Dingkang Liang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Dingkang Liang has a total of 191 co-authors. Here are the top co-authors by number of shared publications:
- Xiang Bai
Huazhong University of Science and Technology, Wuhan, China
26 shared publications - Dingyuan Zhang
Huazhong University of Science and Technology
4 shared publications Xiang Bai
Huazhong University of Science and Technology
4 shared publicationsBing Wang
Xiaomi EV
3 shared publicationsHongwei Xie
Xiaomi EV
3 shared publicationsWei Hua
School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China
3 shared publications
Latest Publications
- 5 October 2026
- Published by Springer Nature
- p. 511-529
Wat3R: Underwater 3D Geometry Learning Without Annotations
- 5 October 2026
- Published by Springer Nature
- p. 511-529
Wat3R: Underwater 3D Geometry Learning Without Annotations
- Open Access
- 15 September 2026
- Published by Springer Nature
- p. 237-258
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
- 15 September 2026
- Published by Springer Nature
- p. 237-258
Open AccessGeneration Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
- 15 September 2026
- Published by Springer Nature
- p. 80-99
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
- 15 September 2026
- Published by Springer Nature
- p. 80-99
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
- 14 September 2026
- Published by Springer Nature
- p. 314-333
Towards Generalizable Robotic Manipulation in Dynamic Environments
- 14 September 2026
- Published by Springer Nature
- p. 314-333
Towards Generalizable Robotic Manipulation in Dynamic Environments
- 10 September 2026
- Published by Springer Nature
- p. 503-522
MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
- 10 September 2026
- Published by Springer Nature
- p. 503-522
MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
- 9 September 2026
- Published by Springer Nature
- p. 433-451
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
- 9 September 2026
- Published by Springer Nature
- p. 433-451
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 8558-8573
Extending Large Vision–Language Model for Diverse Interactive Tasks in Autonomous Driving
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 8558-8573
Extending Large Vision–Language Model for Diverse Interactive Tasks in Autonomous Driving
- Open Access
Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution
Task scheduling is critical for embodied AI, enabling agents to follow natural language instructions and execute actions efficiently in 3D physical worlds. However, existing datasets often simplify task planning by ignoring operations research (OR) knowledge and 3D spatial grounding. In this work, we propose Operations Research knowledge-based 3D Grounded Task Scheduling (ORS3D), a new task that requires the synergy of language understanding, 3D grounding, and efficiency optimization. Unlike prior settings, ORS3D demands that agents minimize total completion time by leveraging parallelizable subtasks, e.g., cleaning the sink while the microwave operates. To facilitate research on ORS3D, we construct ORS3D-60K, a large-scale dataset comprising 60K composite tasks across 4K real-world scenes. Furthermore, we propose GRANT, an embodied multi-modal large language model equipped with a simple yet effective scheduling token mechanism to generate efficient task schedules and grounded actions. Extensive experiments on ORS3D-60K validate the effectiveness of GRANT across language understanding, 3D grounding, and scheduling efficiency. The code is available at https://github.com/H-EmbodVis/GRANT
Open AccessCook and Clean Together: Teaching Embodied Agents for Parallel Task Execution
Task scheduling is critical for embodied AI, enabling agents to follow natural language instructions and execute actions efficiently in 3D physical worlds. However, existing datasets often simplify task planning by ignoring operations research (OR) knowledge and 3D spatial grounding. In this work, we propose Operations Research knowledge-based 3D Grounded Task Scheduling (ORS3D), a new task that requires the synergy of language understanding, 3D grounding, and efficiency optimization. Unlike prior settings, ORS3D demands that agents minimize total completion time by leveraging parallelizable subtasks, e.g., cleaning the sink while the microwave operates. To facilitate research on ORS3D, we construct ORS3D-60K, a large-scale dataset comprising 60K composite tasks across 4K real-world scenes. Furthermore, we propose GRANT, an embodied multi-modal large language model equipped with a simple yet effective scheduling token mechanism to generate efficient task schedules and grounded actions. Extensive experiments on ORS3D-60K validate the effectiveness of GRANT across language understanding, 3D grounding, and scheduling efficiency. The code is available at https://github.com/H-EmbodVis/GRANT
- Open Access
NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
Underwater exploration offers critical insights into our planet and attracts increasing attention for its broader applications in resource exploration, national security, etc. We study the underwater scene understanding methods, which aim to achieve automated underwater exploration. The underwater scene understanding task demands multi-task perceptions from multiple granularities. However, the absence of large-scale underwater multi-task instruction-tuning datasets hinders the progress of this research. To bridge this gap, we construct NautData, a dataset containing 1.45 M image-text pairs supporting eight underwater scene understanding tasks. It enables the development and thorough evaluation of the underwater scene understanding models. Underwater image degradation is a widely recognized challenge that interferes with underwater tasks. To improve the robustness of underwater scene understanding, we introduce physical priors derived from underwater imaging models and propose a plug-and-play vision feature enhancement (VFE) module, which explicitly restores clear underwater information. We integrate this module into renowned baselines LLaVA-1.5 and Qwen2.5-VL and build our underwater LMM, NAUTILUS. Experiments conducted on the NautData and public underwater datasets demonstrate the effectiveness of the VFE module, consistently improving the performance of both baselines on the majority of supported tasks, thus ensuring the superiority of NAUTILUS in the underwater scene understanding area. Data and models are available at https://github.com/H-EmbodVis/NAUTILUS.
Open AccessNAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
Underwater exploration offers critical insights into our planet and attracts increasing attention for its broader applications in resource exploration, national security, etc. We study the underwater scene understanding methods, which aim to achieve automated underwater exploration. The underwater scene understanding task demands multi-task perceptions from multiple granularities. However, the absence of large-scale underwater multi-task instruction-tuning datasets hinders the progress of this research. To bridge this gap, we construct NautData, a dataset containing 1.45 M image-text pairs supporting eight underwater scene understanding tasks. It enables the development and thorough evaluation of the underwater scene understanding models. Underwater image degradation is a widely recognized challenge that interferes with underwater tasks. To improve the robustness of underwater scene understanding, we introduce physical priors derived from underwater imaging models and propose a plug-and-play vision feature enhancement (VFE) module, which explicitly restores clear underwater information. We integrate this module into renowned baselines LLaVA-1.5 and Qwen2.5-VL and build our underwater LMM, NAUTILUS. Experiments conducted on the NautData and public underwater datasets demonstrate the effectiveness of the VFE module, consistently improving the performance of both baselines on the majority of supported tasks, thus ensuring the superiority of NAUTILUS in the underwater scene understanding area. Data and models are available at https://github.com/H-EmbodVis/NAUTILUS.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9753-9762
DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9753-9762
Open AccessDriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment