arXiv subjects

Yunzhi Xu

Publications and source records attributed to Yunzhi Xu.

7 recordsLinked to original sources

arXiv2026

Vision-Force Admittance Learning for Peg Insertion into a Movable Hole

Precise manipulation in dynamic environments, whether induced by a mobile robot base or a target with unknown motion, remains a major challenge in robotics. Manipulation in dynamic environments introduces substantial uncertainty, which fundamentally conflicts with the tight precision requirement of precise tasks such as peg-in-the-hole. We propose a Vision-Force Admittance Learning (VFAL) framework that fuses asynchronous visual feedback with a high-frequency force-based model, using visual pose estimations as a regularization term. VFAL adapts insertion strategies online to dynamic motion while maintaining millimeter-level precision. To obtain robust, low-frequency pose information, we employ state-of-the-art vision foundation models for visual pose estimation. Additionally, we incorporate failure recovery mechanisms to enhance overall robustness. We validate our approach in real-world experiments, demonstrating high success rates and strong adaptability to various pegs and dynamic environments.

cs.RO↗

arXiv2026

Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

We present Nanbeige4.1-3B, a unified generalist language model that simultaneously achieves strong agentic behavior, code generation, and general reasoning with only 3B parameters. To the best of our knowledge, it is the first open-source small language model (SLM) to achieve such versatility in a single model. To improve reasoning and preference alignment, we combine point-wise and pair-wise reward modeling, ensuring high-quality, human-aligned responses. For code generation, we design complexity-aware rewards in Reinforcement Learning, optimizing both correctness and efficiency. In deep search, we perform complex data synthesis and incorporate turn-level supervision during training. This enables stable long-horizon tool interactions, allowing Nanbeige4.1-3B to reliably execute up to 600 tool-call turns for complex problem-solving. Extensive experimental results show that Nanbeige4.1-3B significantly outperforms prior models of similar scale, such as Nanbeige4-3B-2511 and Qwen3-4B, even achieving superior performance compared to much larger models, such as Qwen3-30B-A3B. Our results demonstrate that small models can achieve both broad competence and strong specialization simultaneously, redefining the potential of 3B parameter models.

cs.AI↗

arXiv2025

HyKid: An Open MRI Dataset with Expert-Annotated Multi-Structure and Choroid Plexus in Pediatric Hydrocephalus

Evaluation of hydrocephalus in children is challenging, and the related research is limited by a lack of publicly available, expert-annotated datasets, particularly those with segmentation of the choroid plexus. To address this, we present HyKid, an open-source dataset from 48 pediatric patients with hydrocephalus. 3D MRIs were provided with 1mm isotropic resolution, which was reconstructed from routine low-resolution images using a slice-to-volume algorithm. Manually corrected segmentations of brain tissues, including white matter, grey matter, lateral ventricle, external CSF, and the choroid plexus, were provided by an experienced neurologist. Additionally, structured data was extracted from clinical radiology reports using a Retrieval-Augmented Generation framework. The strong correlation between choroid plexus volume and total CSF volume provided a potential biomarker for hydrocephalus evaluation, achieving excellent performance in a predictive model (AUC = 0.87). The proposed HyKid dataset provided a high-quality benchmark for neuroimaging algorithms development, and it revealed the choroid plexus-related features in hydrocephalus assessments. Our datasets are publicly available at https://www.synapse.org/Synapse:syn68544889.

cs.CV↗

arXiv2025

Nanomechanics and Pore Structure of Sodium and Potassium Geopolymer Gels: Experiments, Molecular Dynamics and Coarse-Grained Simulations

The link between composition, microstructure and mechanics of NASH and KASH gels is elusive, even in pure metakaolin-based geopolymers. This article exploits molecular mechanics, coarse-grained nanomechanics and micromechanics, to interpret new experimental results from microscopy, porosimetry and nanoindentation. KASH displays a finer nanogranular structure than NASH (3 vs 30 nm particle diameters, 5 vs 50 nm average pore diameters), higher skeletal density (2.3 vs 2.02 g/cm$^3$), nanoindentation moduli (9.21 vs 7.5 GPa) and hardness (0.56 vs 0.37 GPa) despite a higher total porosity (0.48-0.53 vs 0.38). This suggests a stiffer and stronger solid skeleton for KASH, confirmed through predictive molecular dynamics simulations on recent and new models of NASH and KASH. The atomistic simulations inform mechanical interactions for new, coarse-grained, particle-based models of NASH and KASH. The resulting simulations predict the nanoindentation result that KASH is stiffer than equally porous NASH and the impact of formation eigenstresses on elastic moduli.

cond-mat.mtrl-sci↗

arXiv2025

MiniMax-01: Scaling Foundation Models with Lightning Attention

We introduce MiniMax-01 series, including MiniMax-Text-01 and MiniMax-VL-01, which are comparable to top-tier models while offering superior capabilities in processing longer contexts. The core lies in lightning attention and its efficient scaling. To maximize computational capacity, we integrate it with Mixture of Experts (MoE), creating a model with 32 experts and 456 billion total parameters, of which 45.9 billion are activated for each token. We develop an optimized parallel strategy and highly efficient computation-communication overlap techniques for MoE and lightning attention. This approach enables us to conduct efficient training and inference on models with hundreds of billions of parameters across contexts spanning millions of tokens. The context window of MiniMax-Text-01 can reach up to 1 million tokens during training and extrapolate to 4 million tokens during inference at an affordable cost. Our vision-language model, MiniMax-VL-01 is built through continued training with 512 billion vision-language tokens. Experiments on both standard and in-house benchmarks show that our models match the performance of state-of-the-art models like GPT-4o and Claude-3.5-Sonnet while offering 20-32 times longer context window. We publicly release MiniMax-01 at https://github.com/MiniMax-AI.

cs.CL↗

arXiv2022

Fetal Brain Tissue Annotation and Segmentation Challenge Results

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, brainstem, deep grey matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

eess.IV↗

arXiv2021

Fabrication of Fiber-Reinforced Polymer Ceramic Composites by Wet Electrospinning

We propose a novel approach of wet electrospinning to yield fiber-reinforced polymer ceramic composites, where a reactive ceramic precursor gel is used as a collector. We illustrate our approach by generating polyethylene oxide (PEO) fibers in a potassium silicate gel; the gel is later activated using metakaolin to yield a ceramic-0.5 wt% PEO fiber composite. An increase of 29% and 22% is recorded for the fabricated polymer ceramic composites in terms of indentation modulus and indentation hardness respectively. Our initial findings demonstrate the process viability and might lead to a potentially scalable manufacturing approach for fiber-reinforced polymer ceramic composites.

cond-mat.soft↗