Chaomin Shen

Chaomin Shen

Auto-generated profile, based on publicly available information

Chaomin Shen

East China Normal University

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 February 2025 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JWJunjie Wen
Junjie Wen
YZYichen Zhu
Yichen Zhu
JLJinming Li
Jinming Li
MZMinjie Zhu
Minjie Zhu
ZTZhibin Tang
Zhibin Tang
JTJian Tang
Jian Tang
Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this letter, we introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models: (1) faster inference speeds, and (2) improved data efficiency, eliminating the need for pre-training stage. Our framework incorporates two essential components to build TinyVLA: (1) initializing the policy backbone with robust, high-speed multimodal models, and (2) integrating a diffusion policy decoder during fine-tuning to enable precise robot actions. We conducted extensive evaluations of TinyVLA in both simulation and on real robots, demonstrating that our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance. Additionally, TinyVLA exhibits strong generalization capabilities across various dimensions, including language instructions, novel objects, unseen positions, changes in object appearance, background variations, and environmental shifts, often matching or exceeding the performance of OpenVLA. We believe that TinyVLA offers an interesting perspective on utilizing pre-trained multimodal models for policy learning.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
MZMinjie Zhu
Minjie Zhu
YZYichen Zhu
Yichen Zhu
WZWill Zhang
Will Zhang
XLXin Liu
Xin Liu
ZXZhiyuan Xu
Zhiyuan Xu
YPYaxin Peng
Yaxin Peng
Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inference phases, restricting their use to a limited audience within the research and user communities. In this paper, we investigate the design aspects of Multimodal Small Language Models (MSLMs) and propose an efficient multimodal assistant named Mipha, which is designed to create synergy among various aspects: visual representation, language models, and optimization strategies. We show that without increasing the volume of training data, our Mipha-3B outperforms the state-of-the-art large MLLMs, especially LLaVA-1.5-13B, on multiple benchmarks. Through detailed discussion, we provide insights and guidelines for developing strong MSLMs that rival the capabilities of MLLMs.

2 February 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XDXiaofeng Ding
Xiaofeng Ding
CSChaomin Shen
Chaomin Shen
TZTieyong ZENG
Tieyong ZENG
YPYaxin Peng
Yaxin Peng
Semantic segmentation has achieved great progress by effectively fusing features of contextual information. In this article, we propose an end-to-end semantic attention boosting (SAB) framework to adaptively fuse the contextual information iteratively across layers with semantic regularization. Specifically, we first propose a pixelwise semantic attention (SAP) block, with a semantic metric representing the pixelwise category relationship, to aggregate the nonlocal contextual information. In addition, we improve the computation complexity of SAP block from O(n²) to O(n) for images with size n. Second, we present a categorywise semantic attention (SAC) block to adaptively balance the nonlocal contextual dependencies and the local consistency with a categorywise weight, overcoming the contextual information confusion caused by the feature imbalance within intra-category. Furthermore, we propose the SAB module to refine the segmentation with SAC and SAP blocks. By applying the SAB module iteratively across layers, our model shrinks the semantic gap and enhances the structure reasoning by fully utilizing the coarse segmentation information. Extensive quantitative evaluations demonstrate that our method significantly improves the segmentation results and achieves superior performance on the PASCAL VOC 2012, Cityscapes, PASCAL Context, and ADE20K datasets.

1 September 2007 in Image and Vision Computing
Verified
Journal Article
Closed access
LPLing Pi
Ling Pi
CSChaomin Shen
Chaomin Shen
FLFang Li
Fang Li
JFJinsong Fan
Jinsong Fan

21 September 2006 in Journal of Mathematical Imaging and Vision
Verified
Journal Article
Closed access
PDF file
LPLing Pi
Ling Pi
JFJinsong Fan
Jinsong Fan
CSChaomin Shen
Chaomin Shen

3 December 2012 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
FFFaming Fang
Faming Fang
FLFang Li
Fang Li
GZGuixu Zhang
Guixu Zhang
CSChaomin Shen
Chaomin Shen
With the increasing availability of multisource image data from Earth observation satellites, image fusion, a technique that produces a single image which preserves major salient features from a set of different inputs, has become an important tool in the field of remote sensing since usually the complete information cannot be obtained by a single sensor. In this article, we develop a new pixel-based variational model for image fusion using gradient features. The basic assumption is that the fused image should have a gradient that is close to the most salient gradient in the multisource inputs. Meanwhile, we integrate the inputs with the average quadratic local dispersion measure for the purpose of uniform and natural perception. Furthermore, we introduce a split Bregman algorithm to implement the proposed functional more effectively. To verify the effect of the proposed method, we visually and quantitatively compare it with the conventional image fusion schemes, such as the Laplacian pyramid, morphological pyramid, and geometry-based enhancement fusion methods. The results demonstrate the effectiveness and stability of the proposed method in terms of the related fusion evaluation benchmarks. In particular, the computation efficiency of the proposed method compared with other variational methods also shows that our method is remarkable.