829 records · Page 46Linked to original sources

arXiv2024

Stacking faults enabled second harmonic generation in centrosymmetric van der Waals RhI3

Second harmonic generation (SHG) in van der Waals (vdWs) materials has garnered significant attention due to its potential for integrated nonlinear optical and optoelectronic applications. Stacking faults in vdWs materials, a typical kind of planar defect, can introduce a new degree of freedom to modulate the crystal symmetry and resultant SHG response, however, the physical origin and tunability of stacking-fault-governed SHG in vdWs materials remain unclear. Here, taking the intrinsically centrosymmetric vdWs RhI3 as an example, we theoretically reveal the origin of stacking-fault-governed SHG response, where the SHG response comes from the energetically favorable AC- Cstacking fault of which the electrical transitions along the high symmetry paths Gamma-M and Gamma-K in the Brillion zone play the dominant role at 810 nm. Such stacking-fault-governed SHG response is further confirmed via structural characterizations and SHG measurements. Furthermore, by applying hydrostatic pressure on RhI3, the correlation between structural evolution and SHG response is revealed with SHG enhancement up to 6.9 times, where the decreased electronic transition energies and huger momentum matrix elements due to the stronger interlayer interactions upon compression magnify the SHG susceptibility. This study develops a promising foundation based on strategically designed stacking faults for pioneering new avenues in nonlinear nano-optics.

physics.optics↗

arXiv2024

Cooperative Open-ended Learning Framework for Zero-shot Coordination

Zero-shot coordination in cooperative artificial intelligence (AI) remains a significant challenge, which means effectively coordinating with a wide range of unseen partners. Previous algorithms have attempted to address this challenge by optimizing fixed objectives within a population to improve strategy or behaviour diversity. However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility. To address this issue, we propose the Cooperative Open-ended LEarning (COLE) framework, which constructs open-ended objectives in cooperative games with two players from the perspective of graph theory to assess and identify the cooperative ability of each strategy. We further specify the framework and propose a practical algorithm that leverages knowledge from game theory and graph theory. Furthermore, an analysis of the learning process of the algorithm shows that it can efficiently overcome cooperative incompatibility. The experimental results in the Overcooked game environment demonstrate that our method outperforms current state-of-the-art methods when coordinating with different-level partners. Our demo is available at https://sites.google.com/view/cole-2023.

cs.AI↗

arXiv2024

Rare events in a stochastic vegetation-water dynamical system based on machine learning

Stochastic vegetation-water dynamical systems play a pivotal role in ecological stability, biodiversity, water resource management, and adaptation to climate change. This research proposes a machine learning-based method for analyzing rare events in stochastic vegetation-water dynamical systems with multiplicative Gaussian noise. Utilizing the Freidlin-Wentzell large deviation theory, we derive the asymptotic expressions for the quasipotential and the mean first exit time. Based on the decomposition of vector field, we design a neural network architecture to compute the most probable transition paths and the mean first exit time for both non-characteristic and characteristic boundary scenarios. The results indicate that this method can effectively predict early warnings of vegetation degradation, providing new theoretical foundations and mathematical tools for ecological management and conservation. Moreover, the method offers new possibilities for exploring more complex and higher-dimensional stochastic dynamical systems.

math.DS↗

arXiv2024

HPE Transformer: Learning to Optimize Multi-Group Multicast Beamforming Under Nonconvex QoS Constraints

This paper studies the quality-of-service (QoS) constrained multi-group multicast beamforming design problem, where each multicast group is composed of a number of users requiring the same content. Due to the nonconvex QoS constraints, this problem is nonconvex and NP-hard. While existing optimization-based iterative algorithms can obtain a suboptimal solution, their iterative nature results in large computational complexity and delay. To facilitate real-time implementations, this paper proposes a deep learning-based approach, which consists of a beamforming structure assisted problem transformation and a customized neural network architecture named hierarchical permutation equivariance (HPE) transformer. The proposed HPE transformer is proved to be permutation equivariant with respect to the users within each multicast group, and also permutation equivariant with respect to different multicast groups. Simulation results demonstrate that the proposed HPE transformer outperforms state-of-the-art optimization-based and deep learning-based approaches for multi-group multicast beamforming design in terms of the total transmit power, the constraint violation, and the computational time. In addition, the proposed HPE transformer achieves pretty good generalization performance on different numbers of users, different numbers of multicast groups, and different signal-to-interference-plus-noise ratio targets.

cs.IT↗

arXiv2024

Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions

Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its semantics, syntax, or other attributes. This task is especially challenging given the intrinsic lack of parallel text pairings. Among existing methods for UTST tasks, attention masking approach and Large Language Models (LLMs) are deemed as two pioneering methods. However, they have shortcomings in generating unsmooth sentences and changing the original contents, respectively. In this paper, we investigate if we can combine these two methods effectively. We propose four ways of interactions, that are pipeline framework with tuned orders; knowledge distillation from LLMs to attention masking model; in-context learning with constructed parallel examples. We empirically show these multi-way interactions can improve the baselines in certain perspective of style strength, content preservation and text fluency. Experiments also demonstrate that simply conducting prompting followed by attention masking-based revision can consistently surpass the other systems, including supervised text style transfer systems. On Yelp-clean and Amazon-clean datasets, it improves the previously best mean metric by 0.5 and 3.0 absolute percentages respectively, and achieves new SOTA results.

cs.CL↗

arXiv2024

Continuous-variable quantum key distribution over 28.6 km fiber with an integrated silicon photonic receiver chip

Quantum key distribution, which ensures information-theoretically secret key generation, is currently advancing through photonic integration to achieve high performance, cost reduction and compact size, thereby facilitating the large-scale deployment. Continuous-variable quantum key distribution is an attractive approach for photonic integrations due to its compatibility with off-the-shelf optical communication devices. However, its chip-based systems have encountered significant limitations primarily related to the shot-noise-limited receiver design, which demands low noise, wide bandwidth, high clearance and well stability. Here, we report the implementation of a real local oscillator continuous-variable quantum key distribution system with an integrated silicon photonic receiver chip. Thanks to the well-designed chip-based homodyne detectors with a bandwidth up to 1.5 GHz and a clearance up to 7.42 dB, the transmission distance of the system has been extended to 28.6 km, achieving a secret key generation rate of Mbps level. This technological advancement enables the quantum key distribution systems with photonic integrated receivers to achieve the coverage in both access network scenarios and short-distance metropolitan interconnections, paving the way for the development of the next-generation quantum key distribution networks on a large scale.

quant-ph↗

arXiv2024

FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving

This is the first paper in a series of work we have accomplished over the past three years. In this paper, we have constructed a consistent formal plane geometry system. This will serve as a crucial bridge between IMO-level plane geometry challenges and readable AI automated reasoning. Within this formal framework, we have been able to seamlessly integrate modern AI models with our formal system. AI is now capable of providing deductive reasoning solutions to IMO-level plane geometry problems, just like handling other natural languages, and these proofs are readable, traceable, and verifiable. We propose the geometry formalization theory (GFT) to guide the development of the geometry formal system. Based on the GFT, we have established the FormalGeo, which consists of 88 geometric predicates and 196 theorems. It can represent, validate, and solve IMO-level geometry problems. we also have crafted the FGPS (formal geometry problem solver) in Python. It serves as both an interactive assistant for verifying problem-solving processes and an automated problem solver. We've annotated the formalgeo7k and formalgeo-imo datasets. The former contains 6,981 (expand to 133,818 through data augmentation) geometry problems, while the latter includes 18 (expand to 2,627 and continuously increasing) IMO-level challenging geometry problems. All annotated problems include detailed formal language descriptions and solutions. Implementation of the formal system and experiments validate the correctness and utility of the GFT. The backward depth-first search method only yields a 2.42% problem-solving failure rate, and we can incorporate deep learning techniques to achieve lower one. The source code of FGPS and datasets are available at https://github.com/BitSecret/FGPS.

cs.AI↗

arXiv2024

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data

We introduce a text-to-speech (TTS) model called BASE TTS, which stands for $\textbf{B}$ig $\textbf{A}$daptive $\textbf{S}$treamable TTS with $\textbf{E}$mergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes ("speechcodes") followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are built using a novel speech tokenization technique that features speaker ID disentanglement and compression with byte-pair encoding. Echoing the widely-reported "emergent abilities" of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences. We design and share a specialized dataset to measure these emergent abilities for text-to-speech. We showcase state-of-the-art naturalness of BASE TTS by evaluating against baselines that include publicly available large-scale text-to-speech systems: YourTTS, Bark and TortoiseTTS. Audio samples generated by the model can be heard at https://amazon-ltts-paper.com/.

cs.LG↗

arXiv2024

Instantaneous Quasiphoton in Strong-Field Ionization

Photon is a concept that does not apply at the instantaneous level when light is described by classical electromagnetic fields. Exploiting the dynamical rotational symmetry of circularly or elliptically polarized classical light pulses, however, we demonstrate the existence of instantaneous quasiphotons down to the subcycle level. We illustrate the concept of quasiphotons in strong-field ionization through the correlated spectrum of angular momentum and energy of photoelectrons, both at the tunnel exit and in the asymptotic region. Moreover, we propose a protocol based on electron vortices to directly visualize the existence of quasiphotons. Our work paves the pathway towards a deeper understanding of fundamental light-matter interactions with photonic characteristics on the subcycle scale.

physics.atom-ph↗

arXiv2024

CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification

Recently, prefix-tuning was proposed to efficiently adapt pre-trained language models to a broad spectrum of natural language classification tasks. It leverages soft prefix as task-specific indicators and language verbalizers as categorical-label mentions to narrow the formulation gap from pre-training language models. However, when the label space increases considerably (i.e., many-class classification), such a tuning technique suffers from a verbalizer ambiguity problem since the many-class labels are represented by semantic-similar verbalizers in short language phrases. To overcome this, inspired by the human-decision process that the most ambiguous classes would be mulled over for each instance, we propose a brand-new prefix-tuning method, Counterfactual Contrastive Prefix-tuning (CCPrefix), for many-class classification. Basically, an instance-dependent soft prefix, derived from fact-counterfactual pairs in the label space, is leveraged to complement the language verbalizers in many-class classification. We conduct experiments on many-class benchmark datasets in both the fully supervised setting and the few-shot setting, which indicates that our model outperforms former baselines.

cs.CL↗

arXiv2024

Whittaker categories and the minimal nilpotent finite $W$-algebra for $\mathfrak{sl}_{n+1}$

For any $\mathbf{a}=(a_1,\dots,a_n)\in \mathbb{C}^n$, we introduce a Whittaker category $\mathcal{H}_{\mathbf{a}}$ whose objects are $\mathfrak{sl}_{n+1}$-modules $M$ such that $e_{0i}-a_i$ acts locally nilpotently on $M$ for all $i \in \{1,\dots,n\}$, and the subspace $\mathrm{wh}_{\mathbf{a}}(M)=\{v\in M \mid e_{0i} v=a_iv, \ i=1,\dots,n\}$ is finite dimensional. In this paper, we first give a tensor product decomposition $U_S=W\otimes B$ of the localization $U_S$ of $U(\mathfrak{sl}_{n+1})$ with respect to the Ore subset $S$ generated by $e_{01},\dots, e_{0n}$. We show that the associative algebra $W$ is isomorphic to the type $A_n$ finite $W$-algebra $W(e)$ defined by a minimal nilpotent element $e$ in $\mathfrak{sl}_{n+1}$. Then using $W$-modules as a bridge, we show that each block with a generalized central character of $\mathcal{H}_{\mathbf{1}}$ is equivalent to the corresponding block of the cuspidal category $\mathcal{C}$, which is completely characterized by Grantcharov and Serganova. As a consequence, each regular integral block of $\mathcal{H}_{\mathbf{1}}$ and the category of finite dimensional modules over $W(e) can be described by a well-studied quiver with certain quadratic relations.

math.RT↗

arXiv2024

Quasi van der Waals Epitaxial Growth of GaAsSb Nanowires on Graphitic Substrate for Photonic Applications

III-V semiconductor nanowires are considered promising building blocks for advanced photonic devices. One of the key advantages is that the lattice mismatch can easily be accommodated in 1D structures, resulting in superior heteroepitaxial quality compared to thin films. However, few reports break the limitation of using bulk crystalline materials as substrates for epitaxial growth of high-quality photonic 1D components, making monolithic integration of III-V components on arbitrary substrates challenging. In this work, we show that the growth of self-catalyzed GaAsSb nanowires on graphitic substrates can be promoted by creating step edges of monolayer thickness on kish graphite before the growth. By further alternating the deposition sequence of the group-III element Al and the group-V elements As and Sb, it was found that triangular crystallites form when Al is deposited first. This indicates that the surface binding energy between the graphitic surface and the III-V nucleus profoundly influences the epitaxial growth of III-V materials on graphitic surfaces. Using the optimized growth recipe with an AlAsSb buffer nuclei, vertical [111]-oriented GaAsSb/GaAs nanowires with GaAsSb-based multiple axial superlattices were grown on exfoliated graphite, which was attached to a (001) AlAs/GaAs distributed Bragg reflector (DBR) using the simple Scotch tape method. Fabry-Pérot resonance modes were observed under optical excitation at room temperature, indicating a successful monolithic integration with optical feedback from the DBR system. These results demonstrate the great potential for flexible integration of high-efficiency III-V nanowire photonic devices on arbitrary photonic platforms using a 2D material buffer layer, e.g., graphene, without breaking the orientation registry.

cond-mat.mes-hall↗

arXiv2024

HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline

Industrial SAT formula generation is a critical yet challenging task. Existing SAT generation approaches can hardly simultaneously capture the global structural properties and maintain plausible computational hardness. We first present an in-depth analysis for the limitation of previous learning methods in reproducing the computational hardness of original instances, which may stem from the inherent homogeneity in their adopted split-merge procedure. On top of the observations that industrial formulae exhibit clear community structure and oversplit substructures lead to the difficulty in semantic formation of logical structures, we propose HardSATGEN, which introduces a fine-grained control mechanism to the neural split-merge paradigm for SAT formula generation to better recover the structural and computational properties of the industrial benchmarks. Experiments including evaluations on private and practical corporate testbed show the superiority of HardSATGEN being the only method to successfully augment formulae maintaining similar computational hardness and capturing the global structural properties simultaneously. Compared to the best previous methods, the average performance gains achieve 38.5% in structural statistics, 88.4% in computational metrics, and over 140.7% in the effectiveness of guiding solver tuning by our generated instances. Source code is available at http://github.com/Thinklab-SJTU/HardSATGEN

cs.AI↗

arXiv2024

A new approach to the genus spectra of abelian $p$-groups

Given a finite group $G$, the {\it genus spetrum} ${\rm sp}(G)$ of $G$ is the set of integers $g\geq 0$ such that $G$ can act faithfully on an orientable closed surface of genus $g$ by orientation-preserving homeomorphisms. The determination of ${\rm sp}(G)$ is a classical topic and has a long history, but progress is lacked. In this paper, when $G$ is an abelian $p$-group with $p>2$, we propose a new approach to ${\rm sp}(G)$, giving a structural description for ${\rm sp}(G)$ in terms of a function which can be computed in finitely many steps.

math.GR↗

arXiv2024

An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain

Spiking neural networks (SNNs) are rich in spatio-temporal dynamics and are suitable for processing event-based neuromorphic data. However, event-based datasets are usually less annotated than static datasets. This small data scale makes SNNs prone to overfitting and limits their performance. In order to improve the generalization ability of SNNs on event-based datasets, we use static images to assist SNN training on event data. In this paper, we first discuss the domain mismatch problem encountered when directly transferring networks trained on static datasets to event data. We argue that the inconsistency of feature distributions becomes a major factor hindering the effective transfer of knowledge from static images to event data. To address this problem, we propose solutions in terms of two aspects: feature distribution and training strategy. Firstly, we propose a knowledge transfer loss, which consists of domain alignment loss and spatio-temporal regularization. The domain alignment loss learns domain-invariant spatial features by reducing the marginal distribution distance between the static image and the event data. Spatio-temporal regularization provides dynamically learnable coefficients for domain alignment loss by using the output features of the event data at each time step as a regularization term. In addition, we propose a sliding training strategy, which gradually replaces static image inputs probabilistically with event data, resulting in a smoother and more stable training for the network. We validate our method on neuromorphic datasets, including N-Caltech101, CEP-DVS, and N-Omniglot. The experimental results show that our proposed method achieves better performance on all datasets compared to the current state-of-the-art methods. Code is available at https://github.com/Brain-Cog-Lab/Transfer-for-DVS.

cs.CV↗

arXiv2024

Activity Detection for Massive Connectivity in Cell-free Networks with Unknown Large-scale Fading, Channel Statistics, Noise Variance, and Activity Probability: A Bayesian Approach

Activity detection is an important task in the next generation grant-free multiple access. While there are a number of existing algorithms designed for this purpose, they mostly require precise information about the network, such as large-scale fading coefficients, small-scale fading channel statistics, noise variance at the access points, and user activity probability. Acquiring these information would take a significant overhead and their estimated values might not be accurate. This problem is even more severe in cell-free networks as there are many of these parameters to be acquired. Therefore, this paper sets out to investigate the activity detection problem without the above-mentioned information. In order to handle so many unknown parameters, this paper employs the Bayesian approach, where the unknown variables are endowed with prior distributions which effectively act as regularizations. Together with the likelihood function, a maximum a posteriori (MAP) estimator and a variational inference algorithm are derived. Extensive simulations demonstrate that the proposed methods, even without the knowledge of these system parameters, perform better than existing state-of-the-art methods, such as covariance-based and approximate message passing methods.

cs.LG↗

arXiv2024

Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks

The evolution of the human brain has led to the development of complex synaptic plasticity, enabling dynamic adaptation to a constantly evolving world. This progress inspires our exploration into a new paradigm for Spiking Neural Networks (SNNs): a Plasticity-Driven Learning Framework (PDLF). This paradigm diverges from traditional neural network models that primarily focus on direct training of synaptic weights, leading to static connections that limit adaptability in dynamic environments. Instead, our approach delves into the heart of synaptic behavior, prioritizing the learning of plasticity rules themselves. This shift in focus from weight adjustment to mastering the intricacies of synaptic change offers a more flexible and dynamic pathway for neural networks to evolve and adapt. Our PDLF does not merely adapt existing concepts of functional and Presynaptic-Dependent Plasticity but redefines them, aligning closely with the dynamic and adaptive nature of biological learning. This reorientation enhances key cognitive abilities in artificial intelligence systems, such as working memory and multitasking capabilities, and demonstrates superior adaptability in complex, real-world scenarios. Moreover, our framework sheds light on the intricate relationships between various forms of plasticity and cognitive functions, thereby contributing to a deeper understanding of the brain's learning mechanisms. Integrating this groundbreaking plasticity-centric approach in SNNs marks a significant advancement in the fusion of neuroscience and artificial intelligence. It paves the way for developing AI systems that not only learn but also adapt in an ever-changing world, much like the human brain.

cs.NE↗

arXiv2024

A New Method for Vehicle Logo Recognition Based on Swin Transformer

Intelligent Transportation Systems (ITS) utilize sensors, cameras, and big data analysis to monitor real-time traffic conditions, aiming to improve traffic efficiency and safety. Accurate vehicle recognition is crucial in this process, and Vehicle Logo Recognition (VLR) stands as a key method. VLR enables effective management and monitoring by distinguishing vehicles on the road. Convolutional Neural Networks (CNNs) have made impressive strides in VLR research. However, achieving higher performance demands significant time and computational resources for training. Recently, the rise of Transformer models has brought new opportunities to VLR. Swin Transformer, with its efficient computation and global feature modeling capabilities, outperforms CNNs under challenging conditions. In this paper, we implement real-time VLR using Swin Transformer and fine-tune it for optimal performance. Extensive experiments conducted on three public vehicle logo datasets (HFUT-VL1, XMU, CTGU-VLD) demonstrate impressive top accuracy results of 99.28%, 100%, and 99.17%, respectively. Additionally, the use of a transfer learning strategy enables our method to be on par with state-of-the-art VLR methods. These findings affirm the superiority of our approach over existing methods. Future research can explore and optimize the application of the Swin Transformer in other vehicle vision recognition tasks to drive advancements in ITS.

cs.CV↗