arXiv subjects

Xin Chen

Publications and source records attributed to Xin Chen.

At least 451 records · Page 25Linked to original sources

arXiv2023

Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning

We propose a model-free reinforcement learning solution, namely the ASAP-Phi framework, to encourage an agent to fulfill a formal specification ASAP. The framework leverages a piece-wise reward function that assigns quantitative semantic reward to traces not satisfying the specification, and a high constant reward to the remaining. Then, it trains an agent with an actor-critic-based algorithm, such as soft actor-critic (SAC), or deep deterministic policy gradient (DDPG). Moreover, we prove that ASAP-Phi produces policies that prioritize fulfilling a specification ASAP. Extensive experiments are run, including ablation studies, on state-of-the-art benchmarks. Results show that our framework succeeds in finding sufficiently fast trajectories for up to 97\% test cases and defeats baselines.

cs.LG↗

arXiv2023

Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism

The Mixture of Experts (MoE) model becomes an important choice of large language models nowadays because of its scalability with sublinear computational complexity for training and inference. However, existing MoE models suffer from two critical drawbacks, 1) tremendous inner-node and inter-node communication overhead introduced by all-to-all dispatching and gathering, and 2) limited scalability for the backbone because of the bound data parallel and expert parallel to scale in the expert dimension. In this paper, we systematically analyze these drawbacks in terms of training efficiency in the parallel framework view and propose a novel MoE architecture called Pipeline MoE (PPMoE) to tackle them. PPMoE builds expert parallel incorporating with tensor parallel and replaces communication-intensive all-to-all dispatching and gathering with a simple tensor index slicing and inner-node all-reduce. Besides, it is convenient for PPMoE to integrate pipeline parallel to further scale the backbone due to its flexible parallel architecture. Extensive experiments show that PPMoE not only achieves a more than $1.75\times$ speed up compared to existing MoE architectures but also reaches $90\%$ throughput of its corresponding backbone model that is $20\times$ smaller.

cs.DC↗

arXiv2023

A Self-attention Knowledge Domain Adaptation Network for Commercial Lithium-ion Batteries State-of-health Estimation under Shallow Cycles

Accurate state-of-health (SOH) estimation is critical to guarantee the safety, efficiency and reliability of battery-powered applications. Most SOH estimation methods focus on the 0-100\% full state-of-charge (SOC) range that has similar distributions. However, the batteries in real-world applications usually work in the partial SOC range under shallow-cycle conditions and follow different degradation profiles with no labeled data available, thus making SOH estimation challenging. To estimate shallow-cycle battery SOH, a novel unsupervised deep transfer learning method is proposed to bridge different domains using self-attention distillation module and multi-kernel maximum mean discrepancy technique. The proposed method automatically extracts domain-variant features from charge curves to transfer knowledge from the large-scale labeled full cycles to the unlabeled shallow cycles. The CALCE and SNL battery datasets are employed to verify the effectiveness of the proposed method to estimate the battery SOH for different SOC ranges, temperatures, and discharge rates. The proposed method achieves a root-mean-square error within 2\% and outperforms other transfer learning methods for different SOC ranges. When applied to batteries with different operating conditions and from different manufacturers, the proposed method still exhibits superior SOH estimation performance. The proposed method is the first attempt at accurately estimating battery SOH under shallow-cycle conditions without needing a full-cycle characteristic test.

cs.LG↗

arXiv2023

POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems

Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performances on challenging control problems. However, the potential adoption of NN controllers in real-life applications also gives rise to a growing concern over the safety of these neural-network controlled systems (NNCSs), especially when used in safety-critical applications. In this work, we present POLAR-Express, an efficient and precise formal reachability analysis tool for verifying the safety of NNCSs. POLAR-Express uses Taylor model arithmetic to propagate Taylor models (TMs) across a neural network layer-by-layer to compute an overapproximation of the neural-network function. It can be applied to analyze any feed-forward neural network with continuous activation functions. We also present a novel approach to propagate TMs more efficiently and precisely across ReLU activation functions. In addition, POLAR-Express provides parallel computation support for the layer-by-layer propagation of TMs, thus significantly improving the efficiency and scalability over its earlier prototype POLAR. Across the comparison with six other state-of-the-art tools on a diverse set of benchmarks, POLAR-Express achieves the best verification efficiency and tightness in the reachable set analysis.

eess.SY↗

arXiv2023

Observation of non-superconducting phase changes in LuH$_{2\pm\text{x}}$N$_y$

The recent report of near-ambient superconductivity in nitrogen doped lutetium hydride has triggered a worldwide fanaticism and raised major questions about the latest claims. An intriguing phenomenon of color changes in pressurized samples from blue to pink to red was observed and correlated with the claimed superconducting transition, but the origin and underlying physics of these color changes have yet to be elucidated. Here we report synthesis and characterization of high-purity nitrogen doped lutetium hydride LuH$_{2\pm\text{x}}$N$_y$ with the same structure and composition as in the main phase of near-ambient superconductor1. We find a new purple phase of LuH$_{2\pm\text{x}}$N$_y$ between blue and pink phase, and reveal that the sample color changes likely stem from pressure-driven redistribution of nitrogen and its interaction with the LuH$_2$ framework. No superconducting transition is found in all blue, purple, pink and red phases at temperatures 1.8-300 K and pressures 0-30 GPa. Instead, we identify a notable temperature-induced resistance anomaly of structural and/or electronic origin in LuH$_{2\pm\text{x}}$N$_y$, which is most pronounced in the pink phase and may have been erroneously interpreted as a sign of superconducting transition. This work establishes key benchmarks for nitrogen doped lutetium hydrides, allowing an in-depth understanding of the novel pressure-induced phase changes.

cond-mat.supr-con↗

arXiv2023

Devil is in the Queries: Advancing Mask Transformers for Real-world Medical Image Segmentation and Out-of-Distribution Localization

Real-world medical image segmentation has tremendous long-tailed complexity of objects, among which tail conditions correlate with relatively rare diseases and are clinically significant. A trustworthy medical AI algorithm should demonstrate its effectiveness on tail conditions to avoid clinically dangerous damage in these out-of-distribution (OOD) cases. In this paper, we adopt the concept of object queries in Mask Transformers to formulate semantic segmentation as a soft cluster assignment. The queries fit the feature-level cluster centers of inliers during training. Therefore, when performing inference on a medical image in real-world scenarios, the similarity between pixels and the queries detects and localizes OOD regions. We term this OOD localization as MaxQuery. Furthermore, the foregrounds of real-world medical images, whether OOD objects or inliers, are lesions. The difference between them is less than that between the foreground and background, possibly misleading the object queries to focus redundantly on the background. Thus, we propose a query-distribution (QD) loss to enforce clear boundaries between segmentation targets and other regions at the query level, improving the inlier segmentation and OOD indication. Our proposed framework is tested on two real-world segmentation tasks, i.e., segmentation of pancreatic and liver tumors, outperforming previous state-of-the-art algorithms by an average of 7.39% on AUROC, 14.69% on AUPR, and 13.79% on FPR95 for OOD localization. On the other hand, our framework improves the performance of inlier segmentation by an average of 5.27% DSC when compared with the leading baseline nnUNet.

cs.CV↗

arXiv2023

Visual Prompt Multi-Modal Tracking

Visible-modal object tracking gives rise to a series of downstream multi-modal tracking tributaries. To inherit the powerful representations of the foundation model, a natural modus operandi for multi-modal tracking is full fine-tuning on the RGB-based parameters. Albeit effective, this manner is not optimal due to the scarcity of downstream data and poor transferability, etc. In this paper, inspired by the recent success of the prompt learning in language models, we develop Visual Prompt multi-modal Tracking (ViPT), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to various downstream multimodal tracking tasks. ViPT finds a better way to stimulate the knowledge of the RGB-based model that is pre-trained at scale, meanwhile only introducing a few trainable parameters (less than 1% of model parameters). ViPT outperforms the full fine-tuning paradigm on multiple downstream tracking tasks including RGB+Depth, RGB+Thermal, and RGB+Event tracking. Extensive experiments show the potential of visual prompt learning for multi-modal tracking, and ViPT can achieve state-of-the-art performance while satisfying parameter efficiency. Code and models are available at https://github.com/jiawen-zhu/ViPT.

cs.CV↗

arXiv2023

Self-driven photo-polarized water molecule triggered graphene-based photodetector

Flowing water can be used as an energy source for generators, providing a major part of the energy for daily life. However, water is rarely used for information or electronic devices. Herein, we present the feasibility of a polarized liquid-triggered photodetector in which polarized water is sandwiched between graphene and semiconductor. Due to the polarization and depolarization processes of water molecular under the driven of photogenerated carriers, a photo-sensitive current can be repeatably produced, resulting in a high-performance photodetector. The response wavelength of the photodetector can be finely tuned as a result of the free choice of semiconductors as there is no requirement of lattice match between graphene and the semiconductors. Under zero voltage bias, the responsivity and specific detectivity of Gr/NaCl (0.5 M)/N-GaN reaches values of 130.7 mA/W and 2.8*10^12 Jones under 350 nm illumination. Meanwhile, using a polar liquid photodetector can successfully read the photoplethysmography signals to produce accurate oxygen blood saturation and heart rate. Compared with the commercial pulse oximetry sensor, the average errors of oxygen saturation and heart rate in the designed photoplethysmography sensor are~1.9% and ~2.1%, respectively. This study transfers the message that water can be used as high-performance photodetector in informative industries.

physics.app-ph↗

arXiv2023

Transferable Deep Learning Power System Short-Term Voltage Stability Assessment with Physics-Informed Topological Feature Engineering

Deep learning (DL) algorithms have been widely applied to short-term voltage stability (STVS) assessment in power systems. However, transferring the knowledge learned in one power grid to other power grids with topology changes is still a challenging task. This paper proposed a transferable DL-based model for STVS assessment by constructing the topology-aware voltage dynamic features from raw PMU data. Since the reactive power flow and grid topology are essential to voltage stability, the topology-aware and physics-informed voltage dynamic features are utilized to effectively represent the topological and temporal patterns from post-disturbance system dynamic trajectories. The proposed DL-based STVS assessment model is tested under random operating conditions on the New England 39-bus system. It has 99.99\% classification accuracy of the short-term voltage stability status using the topology-aware and physics-informed voltage dynamic features. In addition to high accuracy, the experiments show good adaptability to PMU errors. Moreover, The proposed STVS assessment method has outstanding performance on new grid topologies after fine-tuning. In particular, the highest accuracy reaches 99.68\% in evaluation, which demonstrates a good knowledge transfer ability of the proposed model for power grid topology change.

eess.SY↗

arXiv2023

Comparative study of first-principles approaches for effective Coulomb interaction strength $U_{\rm eff}$ between localized $f$-electrons: lanthanide metals as an example

As correlation strength has a key influence on the simulation of strongly correlated materials, many approaches have been proposed to obtain the parameter using first-principles calculations. However, the comparison of the different Coulomb strengths obtained using these approaches and an investigation of the mechanisms behind them are still needed. Taking lanthanide metals as an example, we research the factors that affect the effective Coulomb interaction strength, $U_{\rm eff}$, by local screened Coulomb correction (LSCC), linear response (LR) and constrained random-phase approximation (cRPA) in VASP. The $U^{\rm LSCC}_{\rm eff}$ value increases from 4.75 eV to 7.78 eV, $U^{\rm LR}_{\rm eff}$ is almost stable at about 6.0 eV (except for Eu, Er and Lu), and $U^{\rm cRPA}_{\rm eff}$ shows a two-stage decreasing trend in both light and heavy lanthanides. To investigate these differences, we established a scheme to analyze coexistence and competition between the orbital localization and the screening effect. We find that LSCC and cRPA are dominated by the orbital localization and the screening effect, respectively, whereas LR shows a balance of the competition between the two factors. Additionally, the performance of these approaches is influenced by different starting points from PBE and PBE+$U$, especially for cRPA. Our results provide useful knowledge for understanding the $U_{\rm eff}$ of lanthanide materials, and similar analyses can also be used in the research of other correlation strength simulation approaches.

cond-mat.mtrl-sci↗

arXiv2023

Logarithmic heat kernels estimates without curvature restrictions

The main results of the article are short time estimates and asymptotic estimates for the first two order derivatives of the logarithmic heat kernel of a complete Riemannian manifold. We remove all curvature restrictions and also develop several techniques. A basic tool developed here is intrinsic stochastic variations with prescribed second order covariant differentials, allowing to obtain a path integration representation for the second order derivatives of the heat semigroup $P_t$ on a complete Riemannian manifold, again without any assumptions on the curvature. The novelty is the introduction of an $ε^2$ term in the variation allowing greater control. We also construct a family of cut-off stochastic processes adapted to an exhaustion by compact subsets with smooth boundaries, each process is constructed path by path and differentiable in time, furthermore the differentials have locally uniformly bounded moments with respect to the Brownian motion measures, allowing to by-pass the lack of continuity of the exit time of the Brownian motions on its initial position.

math.PR↗

arXiv2023

Hidden Euclidean dynamical symmetry in the U(n+1) vibron model

Based on the boson realization of the Euclidean algebras, it is found that the E($n$) dynamical symmetry (DS) may emerge at the critical point of the U($n$)-SO($n+1$) quantum phase transition. To justify this finding, we provide a detailed analysis of the critical dynamics in the U($n+1$) vibron model in both quantal and classical ways. It is further shown that the low-lying structure of $^{82}$Kr may serve as an excellent empirical realization of the E(5) DS in experiments.

nucl-th↗

arXiv2023

Dyadic Green Function Approach to Multichromophoric Forster Resonance Energy Transfer under Electromagnetic Fluctuations near Metallic Thin Films

The near-field spectroscopic information is critically important to determine the Forster resonant energy transfer(FRET) rate and the distance dependence in the vicinity of metal surfaces. The high density of evanescent near-field modes in the vicinity of a metal surface can strongly modulate the FRET in multichromophoric systems. Based on the previous generalized FRET [A. Poudel, X. Chen and M. Ratner, J. Phys. Chem. Lett. 7(2016) 955], the theory of FRET is generalized for the multichromophore aggregates and nonequilibrium situations in the vicinity of evanescent surface electromagnetic waves of nanophotonic structures. The classic dyadic green function (DGF) approach to multichromophoric FRET (MC-FRET) in the existence of evanescent near-field is established. The classic DGF approach provides a microscopic understanding of the interaction between the emission and absorption spectral coupling and the evanescent electromagnetic field. The MC-FRET of the ring structures demonstrates complicated distance dependence in the vicinity of the silver thin film. Given the analytic expression of hyperbolic multi-layer thin film, the generalized coupling due to the metallic thin film is determined by the scattering DGF above the metal surface. The decomposition of the reduced scattering DGF by ignoring $S$ wave in the evanescent wave shows how the interface of the metallic thin films modulates the MC-FRET.

physics.chem-ph↗

arXiv2023

Disentangled Causal Embedding With Contrastive Learning For Recommender System

Recommender systems usually rely on observed user interaction data to build personalized recommendation models, assuming that the observed data reflect user interest. However, user interacting with an item may also due to conformity, the need to follow popular items. Most previous studies neglect user's conformity and entangle interest with it, which may cause the recommender systems fail to provide satisfying results. Therefore, from the cause-effect view, disentangling these interaction causes is a crucial issue. It also contributes to OOD problems, where training and test data are out-of-distribution. Nevertheless, it is quite challenging as we lack the signal to differentiate interest and conformity. The data sparsity of pure cause and the items' long-tail problem hinder disentangled causal embedding. In this paper, we propose DCCL, a framework that adopts contrastive learning to disentangle these two causes by sample augmentation for interest and conformity respectively. Futhermore, DCCL is model-agnostic, which can be easily deployed in any industrial online system. Extensive experiments are conducted over two real-world datasets and DCCL outperforms state-of-the-art baselines on top of various backbone models in various OOD environments. We also demonstrate the performance improvements by online A/B testing on Kuaishou, a billion-user scale short-video recommender system.

cs.IR↗

arXiv2023

A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction

Neural Radiance Fields (NeRF) has achieved impressive results in single object scene reconstruction and novel view synthesis, which have been demonstrated on many single modality and single object focused indoor scene datasets like DTU, BMVS, and NeRF Synthetic.However, the study of NeRF on large-scale outdoor scene reconstruction is still limited, as there is no unified outdoor scene dataset for large-scale NeRF evaluation due to expensive data acquisition and calibration costs. In this paper, we propose a large-scale outdoor multi-modal dataset, OMMO dataset, containing complex land objects and scenes with calibrated images, point clouds and prompt annotations. Meanwhile, a new benchmark for several outdoor NeRF-based tasks is established, such as novel view synthesis, surface reconstruction, and multi-modal NeRF. To create the dataset, we capture and collect a large number of real fly-view videos and select high-quality and high-resolution clips from them. Then we design a quality review module to refine images, remove low-quality frames and fail-to-calibrate scenes through a learning-based automatic evaluation plus manual review. Finally, a number of volunteers are employed to add the text descriptions for each scene and key-frame to meet the potential multi-modal requirements in the future. Compared with existing NeRF datasets, our dataset contains abundant real-world urban and natural scenes with various scales, camera trajectories, and lighting conditions. Experiments show that our dataset can benchmark most state-of-the-art NeRF methods on different tasks. We will release the dataset and model weights very soon.

cs.CV↗

arXiv2023

Forward-backward stochastic differential equations on tensor fields and application to Navier-Stokes equations on Riemannian manifolds

In this paper we introduce a class of forward-backward stochastic differential equations on tensor fields of Riemannian manifolds, which are related to semi-linear parabolic partial differential equations on tensor fields. Moreover, we will use these forward-backward stochastic differential equations to give a stochastic characterization of incompressible Navier-Stokes equations on Riemannian manifolds, where some extra conditions used in [22] are not required.

math.PR↗

arXiv2023

End-to-End 3D Dense Captioning with Vote2Cap-DETR

3D dense captioning aims to generate multiple captions localized with their associated object regions. Existing methods follow a sophisticated ``detect-then-describe'' pipeline equipped with numerous hand-crafted components. However, these hand-crafted components would yield suboptimal performance given cluttered object spatial and class distributions among different scenes. In this paper, we propose a simple-yet-effective transformer framework Vote2Cap-DETR based on recent popular \textbf{DE}tection \textbf{TR}ansformer (DETR). Compared with prior arts, our framework has several appealing advantages: 1) Without resorting to numerous hand-crafted components, our method is based on a full transformer encoder-decoder architecture with a learnable vote query driven object decoder, and a caption decoder that produces the dense captions in a set-prediction manner. 2) In contrast to the two-stage scheme, our method can perform detection and captioning in one-stage. 3) Without bells and whistles, extensive experiments on two commonly used datasets, ScanRefer and Nr3D, demonstrate that our Vote2Cap-DETR surpasses current state-of-the-arts by 11.13\% and 7.11\% in CIDEr@0.5IoU, respectively. Codes will be released soon.

cs.CV↗

arXiv2022

POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems

We present POLAR, a polynomial arithmetic-based framework for efficient bounded-time reachability analysis of neural-network controlled systems (NNCSs). Existing approaches that leverage the standard Taylor Model (TM) arithmetic for approximating the neural-network controller cannot deal with non-differentiable activation functions and suffer from rapid explosion of the remainder when propagating the TMs. POLAR overcomes these shortcomings by integrating TM arithmetic with \textbf{Bernstein B{é}zier Form} and \textbf{symbolic remainder}. The former enables TM propagation across non-differentiable activation functions and local refinement of TMs, and the latter reduces error accumulation in the TM remainder for linear mappings in the network. Experimental results show that POLAR significantly outperforms the current state-of-the-art tools in terms of both efficiency and tightness of the reachable set overapproximation. The source code can be found in https://github.com/ChaoHuang2018/POLAR_Tool

eess.SY↗