Deformations and extensions of homotopy associative algebras
The representation and the cohomology theory of associative 2-algebras are developed. We study the deformations and abelian extensions of associative 2-algebras in details.
math.RA↗
arXiv subjects
Tao Zhang
Publications and source records attributed to Tao Zhang.
On the proximal point algorithms for solving the monotone inclusion problem
We consider finding a zero point of the maximally monotone operator $T$. First, instead of using the proximal point algorithm (PPA) for this purpose, we employ PPA to solve its Yosida regularization $T_λ$. Then, based on an $O(a_{k+1})$ ($a_{k+1}\geq \varepsilon>0$) resolvent index of $T$, it turns out that we can establish a convergence rate of $O (1/{\sqrt{\sum_{i=0}^{k}a_{i+1}^2}})$ for both the $\|T_λ(\cdot)\|$ and the gap function $\mathtt{Gap}(\cdot)$ in the non-ergodic sense, and $O(1/\sum_{i=0}^{k}a_{i+1})$ for $\mathtt{Gap}(\cdot)$ in the ergodic sense. Second, to enhance the convergence rate of the newly-proposed PPA, we introduce an accelerated variant called the Contracting PPA. By utilizing a resolvent index of $T$ bounded by $O(a_{k+1})$ ($a_{k+1}\geq \varepsilon>0$), we establish a convergence rate of $O(1/\sum_{i=0}^{k}a_{i+1})$ for both $\|T_λ(\cdot)\|$ and $\mathtt {Gap}(\cdot)$, considering the non-ergodic sense. Third, to mitigate the limitation that the Contracting PPA lacks a convergence guarantee, we propose two additional versions of the algorithm. These novel approaches not only ensure guaranteed convergence but also provide sublinear and linear convergence rates for both $\|T_λ(\cdot)\|$ and $\mathtt {Gap}(\cdot)$, respectively, in the non-ergodic sense.
math.OC↗
Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling
Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.
cs.CL↗
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation (VSS), and video panoptic segmentation (VPS). Unlike previous methods that model video segmentation in an end-to-end manner, our approach decouples video segmentation into three cascaded sub-tasks: segmentation, tracking, and refinement. This decoupling design allows for simpler and more effective modeling of the spatio-temporal representations of objects, especially in complex scenes and long videos. Accordingly, we introduce two novel components: the referring tracker and the temporal refiner. These components track objects frame by frame and model spatio-temporal representations based on pre-aligned features. To improve the tracking capability of DVIS, we propose a denoising training strategy and introduce contrastive learning, resulting in a more robust framework named DVIS++. Furthermore, we evaluate DVIS++ in various settings, including open vocabulary and using a frozen pre-trained backbone. By integrating CLIP with DVIS++, we present OV-DVIS++, the first open-vocabulary universal video segmentation framework. We conduct extensive experiments on six mainstream benchmarks, including the VIS, VSS, and VPS datasets. Using a unified architecture, DVIS++ significantly outperforms state-of-the-art specialized methods on these benchmarks in both close- and open-vocabulary settings. Code:~\url{https://github.com/zhang-tao-whu/DVIS_Plus}.
cs.CV↗
Towards Accelerating Particle-Resolved Direct Numerical Simulation with Neural Operators
We present our ongoing work aimed at accelerating a particle-resolved direct numerical simulation model designed to study aerosol-cloud-turbulence interactions. The dynamical model consists of two main components - a set of fluid dynamics equations for air velocity, temperature, and humidity, coupled with a set of equations for particle (i.e., cloud droplet) tracing. Rather than attempting to replace the original numerical solution method in its entirety with a machine learning (ML) method, we consider developing a hybrid approach. We exploit the potential of neural operator learning to yield fast and accurate surrogate models and, in this study, develop such surrogates for the velocity and vorticity fields. We discuss results from numerical experiments designed to assess the performance of ML architectures under consideration as well as their suitability for capturing the behavior of relevant dynamical systems.
physics.flu-dyn↗
Search for Dark-Matter-Nucleon Interactions with a Dark Mediator in PandaX-4T
We report results of a search for dark-matter-nucleon interactions via a dark mediator using optimized low-energy data from the PandaX-4T liquid xenon experiment. With the ionization-signal-only data and utilizing the Migdal effect, we set the most stringent limits on the cross section for dark matter masses ranging from 30~$\rm{MeV/c^2}$ to 2~$\rm{GeV/c^2}$. Under the assumption that the dark mediator is a dark photon that decays into scalar dark matter pairs in the early Universe, we rule out significant parameter space of such thermal relic dark-matter model.
hep-ex↗
A family of Barzilai-Borwein steplengths from the viewpoint of scaled total least squares
The Barzilai-Borwein (BB) steplengths play great roles in practical gradient methods for solving unconstrained optimization problems. Motivated by the observation that the two well-known BB steplengths correspond to the ordinary and the data least squares, respectively, we present a family of BB steplengths from the viewpoint of scaled total least squares. Numerical experiments demonstrate that a high performance can be received by a carefully-selected BB steplength in the new family.
math.OC↗
PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images
Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared pre-training dataset, 2) the distinctiveness of non-iconic infrared images rendering common pre-training tasks like masked image modeling (MIM) less effective, and 3) the scarcity of fine-grained textures making it particularly challenging to learn general image features. To address these issues, we construct a Multi-Scene Infrared Pre-training (MSIP) dataset comprising 178,756 images, and introduce object-sensitive random RoI cropping, an image preprocessing method, to tackle the challenge posed by non-iconic images. To alleviate the impact of weak textures on feature learning, we propose a pre-training paradigm called Pre-training with ADapter (PAD), which uses adapters to learn domain-specific features while freezing parameters pre-trained on ImageNet to retain the general feature extraction capability. This new paradigm is applicable to any transformer-based SSL method. Furthermore, to achieve more flexible coordination between pre-trained and newly-learned features in different layers and patches, a patchwise-scale adapter with dynamically learnable scale factors is introduced. Extensive experiments on three downstream tasks show that PAD, with only 1.23M pre-trainable parameters, outperforms other baseline paradigms including continual full pre-training on MSIP. Our code and dataset are available at https://github.com/casiatao/PAD.
cs.CV↗
Technical Report for Argoverse Challenges on Unified Sensor-based Detection, Tracking, and Forecasting
This report presents our Le3DE2E solution for unified sensor-based detection, tracking, and forecasting in Argoverse Challenges at CVPR 2023 Workshop on Autonomous Driving (WAD). We propose a unified network that incorporates three tasks, including detection, tracking, and forecasting. This solution adopts a strong Bird's Eye View (BEV) encoder with spatial and temporal fusion and generates unified representations for multi-tasks. The solution was tested in the Argoverse 2 sensor dataset to evaluate the detection, tracking, and forecasting of 26 object categories. We achieved 1st place in Detection, Tracking, and Forecasting on the E2E Forecasting track in Argoverse Challenges at CVPR 2023 WAD.
cs.CV↗
JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction
Product attribute value extraction is an important task in e-Commerce which can help several downstream applications such as product search and recommendation. Most previous models handle this task using sequence labeling or question answering method which rely on the sequential position information of values in the product text and are vulnerable to data discrepancy between training and testing. This limits their generalization ability to real-world scenario in which each product can have multiple descriptions across various shopping platforms with different composition of text and style. They also have limited zero-shot ability to new values. In this paper, we propose a multi-task learning model with value generation/classification and attribute prediction called JPAVE to predict values without the necessity of position information of values in the text. Furthermore, the copy mechanism in value generator and the value attention module in value classifier help our model address the data discrepancy issue by only focusing on the relevant part of input text and ignoring other information which causes the discrepancy issue such as sentence structure in the text. Besides, two variants of our model are designed for open-world and closed-world scenarios. In addition, copy mechanism introduced in the first variant based on value generation can improve its zero-shot ability for identifying unseen values. Experimental results on a public dataset demonstrate the superiority of our model compared with strong baselines and its generalization ability of predicting new values.
cs.CL↗
Aspect-based Meeting Transcript Summarization: A Two-Stage Approach with Weak Supervision on Sentence Classification
Aspect-based meeting transcript summarization aims to produce multiple summaries, each focusing on one aspect of content in a meeting transcript. It is challenging as sentences related to different aspects can mingle together, and those relevant to a specific aspect can be scattered throughout the long transcript of a meeting. The traditional summarization methods produce one summary mixing information of all aspects, which cannot deal with the above challenges of aspect-based meeting transcript summarization. In this paper, we propose a two-stage method for aspect-based meeting transcript summarization. To select the input content related to specific aspects, we train a sentence classifier on a dataset constructed from the AMI corpus with pseudo-labeling. Then we merge the sentences selected for a specific aspect as the input for the summarizer to produce the aspect-based summary. Experimental results on the AMI corpus outperform many strong baselines, which verifies the effectiveness of our proposed method.
cs.CL↗
Correlation between spin state and activity for hydrogen evolution
Spin plays a key role in physical and chemical reactions, such as oxygen evolution and hydrogen evolution reactions (OER/HER); but the spin-activity correlation has remained unclear. Based on a transition metal (TM)-doped PtN2 monolayer model with a well-defined spin center as adsorption site, we here reveal that only active spin state can enhance the strength of hydrogen adsorption, while inert spin state offers very little influence. Specifically, the unpaired electron along the out-of-plane direction such as in dZ2 orbital, acting as an active spin state, will strongly hybridize with hydrogen, resulting in enhanced hydrogen binding energy because dZ2 orbital is just enough to accommodate two electrons to form a bonding orbital. While the in-plane unpaired electron such as in dX2-Y2 orbital, plays a negligible role in adsorbing hydrogen atom. This is verified by a series of single atom catalysts comprising of PtN2 monolayer by replacing Pt atom with a TM (Fe, Co, Ni, Ru, Rh, Pd, Os, or Ir) atom, or subsequent adsorbing a Cl atom. One of the most promising materials is Pd@PtN2-Cl that offers superior HER activity, even better than pure Pt. This work uncovers the nature of spin-activity correlation, thus paving the way for the design of high-performance catalysts through spin-engineering.
cond-mat.mtrl-sci↗
CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks
While Chain-of-Thought prompting is popular in reasoning tasks, its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored. Motivated by multi-step reasoning of LLMs, we propose Coarse-to-Fine Chain-of-Thought (CoF-CoT) approach that breaks down NLU tasks into multiple reasoning steps where LLMs can learn to acquire and leverage essential concepts to solve tasks from different granularities. Moreover, we propose leveraging semantic-based Abstract Meaning Representation (AMR) structured knowledge as an intermediate step to capture the nuances and diverse structures of utterances, and to understand connections between their varying levels of granularity. Our proposed approach is demonstrated effective in assisting the LLMs adapt to the multi-grained NLU tasks under both zero-shot and few-shot multi-domain settings.
cs.CL↗
A Policy Optimization Method Towards Optimal-time Stability
In current model-free reinforcement learning (RL) algorithms, stability criteria based on sampling methods are commonly utilized to guide policy optimization. However, these criteria only guarantee the infinite-time convergence of the system's state to an equilibrium point, which leads to sub-optimality of the policy. In this paper, we propose a policy optimization technique incorporating sampling-based Lyapunov stability. Our approach enables the system's state to reach an equilibrium point within an optimal time and maintain stability thereafter, referred to as "optimal-time stability". To achieve this, we integrate the optimization method into the Actor-Critic framework, resulting in the development of the Adaptive Lyapunov-based Actor-Critic (ALAC) algorithm. Through evaluations conducted on ten robotic tasks, our approach outperforms previous studies significantly, effectively guiding the system to generate stable patterns.
cs.RO↗
Stochastic Game with Interactive Information Acquisition: Pipelined Perfect Markov Bayesian Equilibrium
This paper studies a multi-player, general-sum stochastic game characterized by a dual-stage temporal structure per period. The agents face uncertainty regarding the time-evolving state that is realized at the beginning of each period. During the first stage, agents engage in information acquisition regarding the unknown state. Each agent strategically selects from multiple signaling options, each carrying a distinct cost. The selected signaling rule dispenses private information that determines the type of the agent. In the second stage, the agents play a Bayesian game by taking actions contingent on their private types. We introduce an equilibrium concept, Pipelined Perfect Markov Bayesian Equilibrium (PPME), which incorporates the Markov perfect equilibrium and the perfect Bayesian equilibrium. We propose a novel equilibrium characterization principle termed fixed-point alignment and deliver a set of verifiable necessary and sufficient conditions for any strategy profile to achieve PPME.
cs.GT↗
Frequency Tunable Magnetostatic Wave Filters With Zero Static Power Magnetic Biasing Circuitry
A single tunable filter simplifies complexity, reduces insertion loss, and minimizes size compared to frequency switchable filter banks commonly used for radio frequency (RF) band selection. Magnetostatic wave (MSW) filters stand out for their wide, continuous frequency tuning and high-quality factor. However, MSW filters employing electromagnets for tuning consume excessive power and space, unsuitable for consumer wireless applications. Here, we demonstrate miniature and high selectivity MSW tunable filters with zero static power consumption, occupying less than 2 cc. The center frequency is continuously tunable from 3.4 GHz to 11.1 GHz via current pulses of sub-millisecond duration applied to a small and nonvolatile magnetic bias assembly. This assembly is limited in the area over which it can achieve a large and uniform magnetic field, necessitating filters realized from small resonant cavities micromachined in thin films of Yttrium Iron Garnet. Filter insertion loss of 3.2 dB to 5.1 dB and out-of-band third order input intercept point greater than 41 dBm are achieved. The filter's broad frequency range, compact size, low insertion loss, high out-of-band linearity, and zero static power consumption are essential for protecting RF transceivers and antennas from interference, thus facilitating their use in mobile applications like IoT and 6G networks.
physics.app-ph↗
On (co-)morphisms of $n$-Lie-Rinehart algebras with applications to Nambu-Poisson manifolds
In this paper, we give a unified description of morphisms and comorphisms of $n$-Lie-Rinehart algebras. We show that these morphisms and comorphisms can be regarded as two subalgebras of the $ψ$-sum of $n$-Lie-Rinehart algebras. We also provide similar descriptions for morphisms and comorphisms of $n$-Lie algebroids. It is proved that the category of vector bundles with Nambu-Poisson structures of rank $n$ and the category of their dual bundles with $n$-Lie algebroid structures of rank $n$ are equivalent to each other.
math.RA↗
Conformal Lie 2-algebras and conformal omni-Lie algebras
The notions of conformal Lie 2-algebras and conformal omni-Lie algebras are introduced and studied. It is proved that the category of conformal Lie 2-algebras and the category of 2-term conformal $L_{\infty}$-algebras are equivalent. We construct conformal Lie 2-algebras from conformal omni-Lie algebras and Leibniz conformal algebras.
math.RA↗