arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 523 records · Page 29Linked to original sources

arXiv2025

CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detection

Fusing multi-modality inputs from different sensors is an effective way to improve the performance of 3D object detection. However, current methods overlook two important conflicts: point-pixel misalignment and sub-task suppression. The former means a pixel feature from the opaque object is projected to multiple point features of the same ray in the world space, and the latter means the classification prediction and bounding box regression may cause mutual suppression. In this paper, we propose a novel method named Conflict Resolution Network (CoreNet) to address the aforementioned issues. Specifically, we first propose a dual-stream transformation module to tackle point-pixel misalignment. It consists of ray-based and point-based 2D-to-BEV transformations. Both of them achieve approximately unique mapping from the image space to the world space. Moreover, we introduce a task-specific predictor to tackle sub-task suppression. It uses the dual-branch structure which adopts class-specific query and Bbox-specific query to corresponding sub-tasks. Each task-specific query is constructed of task-specific feature and general feature, which allows the heads to adaptively select information of interest based on different sub-tasks. Experiments on the large-scale nuScenes dataset demonstrate the superiority of our proposed CoreNet, by achieving 75.6\% NDS and 73.3\% mAP on the nuScenes test set without test-time augmentation and model ensemble techniques. The ample ablation study also demonstrates the effectiveness of each component. The code is released on https://github.com/liyih/CoreNet.

cs.CV↗

arXiv2025

Probing Nuclear Excitation by Electron Capture in an Electron Beam Ion Trap with Non-destructive Isomer Detection via Precision Mass Spectrometry

Nuclear excitation by electron capture (NEEC) is an important nuclear excitation mechanism which still lacks conclusive experimental verification. This is primarily attributed to strong background x-/$γ$-ray noise and competing nuclear excitation processes which would overshadow the signals in various environments that NEEC takes place. Here, we propose an experimental approach to observe the NEEC process within a background-free environment. Through collisions with a highly-compressed mono-energetic electron beam in an electron beam ion trap, nuclei may get excited to a long-lived isomeric state via the NEEC process. Subsequently, ions can be extracted and Penning-trap mass spectrometry employed to unambiguously detect the isomer. Our study focuses on the promising candidate $^{189}\mathrm{Os}$, demonstrating measurable detection rates of the NEEC process and discussing the feasibility of the proposed approach. This new approach for observing the NEEC process may be realized in the near future.

nucl-ex↗

arXiv2025

Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence

Recent years have witnessed a thriving growth of computing facilities connected at the network edge, cultivating edge networks as a fundamental infrastructure for supporting miscellaneous intelligent services.Meanwhile, Artificial Intelligence (AI) frontiers have extrapolated to the graph domain and promoted Graph Intelligence (GI). Given the inherent relation between graphs and networks, the interdiscipline of graph learning and edge networks, i.e., Edge GI or EGI, has revealed a novel interplay between them -- GI aids in optimizing edge networks, while edge networks facilitate GI model deployment. Driven by this delicate closed-loop, EGI is recognized as a promising solution to fully unleash the potential of edge computing power and is garnering growing attention. Nevertheless, research on EGI remains nascent, and there is a soaring demand within both the communications and AI communities for a dedicated venue to share recent advancements. To this end, this paper promotes the concept of EGI, explores its scope and core principles, and conducts a comprehensive survey concerning recent research efforts on this emerging field. Specifically, this paper introduces and discusses: 1) fundamentals of edge computing and graph learning,2) emerging techniques centering on the closed loop between graph intelligence and edge networks, and 3) open challenges and research opportunities of future EGI. By bridging the gap across communication, networking, and graph learning areas, we believe that this survey can garner increased attention, foster meaningful discussions, and inspire further research ideas in EGI.

cs.DC↗

arXiv2025

Second order asymptotics for discounted aggregate claims of continuous-time renewal risk models with constant interest force

This paper investigates the second order asymptotic expansion for tail probabilities of discounted aggregate claims in continuous-time renewal risk models with constant interest force. Concretely, two types of continuous-time renewal risk models without and with by-claims are separately discussed. By constructing the asymptotic theory and weighted Kesten-type inequality of randomly weighted sums for second order subexponential random variables, second order asymptotic formulae for these two risk models are firstly built. In comparison of the first order asymptotic formulae, our results are more superior and precise, which are demonstrated by some simple numerical studies.

stat.AP↗

arXiv2025

Fitting Different Interactive Information: Joint Classification of Emotion and Intention

This paper is the first-place solution for ICASSP MEIJU@2025 Track I, which focuses on low-resource multimodal emotion and intention recognition. How to effectively utilize a large amount of unlabeled data, while ensuring the mutual promotion of different difficulty levels tasks in the interaction stage, these two points become the key to the competition. In this paper, pseudo-label labeling is carried out on the model trained with labeled data, and samples with high confidence and their labels are selected to alleviate the problem of low resources. At the same time, the characteristic of easy represented ability of intention recognition found in the experiment is used to make mutually promote with emotion recognition under different attention heads, and higher performance of intention recognition is achieved through fusion. Finally, under the refined processing data, we achieve the score of 0.5532 in the Test set, and win the championship of the track.

cs.CV↗

arXiv2025

Attribute-Based Robotic Grasping with Data-Efficient Adaptation

Robotic grasping is one of the most fundamental robotic manipulation tasks and has been the subject of extensive research. However, swiftly teaching a robot to grasp a novel target object in clutter remains challenging. This paper attempts to address the challenge by leveraging object attributes that facilitate recognition, grasping, and rapid adaptation to new domains. In this work, we present an end-to-end encoder-decoder network to learn attribute-based robotic grasping with data-efficient adaptation capability. We first pre-train the end-to-end model with a variety of basic objects to learn generic attribute representation for recognition and grasping. Our approach fuses the embeddings of a workspace image and a query text using a gated-attention mechanism and learns to predict instance grasping affordances. To train the joint embedding space of visual and textual attributes, the robot utilizes object persistence before and after grasping. Our model is self-supervised in a simulation that only uses basic objects of various colors and shapes but generalizes to novel objects in new environments. To further facilitate generalization, we propose two adaptation methods, adversarial adaption and one-grasp adaptation. Adversarial adaptation regulates the image encoder using augmented data of unlabeled images, whereas one-grasp adaptation updates the overall end-to-end model using augmented data from one grasp trial. Both adaptation methods are data-efficient and considerably improve instance grasping performance. Experimental results in both simulation and the real world demonstrate that our approach achieves over 81% instance grasping success rate on unknown objects, which outperforms several baselines by large margins.

cs.RO↗

arXiv2024

Enhanced coarsening of charge density waves induced by electron correlation: Machine-learning enabled large-scale dynamical simulations

The phase ordering kinetics of emergent orders in correlated electron systems is a fundamental topic in non-equilibrium physics, yet it remains largely unexplored. The intricate interplay between quasiparticles and emergent order-parameter fields could lead to unusual coarsening dynamics that is beyond the standard theories. However, accurate treatment of both quasiparticles and collective degrees of freedom is a multi-scale challenge in dynamical simulations of correlated electrons. Here we leverage modern machine learning (ML) methods to achieve a linear-scaling algorithm for simulating the coarsening of charge density waves (CDWs), one of the fundamental symmetry breaking phases in functional electron materials. We demonstrate our approach on the square-lattice Hubbard-Holstein model and uncover an intriguing enhancement of CDW coarsening which is related to the screening of on-site potential by electron-electron interactions. Our study provides fresh insights into the role of electron correlations in non-equilibrium dynamics and underscores the promise of ML force-field approaches for advancing multi-scale dynamical modeling of correlated electron systems.

cond-mat.str-el↗

arXiv2024

Flat level sets of Allen-Cahn equation in half-space

We prove a half-space Bernstein theorem for Allen-Cahn equation. More precisely, we show that every solution $u$ of the Allen-Cahn equation in the half-space $\overline{\mathbb{R}^n_+}:=\{(x_1,x_2,\cdots,x_n)\in\mathbb{R}^n:\,x_1\geq 0\}$ with $|u|\leq 1$, boundary value given by the restriction of a one-dimensional solution on $\{x_1=0\}$ and monotone condition $\partial_{x_n}u>0$ as well as limiting condition $\lim_{x_n\to\pm\infty}u(x',x_n)=\pm 1$ must itself be one-dimensional, and the parallel flat level sets and $\{x_1=0\}$ intersect at the same fixed angle in $(0, \fracπ{2}]$.

math.AP↗

arXiv2024

Text-Driven Tumor Synthesis

Tumor synthesis can generate examples that AI often misses or over-detects, improving AI performance by training on these challenging cases. However, existing synthesis methods, which are typically unconditional -- generating images from random variables -- or conditioned only by tumor shapes, lack controllability over specific tumor characteristics such as texture, heterogeneity, boundaries, and pathology type. As a result, the generated tumors may be overly similar or duplicates of existing training data, failing to effectively address AI's weaknesses. We propose a new text-driven tumor synthesis approach, termed TextoMorph, that provides textual control over tumor characteristics. This is particularly beneficial for examples that confuse the AI the most, such as early tumor detection (increasing Sensitivity by +8.5%), tumor segmentation for precise radiotherapy (increasing DSC by +6.3%), and classification between benign and malignant tumors (improving Sensitivity by +8.2%). By incorporating text mined from radiology reports into the synthesis process, we increase the variability and controllability of the synthetic tumors to target AI's failure cases more precisely. Moreover, TextoMorph uses contrastive learning across different texts and CT scans, significantly reducing dependence on scarce image-report pairs (only 141 pairs used in this study) by leveraging a large corpus of 34,035 radiology reports. Finally, we have developed rigorous tests to evaluate synthetic tumors, including Text-Driven Visual Turing Test and Radiomics Pattern Analysis, showing that our synthetic tumors is realistic and diverse in texture, heterogeneity, boundaries, and pathology.

eess.IV↗

arXiv2024

Geometric construction of Schur algebras

We provide the geometric construction of a series of generalized Schur algebras of any type via Borel-Moore homologies and equivariant K-groups of generalized Steinberg varieties. As applications, we obtain a Schur algebra analogue of the local geometric Langlands correspondence of any type, provide an equivariant K-theoretic realization of quasi-split $\imath$quantum groups of affine type AIII, and establish a geometric Howe duality for affine ($\imath$-)quantum groups.

math.RT↗

arXiv2024

GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generators

Recently, 3D generative domain adaptation has emerged to adapt the pre-trained generator to other domains without collecting massive datasets and camera pose distributions. Typically, they leverage large-scale pre-trained text-to-image diffusion models to synthesize images for the target domain and then fine-tune the 3D model. However, they suffer from the tedious pipeline of data generation, which inevitably introduces pose bias between the source domain and synthetic dataset. Furthermore, they are not generalized to support one-shot image-guided domain adaptation, which is more challenging due to the more severe pose bias and additional identity bias introduced by the single image reference. To address these issues, we propose GCA-3D, a generalized and consistent 3D domain adaptation method without the intricate pipeline of data generation. Different from previous pipeline methods, we introduce multi-modal depth-aware score distillation sampling loss to efficiently adapt 3D generative models in a non-adversarial manner. This multi-modal loss enables GCA-3D in both text prompt and one-shot image prompt adaptation. Besides, it leverages per-instance depth maps from the volume rendering module to mitigate the overfitting problem and retain the diversity of results. To enhance the pose and identity consistency, we further propose a hierarchical spatial consistency loss to align the spatial structure between the generated images in the source and target domain. Experiments demonstrate that GCA-3D outperforms previous methods in terms of efficiency, generalization, pose accuracy, and identity consistency.

cs.CV↗

arXiv2024

ITP: Instance-Aware Test Pruning for Out-of-Distribution Detection

Out-of-distribution (OOD) detection is crucial for ensuring the reliable deployment of deep models in real-world scenarios. Recently, from the perspective of over-parameterization, a series of methods leveraging weight sparsification techniques have shown promising performance. These methods typically focus on selecting important parameters for in-distribution (ID) data to reduce the negative impact of redundant parameters on OOD detection. However, we empirically find that these selected parameters may behave overconfidently toward OOD data and hurt OOD detection. To address this issue, we propose a simple yet effective post-hoc method called Instance-aware Test Pruning (ITP), which performs OOD detection by considering both coarse-grained and fine-grained levels of parameter pruning. Specifically, ITP first estimates the class-specific parameter contribution distribution by exploring the ID data. By using the contribution distribution, ITP conducts coarse-grained pruning to eliminate redundant parameters. More importantly, ITP further adopts a fine-grained test pruning process based on the right-tailed Z-score test, which can adaptively remove instance-level overconfident parameters. Finally, ITP derives OOD scores from the pruned model to achieve more reliable predictions. Extensive experiments on widely adopted benchmarks verify the effectiveness of ITP, demonstrating its competitive performance.

cs.CV↗

arXiv2024

RCTrans: Radar-Camera Transformer via Radar Densifier and Sequential Decoder for 3D Object Detection

In radar-camera 3D object detection, the radar point clouds are sparse and noisy, which causes difficulties in fusing camera and radar modalities. To solve this, we introduce a novel query-based detection method named Radar-Camera Transformer (RCTrans). Specifically, we first design a Radar Dense Encoder to enrich the sparse valid radar tokens, and then concatenate them with the image tokens. By doing this, we can fully explore the 3D information of each interest region and reduce the interference of empty tokens during the fusing stage. We then design a Pruning Sequential Decoder to predict 3D boxes based on the obtained tokens and random initialized queries. To alleviate the effect of elevation ambiguity in radar point clouds, we gradually locate the position of the object via a sequential fusion structure. It helps to get more precise and flexible correspondences between tokens and queries. A pruning training strategy is adopted in the decoder, which can save much time during inference and inhibit queries from losing their distinctiveness. Extensive experiments on the large-scale nuScenes dataset prove the superiority of our method, and we also achieve new state-of-the-art radar-camera 3D detection results. Our implementation is available at https://github.com/liyih/RCTrans.

cs.CV↗

arXiv2024

Evidence for the Sombrero Galaxy as an Accelerator of the Highest-Energy Cosmic Rays

Ultrahigh-energy cosmic rays (UHECRs) are the highest energy messenger from space, with energies exceeding 1 EeV. Although UHECRs were discovered over 60 years ago, their origin still remains a mystery. Pinpointing sources of UHECRs is crucial for understanding the extreme astrophysical processes that accelerate particles to such extraordinary energies. We searched for UHECR multiplets via analyzing 17 years of data with energies greater than 40 EeV from the Pierre Auger Observatory. A spatial association is found between a multiplet of $25.7^{+6.2}_{-7.0}$ cosmic rays and the Sombrero galaxy with a local (global) significance of $4.5~σ~(3.3~σ)$. The Sombrero galaxy hosts a supermassive central black hole with a mass of $\sim1\times 10^9 M_{\odot}$ and exhibits large-scale radio lobes and jets. Our finding provides critical evidence on active supermassive black holes as the source of the highest-energy cosmic rays.

astro-ph.HE↗

arXiv2024

Rapid Reconstruction of Extremely Accelerated Liver 4D MRI via Chained Iterative Refinement

Abstract Purpose: High-quality 4D MRI requires an impractically long scanning time for dense k-space signal acquisition covering all respiratory phases. Accelerated sparse sampling followed by reconstruction enhancement is desired but often results in degraded image quality and long reconstruction time. We hereby propose the chained iterative reconstruction network (CIRNet) for efficient sparse-sampling reconstruction while maintaining clinically deployable quality. Methods: CIRNet adopts the denoising diffusion probabilistic framework to condition the image reconstruction through a stochastic iterative denoising process. During training, a forward Markovian diffusion process is designed to gradually add Gaussian noise to the densely sampled ground truth (GT), while CIRNet is optimized to iteratively reverse the Markovian process from the forward outputs. At the inference stage, CIRNet performs the reverse process solely to recover signals from noise, conditioned upon the undersampled input. CIRNet processed the 4D data (3D+t) as temporal slices (2D+t). The proposed framework is evaluated on a data cohort consisting of 48 patients (12332 temporal slices) who underwent free-breathing liver 4D MRI. 3-, 6-, 10-, 20- and 30-times acceleration were examined with a retrospective random undersampling scheme. Compressed sensing (CS) reconstruction with a spatiotemporal constraint and a recently proposed deep network, Re-Con-GAN, are selected as baselines. Results: CIRNet consistently achieved superior performance compared to CS and Re-Con-GAN. The inference time of CIRNet, CS, and Re-Con-GAN are 11s, 120s, and 0.15s. Conclusion: A novel framework, CIRNet, is presented. CIRNet maintains useable image quality for acceleration up to 30 times, significantly reducing the burden of 4DMRI.

eess.IV↗

arXiv2024

Domain-Pair Intertwined Topological Domain Structure in Elemental Bi Monolayer

Ferroelectric domain structures, separated by domain walls, often display unconventional physics and hold significant potential for applications in nano-devices. Most naturally growth domain walls are charge-neutral to avoid increased electrostatic energy, while the intrinsically stable charged 180° domain walls in Bi monolayer challenged this conventional knowledge and emerged an unexplored field. Here, using machine-learning potential and molecular dynamics (MD) simulations, we investigated the finite-temperature dynamics of domain walls and discovered a domain-pair intertwined topological domain structure in Bi monolayer. In 180° domain walls, a unique polarization switching mechanism is observed, characterized by the out-of-plane shuffle of Bi atoms without bond breaking. This shuffle mechanism reverses the charge properties of Bi atoms, transforming Bi anions into cations and vice versa, ultimately reversing the polarization. Then, we observed a topological multi-domain structure with two groups of domain pairs intertwined. The charged 180° domain walls form local domain pairs, with the 90° domain walls emerge between different domain pairs. This multi-domain maintains a stable topological structure within the strain range (ε_x = 0 to 4.70%) and exhibits rich domain wall reactions under further applied strain. Our findings provide insights into the charged 180° domain walls and the related topological domain structures, enabling new opportunities for applications in electronic and nano-electronic devices.

cond-mat.mtrl-sci↗

arXiv2024

Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation

Vision-language retrieval aims to search for similar instances in one modality based on queries from another modality. The primary objective is to learn cross-modal matching representations in a latent common space. Actually, the assumption underlying cross-modal matching is modal balance, where each modality contains sufficient information to represent the others. However, noise interference and modality insufficiency often lead to modal imbalance, making it a common phenomenon in practice. The impact of imbalance on retrieval performance remains an open question. In this paper, we first demonstrate that ultimate cross-modal matching is generally sub-optimal for cross-modal retrieval when imbalanced modalities exist. The structure of instances in the common space is inherently influenced when facing imbalanced modalities, posing a challenge to cross-modal similarity measurement. To address this issue, we emphasize the importance of meaningful structure-preserved matching. Accordingly, we propose a simple yet effective method to rebalance cross-modal matching by learning structure-preserved matching representations. Specifically, we design a novel multi-granularity cross-modal matching that incorporates structure-aware distillation alongside the cross-modal matching loss. While the cross-modal matching loss constraints instance-level matching, the structure-aware distillation further regularizes the geometric consistency between learned matching representations and intra-modal representations through the developed relational matching. Extensive experiments on different datasets affirm the superior cross-modal retrieval performance of our approach, simultaneously enhancing single-modal retrieval capabilities compared to the baseline models.

cs.CV↗

arXiv2024

Complex orders and chirality in the classical Kitaev-$Γ$ model

It is well-recognized that the low-energy physics of many Kitaev materials is governed by two dominant energy scales, the Ising-like Kitaev coupling $K$ and the symmetric off-diagonal $Γ$ coupling. An understanding of the interplay between these two scales is therefore the natural starting point toward a quantitative description that includes sub-dominant perturbations that are inevitably present in real materials. The present study focuses on the classical $K$-$Γ$ model on the honeycomb lattice, with a specific emphasis on the region $K<0$ and $Γ>0$, which is the most relevant for the available materials and which remains enigmatic in both quantum and classical limits, despite much effort. We employ large-scale Monte Carlo simulations on specially designed finite-size clusters and unravel the presence of a complex multi-sublattice magnetic orders in a wide region of the phase diagram, whose structure is characterized in detail. We show that this order can be quantified in terms of a coarse-grained scalar-chirality order, featuring a counter-rotating modulation on the two spin sublattices. We also provide a comparison to previous studies and discuss the impact of quantum fluctuations on the phase diagram.

cond-mat.str-el↗