Xu Bo
YOU?
Author Swipe
View article: Skeletons Matter: Dynamic Data Augmentation for Text-to-Query
Skeletons Matter: Dynamic Data Augmentation for Text-to-Query Open
The task of translating natural language questions into query languages has long been a central focus in semantic parsing. Recent advancements in Large Language Models (LLMs) have significantly accelerated progress in this field. However, …
View article: MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration Open
Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level s…
View article: MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration Open
Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level s…
View article: MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration Open
Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level s…
View article: Figure 4 from: Fu C-L, Zhou J-N, Liao W-H, Zhang T, Xu B, Li M (2025) Balanophora xinfeniae (Balanophoraceae), a new species from Xizang, China. PhytoKeys 266: 241-252. https://doi.org/10.3897/phytokeys.266.147400
Figure 4 from: Fu C-L, Zhou J-N, Liao W-H, Zhang T, Xu B, Li M (2025) Balanophora xinfeniae (Balanophoraceae), a new species from Xizang, China. PhytoKeys 266: 241-252. https://doi.org/10.3897/phytokeys.266.147400 Open
Figure 4 Line illustration of Balanophora xinfeniae. A. Male individual; B. Male flower; C. Female individual; D. Female flowers surrounding one claviform body. Drawn by Zi-Heng Yu based on YLZB11691-A and YLZB11691-B specimens stored in C…
View article: Balanophora xinfeniae C. L. Fu, M. Li & B. Xu 2025, sp. nov.
Balanophora xinfeniae C. L. Fu, M. Li & B. Xu 2025, sp. nov. Open
Balanophora xinfeniae C. L. Fu, M. Li & B. Xu sp. nov. Figs 3, 4 Type. China • Xizang Autonomous Region: Motuo County (Mêdog), Gelin Village, 29.210161, 95.191856, alt. 1650 m, 29 Apr 2024 (fl.), Meng Li, C. L. Fu & J. N. Zhou YLZB 11691 -…
View article: Balanophora xinfeniae C. L. Fu, M. Li & B. Xu 2025, sp. nov.
Balanophora xinfeniae C. L. Fu, M. Li & B. Xu 2025, sp. nov. Open
Balanophora xinfeniae C. L. Fu, M. Li & B. Xu sp. nov.Figs 3, 4Type.China • Xizang Autonomous Region: Motuo County (Mêdog), Gelin Village, 29.210161, 95.191856, alt. 1650 m, 29 Apr 2024 (fl.), Meng Li, C. L. Fu & J. N. Zho…
View article: Figure 1 from: Fu C-L, Zhou J-N, Liao W-H, Zhang T, Xu B, Li M (2025) Balanophora xinfeniae (Balanophoraceae), a new species from Xizang, China. PhytoKeys 266: 241-252. https://doi.org/10.3897/phytokeys.266.147400
Figure 1 from: Fu C-L, Zhou J-N, Liao W-H, Zhang T, Xu B, Li M (2025) Balanophora xinfeniae (Balanophoraceae), a new species from Xizang, China. PhytoKeys 266: 241-252. https://doi.org/10.3897/phytokeys.266.147400 Open
Figure 1 The cladogram of Balanophora constructed using maximum likelihood (left) and Bayesian inference (right) based on ITS sequences. Numbers at nodes indicate posterior probabilities (PP) or bootstrap percentages (BS). Branches highlig…
View article: Figure 5 from: Fu C-L, Zhou J-N, Liao W-H, Zhang T, Xu B, Li M (2025) Balanophora xinfeniae (Balanophoraceae), a new species from Xizang, China. PhytoKeys 266: 241-252. https://doi.org/10.3897/phytokeys.266.147400
Figure 5 from: Fu C-L, Zhou J-N, Liao W-H, Zhang T, Xu B, Li M (2025) Balanophora xinfeniae (Balanophoraceae), a new species from Xizang, China. PhytoKeys 266: 241-252. https://doi.org/10.3897/phytokeys.266.147400 Open
Figure 5 Distribution of Balanophora xinfeniae (Balanophoraceae).
View article: Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition
Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition Open
Automatic speech recognition (ASR) systems have achieved remarkable performance in common conditions but often struggle to leverage long-context information in contextualized scenarios that require domain-specific knowledge, such as confer…
View article: Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition
Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition Open
Automatic speech recognition (ASR) systems have achieved remarkable performance in common conditions but often struggle to leverage long-context information in contextualized scenarios that require domain-specific knowledge, such as confer…
View article: Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition
Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition Open
Automatic speech recognition (ASR) systems have achieved remarkable performance in common conditions but often struggle to leverage long-context information in contextualized scenarios that require domain-specific knowledge, such as confer…
View article: MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios
MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios Open
Model-based reinforcement learning (MBRL) is a crucial approach to enhance the generalization capabilities and improve the sample efficiency of RL algorithms. However, current MBRL methods focus primarily on building world models for singl…
View article: TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks
TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks Open
While Vision Language Models (VLMs) have demonstrated remarkable capabilities in general visual understanding, their application in the chemical domain has been limited, with previous works predominantly focusing on text and thus overlooki…
View article: MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios
MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios Open
Model-based reinforcement learning (MBRL) is a crucial approach to enhance the generalization capabilities and improve the sample efficiency of RL algorithms. However, current MBRL methods focus primarily on building world models for singl…
View article: TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks
TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks Open
While Vision Language Models (VLMs) have demonstrated remarkable capabilities in general visual understanding, their application in the chemical domain has been limited, with previous works predominantly focusing on text and thus overlooki…
View article: MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios
MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios Open
Model-based reinforcement learning (MBRL) is a crucial approach to enhance the generalization capabilities and improve the sample efficiency of RL algorithms. However, current MBRL methods focus primarily on building world models for singl…
View article: 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos Open
Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3…
View article: 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos Open
Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3…
View article: 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos Open
Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3…
View article: Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning
Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning Open
This dataset supports the study “Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning”It includes (1) the numerical dataset of bridge and seismic hazard parameters, toge…
View article: Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning
Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning Open
This dataset supports the study “Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning”It includes (1) the numerical dataset of bridge and seismic hazard paramet…
View article: Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL
Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL Open
Text-to-SQL is the task of translating natural language questions into SQL queries based on relational databases. Different databases implement their own SQL dialects, leading to variations in syntax. As a result, SQL queries designed for …
View article: Skeletons Matter: Dynamic Data Augmentation for Text-to-Query
Skeletons Matter: Dynamic Data Augmentation for Text-to-Query Open
The task of translating natural language questions into query languages has long been a central focus in semantic parsing. Recent advancements in Large Language Models (LLMs) have significantly accelerated progress in this field. However, …
View article: Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall
Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall Open
Function calling enables large language models (LLMs) to interact with external systems by leveraging tools and APIs. When faced with multi-step tool usage, LLMs still struggle with tool selection, parameter generation, and tool-chain plan…
View article: Coarse-to-Fine Grounded Memory for LLM Agent Planning
Coarse-to-Fine Grounded Memory for LLM Agent Planning Open
Recent advancements in Large Language Models (LLMs) have driven growing interest in LLM-based agents for complex planning tasks. To avoid costly agent training, many studies adopted memory mechanism that enhances LLM with offline experienc…
View article: Ultrahigh-Q chalcogenide micro-racetrack resonators
Ultrahigh-Q chalcogenide micro-racetrack resonators Open
High-quality factor microresonators are an attractive platform for the study of nonlinear photonics, with diverse applications in communications, sensing, and quantum metrology. The characterization of loss mechanisms and nonlinear propert…
View article: An Efficient Data-Driven Framework for Linear Quadratic Output Feedback Control
An Efficient Data-Driven Framework for Linear Quadratic Output Feedback Control Open
Linear quadratic regulator with unmeasurable states and unknown system matrix parameters better aligns with practical scenarios. However, for this problem, balancing the optimality of the resulting controller and the leniency of the algori…
View article: Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall
Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall Open
Function calling enables large language models (LLMs) to interact with external systems by leveraging tools and APIs. When faced with multi-step tool usage, LLMs still struggle with tool selection, parameter generation, and tool-chain plan…
View article: xDeepServe: Model-as-a-Service on Huawei CloudMatrix384
xDeepServe: Model-as-a-Service on Huawei CloudMatrix384 Open
The rise of scaled-out LLMs and scaled-up SuperPods signals a new era in large-scale AI infrastructure. LLMs continue to scale out via MoE, as seen in recent models like DeepSeek, Kimi, and Qwen. In parallel, AI hardware is scaling up, wit…