Liang Yao

Dr. Liang Yao


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
29 January 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Fan LiuFan Liu
Fan Liu
WDWenwen Dai
Wenwen Dai
CZChuanyi Zhang
Chuanyi Zhang
JZJiale Zhu
Jiale Zhu
LYLiang Yao
Liang Yao
XLXin Li
Xin Li
Large vision language models (LVLMs) are built upon large language models (LLMs) and incorporate non-textual modalities; they can perform various multimodal tasks. Applying LVLMs in remote sensing (RS) visual question answering (VQA) tasks can take advantage of the powerful capabilities to promote the development of VQA in RS. However, due to the greater complexity of remote sensing images compared to natural images, general-domain LVLMs tend to perform poorly in RS scenarios and are prone to hallucination phenomena. Multi-agent debate for collaborative reasoning is commonly utilized to mitigate hallucination phenomena. Although this method is effective, it comes with a significant computational burden (e.g., high CPU/GPU demands and slow inference speed). To address these limitations, we propose Co-LLaVA, a model specifically designed for RS VQA tasks. Specifically, Co-LLaVA employs model collaboration between Large Language and Vision Assistant (LLaVA-v1.5) and Contrastive Captioners (CoCas). It combines LVLM with a lightweight generative model, reducing computational burden compared to multi-agent debate. Additionally, through high-dimensional multi-scale features and higher-resolution images, Co-LLaVA can enhance the perception of details in RS images. Experimental results demonstrate the significant performance improvements of our Co-LLaVA over existing LVLMs (e.g., Geochat, RSGPT) on multiple metrics of four RS VQA datasets (e.g., +3% over SkySenseGPT on “Rural/Urban” accuracy in the test set of RSVQA-LR dataset).


19 December 2024 in arXiv
Verified
Preprint
Open access
PDF file
GZGuangwenjie Zou
Guangwenjie Zou
LYLiang Yao
Liang Yao
Fan LiuFan Liu
Fan Liu
CZChuanyi Zhang
Chuanyi Zhang
XLXin Li
Xin Li
JZJun Zhou
Jun Zhou
Since high resolution remote sensing image classification often requires a relatively high computation complexity, lightweight models tend to be practical and efficient. Model pruning is an effective method for model compression. However, existing methods rarely take into account the specificity of remote sensing images, resulting in significant accuracy loss after pruning. To this end, we propose an effective structural pruning approach for remote sensing image classification. Specifically, a pruning strategy that amplifies the differences in channel importance of the model is introduced. Then an adaptive mining loss function is designed for the fine-tuning process of the pruned model. Finally, we conducted experiments on two remote sensing classification datasets. The experimental results demonstrate that our method achieves minimal accuracy loss after compressing remote sensing classification models, achieving state-of-the-art (SoTA) performance.

19 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
HLHongbo Lu
Hongbo Lu
LYLiang Yao
Liang Yao
CHChenghao He
Chenghao He
HHHao Han
Hao Han
Fan LiuFan Liu
Fan Liu
PPPai Peng
Pai Peng
World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagination budget to every scene. We propose RISE (Refining Imagination through SElective Rollout), a system-level adaptive imagination framework that makes sequential ROLL/STOP decisions according to the expected planning benefit of continued rollout. At each step, a Latent Evaluator estimates the risk revealed by the current prefix and how much planning could improve if imagination continues, while a Rollout Gate weighs this expected benefit against additional computation cost. Since factual driving logs expose only one realized future, we further construct CounterDrive, a counterfactual dataset with diverse outcomes and risk levels, to enrich future dynamics and provide localized risk supervision. Each retained sample undergoes expert verification and annotation of trajectory validity, incident onset, and causal category, providing a reusable resource for safety-critical world-modeling research. Experiments on NAVSIM and nuScenes show that RISE achieves the best overall planning performance while reducing unnecessary rollout, with additional transfer results supporting its plug-in generality across WAM architectures.

8 February 2025
Verified
Book Chapter
Closed access
PDF file
SXShengxiang Xu
Shengxiang Xu
LYLiang Yao
Liang Yao
CHChenyu Huang
Chenyu Huang
GJGuoxin Jiang
Guoxin Jiang
Fan LiuFan Liu
Fan Liu