24 papers indexed
Wenda Yu, Tianshi Wang, Fengling Li, Xin Li, Jingjing Li, Lei Zhu
Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions. We introduce ActFovea, a plug-and-play safeguard…
Xin Li, Zhitong Li, Yexin Ji, Yuanyuan Yan, Xiaoqin Chen, Linlin Gao, et al.
Aim: To develop and internally evaluate machine learning (ML) models for predicting incident cardiovascular-kidney-metabolic (CKM) multimorbidity in Chinese adults with overweight or obesity, and to identify key predictors. Methods: We included 4,244 participants from the China H…
Xiang Chen, Hao Li, Jiangxin Dong, Jinshan Pan, Xin Li, Hongbo Ding, et al.
This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provides a common be…
Ruixin Li, Qiang Liu, Xu Han, Xin Li
Offshore wind farms are rapidly expanding into deeper and more remote ocean regions. Their structural safety and operational reliability in harsh marine environments have garnered widespread global attention. Sensing technologies capture structural and environmental conditions an…
Xin Li, Siyuan Duan, Shang Wang, Zhimin Mao, Bingliang Hu, Geng Zhang
Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, acquisition-time and imaging-platform differences between UAV and reference imagery induce substantial cross-domain appearance and viewpo…
Yushan Yashengjiang, Jie Zhang, Miao Sun, Huadong Liang, Xin Li, Zhen-hua Ling
Auditory attention decoding (AAD) identifies the speaker a listener attends to from neural responses like electroencephalography (EEG), making it a key algorithm in neuro-steered hearing aids. However, most neural AAD models are trained as independent short-window classifiers, de…
Kehan Li, Bohan Hou, Minghao Zhu, Tianyi Zhang, Zesen Cheng, Zhikai Wang, et al.
We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, RynnBrain 1.1 supports embodied perception, spatial reasoning, localization, and planning. Compared wi…
We design and analyze \underline{M}echanism-\underline{E}nforced \underline{S}equential \underline{HA}lving (MESHA), an algorithm for Best Arm Identification (BAI) in strategic linear bandits. In this setting, each arm may strategically misreport its feature vector to maximize th…
Xin Li, Juergen Branke, Xuan Vinh Doan
Data-driven optimization often requires collecting data to estimate uncertain model parameters before solving the underlying decision problem. In practice, however, data acquisition may incur non-negligible costs, making it critical to determine when to stop additional data colle…
Linhui Xiao, Guiping Cao, Mingyue Guo, Xianchao Guan, Fan Yang, Ming Tao, et al.
The rapid expansion of large-scale AI models has led to significant performance breakthroughs across diverse domains, yet it has also raised critical concerns regarding computational costs, energy consumption, and environmental sustainability. This survey provides a comprehensive…
Xin Li, Jiaju Han, Ma Yaqi, Chengyin Hu, Yingying Zhao, Jiahuan Long, et al.
Infrared vision-language models are increasingly used for perception under low-light and adverse visual conditions, yet their robustness to localized structured perturbations remains underexplored. Existing infrared adversarial studies mainly focus on object detectors, leaving th…
Haoyu Zhao, Xingyue Zhao, Hangyu Li, Biao Gong, Kehan Li, Siteng Huang, et al.
Scaling robot learning requires massive, diverse trajectory data, yet collection is currently bottlenecked by physical teleoperation, where every demonstration binds operator time to specific hardware and workspaces. We introduce digital teleoperation, a paradigm that decouples d…
Jiaju Han, Ma Yaqi, Yahui Chai, Xuemeng Sun, Xin Li, Qike Zhang, et al.
Infrared remote-sensing imagery captures intensity structure, object-background contrast, and illumination-invariant cues often invisible in RGB imagery. Yet, most remote-sensing vision-language resources and models focus on visible-band semantics, leaving infrared vision-languag…
Haoyu Zhao, Xingyue Zhao, Siteng Huang, Xin Li, Deli Zhao, Zhongyu Li
Robotic manipulation in the open world requires not only recognizing what a scene looks like, but also anticipating how its 3D structure moves under interaction. We argue that synchronized RGB, depth, and optical flow, namely RGB-DF, provide a physically grounded representation t…
Shiming Yu, Leming Shen, Jianing Zhang, Xin Li, Xianjin Xia, Yuanqing Zheng, et al.
The Open Radio Access Network (O-RAN) promises unprecedented flexibility through its reconfigurable architecture and AI-driven control. However, this agility exposes a critical fragility: AI models trained on one network configuration suffer significant performance degradation af…
Zihao Guo, Xin Li, Zhihong Xia
Convection-dominated convection-diffusion problems often develop thin layers, where the solution has sharp transition profiles and its derivatives are highly localized. This creates a structural mismatch for standard physics-informed neural networks (PINNs), whose trial spaces ar…
Yi Pan, Miao Pan, Qi Lu, Jiaming Huang, Man Zhang, Siteng Huang, et al.
Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence. To reduce policy-call frequency while preserving temporal coherence, most generative policies adopt an action chunk mechanism, executing multiple future actions in an o…
Xun Dong, Yibo Xu, Naigang Wang, Xin Li, Penghang Yin, Zi Yang
Zeroth-order (ZO) optimization enables fine-tuning large language models when backpropagation is unavailable or memory-prohibitive, but existing methods often perturb full model weights or randomly constructed low-dimensional subspaces, yielding high-variance estimates and limite…
Xin Li, Wenhui Zhu, Xuanzhao Dong, Xiwen Chen, Yanxi Chen, Yujian Xiong, et al.
Medical image segmentation is dominated by U-Net-style encoder-decoder architectures. Vision Transformers (ViTs) overcome the limited receptive field of convolutional networks through self-attention, enabling modeling of long-range dependencies. Early ViT-based segmentation metho…
Sen Liang, Cong Wang, Zhentao Yu, Fengbin Guan, Zhengguang Zhou, Teng Hu, et al.
Existing instruction-based video editing datasets commonly focus on single-task appearance editing, failing to meet the complex creative demands of real-world scenarios. To bridge this gap, we present Goku, a large-scale dataset featuring 2 million high-quality, instruction-align…
Zhaoqi Wang, Zijian Zhang, Kun Zheng, Zhen Li, Xin Li, Chunlei Li, et al.
The rapid spread of fake news poses increasing threats to information ecosystems, especially as AI-generated misinformation under Generative Engine Optimization (GEO) poisoning allows adversarially crafted content to be systematically surfaced by retrieval systems, contaminating…
Anushiya Arunan, Xin Li, Yan Qin, U-Xuan Tan, Nhu Khue Vuong, Xiaoli Li, et al.
Multimodal industrial anomaly inspection assistants are a critical component of next-generation smart factories, enabling interactive vision-language-based querying. However, multimodal large language models remain impractical for on-site deployment due to prohibitive computation…
Ron Campos, Subhajit Maity, Xin Li, Srijan Das, Aritra Dutta
The softmax activation in multihead attention (MHA) is the de facto standard for attention-based models in visual perception tasks. However, standard softmax can produce noisy attention patterns that dilute relevant features and degrade its performance. In this paper, we propose…