Bin Fang

AAAI Conference 2026 Conference Paper

STOLA: Self-Adaptive Touch-Language Framework for Tactile Commonsense Reasoning in Open-Ended Scenarios

• Ning Cheng
• Jinan Xu
• Jialing Chen
• Bin Fang
• Wenjuan Han

This paper explores the challenges of integrating tactile sensing into intelligent systems for multimodal reasoning, particularly in enabling commonsense reasoning about the open-ended physical world. We identify two key challenges: modality discrepancy, where existing touch-language models often treat touch as a mere sub-modality of language without further addressing the semantic differences, and open-ended tactile data scarcity, where current datasets lack the diversity, open-endedness, and complexity needed for reasoning. To overcome these challenges, we introduce SToLa, a Self-Adaptive Touch-Language framework. SToLa utilizes Mixture of Experts (MoE) to dynamically process, unify, and manage tactile and language modalities, capturing their unique characteristics. Crucially, we also present a comprehensive tactile commonsense reasoning dataset and benchmark featuring free-form questions and responses, 8 physical properties, 4 interactive characteristics, and diverse commonsense knowledge. Experiments show SToLa exhibits competitive performance compared to existing models on the PHYSICLEAR benchmark and self-constructed datasets, proving the effectiveness of the Mixture of Experts architecture in multimodal management and the performance advantages for open-scenario tactile commonsense reasoning tasks.

EAAI Journal 2026 Journal Article

Symmetric Positive Definite manifold deep metric learning for bearing fault diagnosis

• Junshi Cheng
• Ruisheng Ran
• Bin Fang
• Benchao Li

Rolling bearings are essential components in rotating machinery, and their failures can lead to unplanned downtime, substantial economic losses, and even severe safety risks. Consequently, bearing fault diagnosis has become a crucial task in modern industry, with machine learning methods playing a central role. However, many existing methods are designed in Euclidean space, limiting their ability to capture nonlinear features in bearing signals Additionally, they often have excessive parameters and irrelevant features, making it difficult to learn the correct data distribution. To address these challenges, this paper proposes a Symmetric Positive Definite (SPD) manifold deep metric learning method for bearing fault diagnosis, based on a supervised learning. This method transforms the original data into a SPD manifold, and constructs a SPD sparse denoising autoencoder for feature extraction. And then, a multi-class N -pair loss term on SPD manifold is used to improve classification ability. Comprehensive experiments have shown that this method has strong robustness to noise and low computational complexity. Due to the nonlinear expression ability of SPD manifolds, this method improves classification accuracy and is superior to existing methods in Euclidean space.

IROS Conference 2025 Conference Paper

A Bionic Robotic Hand Designed with Multiple Grasping Modes and Magnetic-tactile Perception

• Shixian Wang
• Shaobo Yang
• Junfeng Wang
• Boao Li
• Fuchun Sun
• Junxia Yan
• Bin Fang

This paper presents a novel multi-mode bionic robotic hand. Its bionic finger (BIF) ingeniously combines a magnetic-silica-gel skin with a rigid skeletal framework and integrates a vacuum suction cup at the fingertip. This design enables the bionic manipulator to execute multiple grasping modes, namely enveloping, parallel, and suction grasping. The proposed BIF emulates the skeletal structure of human fingers and equips the fingertip with suction-based grasping functionality, thus achieving both formal bionics and functional superiority. The overall grasping space range of the bionic manipulator can be determined through the computation of the offset of the steel wire, which corresponds to the bending angles of the three joints of the finger. Furthermore, by discerning the four phases within the bionic manipulator’s object-grasping process, in-depth exploration is carried out regarding the unique data characteristics of the magnetic-tactile sensing unit during the grasping operation. On this basis, an accurate prediction of the grasped object’s diameter is achieved. We constructed an autonomous grasping operation platform by integrating an external depth camera with the robotic arm to assess the fundamental performance of this robotic hand in grasping diverse objects.

JBHI Journal 2025 Journal Article

Personalized Lumbar Vertebrae Modeling for Dynamic Assessment of Idiopathic Scoliosis

• Chengyin Wang
• Jianfeng Li
• Shuo Wang
• Yuxuan Wang
• Jianguo Zhang
• Mingjie Dong
• Bin Fang
• Qianyu Zhuang

Clinical assessment of idiopathic scoliosis (IS) patients primarily relies on static imaging techniques. Dynamic digital human (DDH) can provide comprehensive spatio-temporal information for dynamic assessment of the deformed spine in IS patients comparing with static imaging techniques, such as X-ray for general assessment and computed tomography (CT) for surgical planning. The lumbar vertebrae exhibit greater morphological variability than the thoracic region when subjected to different postures and mechanical loads, making them particularly important for dynamic assessment. Therefore, a personalized lumbar vertebrae model (PLVM) is proposed in this work to simulate lumbar vertebrae motion for IS patients; furthermore, an individualized DDH (i-DDH) is proposed by embedding PLVM into DDH to capture the spatio-temporal information. First, we use a bone primitive generation method to construct the DDH by incorporating Neural Radiance Fields (NeRF) and three-dimensional (3D) Gaussian splatting methods. Next, we develop the PLVM generation method to simulate lumbar vertebrae motion under different loads and postures. Finally, the bone primitives and PLVM are merged to generate the i-DDH for dynamic assessment. We validated i-DDH using multi-posture radiographs from eight IS patients awaiting surgery. The results demonstrate high accuracy compared to state-of-the-art (SOTA) models, with a mean angular error of $0. 96^\circ$ and a maximum error of $3. 6^\circ$ relative to radiographs. The proposed i-DDH framework is able to capture the spinal posture and conduct the dynamic assessment of IS patients rather than fixed positions. It overcomes the soft tissue artifact (STA) problem from motion capture systems and the failure to generate 3D spinal deformity of IS patients by training healthy subjects from computer vision methods. It also shows great clinical significance for preoperative planning and clinical assessment by providing dynamic spinal posture that cannot be achieved with static imaging.

EAAI Journal 2025 Journal Article

Thermal behavior prediction of the spindle-bearing system based on the adaptive thermal network modeling method

• Ziquan Zhan
• Shaoke Wan
• Xiaohu Li
• Bin Fang

Differences in comprehension of the heat transfer mechanism in spindle-bearing systems result in diverse thermal network modeling approaches. This leads to variations in simulation results of thermal prediction. To eliminate this epistemic uncertainty and determine the optimal thermal network model for the spindle-bearing system under various operating conditions, this study proposes an adaptive modeling method. Firstly, common thermal network models based on different mechanistic understandings are briefly introduced. Next, a convolutional neural network (CNN) surrogate model based on incremental learning is proposed to accurately approximate numerous thermal networks with limited simulations. Furthermore, considering that the spindle-bearing system comprises a multi-support structure, the grey relational analysis is utilized to mitigate the interaction effects of different support bearings on thermal characteristic analysis. Moreover, based on the CNN surrogate model, a two-step optimization method is proposed to obtain a thermal network model which balances accuracy and structural simplicity. Finally, the effectiveness and accuracy of the optimal thermal network model are validated through the thermal characteristic experiments of the spindle system under various operating conditions.

ICRA Conference 2023 Conference Paper

ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions

• Anjun Chen
• Xiangyu Wang
• Kun Shi 0003
• Shaohao Zhu
• Bin Fang
• Yingfeng Chen
• Jiming Chen 0001
• Yuchi Huo

3D human reconstruction from RGB images achieves decent results in good weather conditions but degrades dramatically in rough weather. Complementary, mmWave radars have been employed to reconstruct 3D human joints and meshes in rough weather. However, combining RGB and mmWave signals for robust all-weather 3D human reconstruction is still an open challenge, given the sparse nature of mmWave and the vulnerability of RGB images. In this paper, we present ImmFusion, the first mmWave-RGB fusion solution to reconstruct 3D human bodies in all weather conditions robustly. Specifically, our ImmFusion consists of image and point backbones for token feature extraction and a Transformer module for token fusion. The image and point backbones refine global and local features from original data, and the Fusion Transformer Module aims for effective information fusion of two modalities by dynamically selecting informative tokens. Extensive experiments on a large-scale dataset, mmBody, captured in various environments demonstrate that ImmFusion can efficiently utilize the information of two modalities to achieve a robust 3D human body reconstruction in all weather conditions. In addition, our method's accuracy is significantly superior to that of state-of-the-art Transformer-based LiDAR-camera fusion methods.

AAAI Conference 2021 Conference Paper

Empirical Regularization for Synthetic Sentence Pairs in Unsupervised Neural Machine Translation

• Xi Ai
• Bin Fang

UNMT tackles translation on monolingual corpora in two required languages. Since there is no explicitly cross-lingual signal, pre-training and synthetic sentence pairs are significant to the success of UNMT. In this work, we empirically study the core training procedure of UNMT to analyze the synthetic sentence pairs obtained from back-translation. We introduce new losses to UNMT to regularize the synthetic sentence pairs by training the UNMT objective and the regularization objective jointly. Our comprehensive experiments support that our method can generally improve the performance of currently successful models on three similar pairs {French, German, Romanian} ↔ English and one dissimilar pair Russian ↔ English with acceptably additional cost.

AAAI Conference 2020 Conference Paper

Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance

• Mingxuan Jing
• Xiaojian Ma
• Wenbing Huang
• Fuchun Sun
• Chao Yang
• Bin Fang
• Huaping Liu

In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect and sufficient, which yet is unrealistic to meet in practice. To work on imperfect demonstrations, we first define an imperfect expert setting for RLfD in a formal way, and then point out that previous methods suffer from two issues in terms of optimality and convergence, respectively. Upon the theoretical findings we have derived, we tackle these two issues by regarding the expert guidance as a soft constraint on regulating the policy exploration of the agent, which eventually leads to a constrained optimization problem. We further demonstrate that such problem is able to be addressed efficiently by performing a local linear search on its dual form. Considerable empirical evaluations on a comprehensive collection of benchmarks indicate our method attains consistent improvement over other RLfD counterparts.

AAAI Conference 2010 Conference Paper

A Computational Model for Saliency Maps by Using Local Entropy

• Yuewei Lin
• Bin Fang
• Yuanyan Tang

This paper presents a computational framework for saliency maps. It employs the Earth Mover's Distance based on weighted-Histogram (EMD-wH) to measure the centersurround difference, instead of the Difference-of-Gaussian (DoG) filter used by traditional models. In addition, the model employs not only the traditional features such as colors, intensity and orientation but also the local entropy which expresses the local complexity. The major advantage of combining the local entropy map is that it can detect the salient regions which are not complex regions. Also, it uses a general framework to integrate the feature dimensions instead of summing the features directly. This model considers both local and global salient information, in contrast to the existing models that consider only one or the other. Furthermore, the "large scale bias" and "central bias" hypotheses are used in this model to select the fixation locations in the saliency map of different scales. The performance of this model is assessed by comparing their saliency maps and human fixation density. The results from this model are finally compared to those from other bottomup models for reference.

IROS Conference 1988 Conference Paper

Control of Robot Manipulators under Repetitive Tasks -Segmented Repetitive Control Approach

• Masayoshi Tomizuka
• George Anwar
• Bin Fang