Jianmin Ji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianmin Ji has a total of 223 co-authors. Here are the top co-authors by number of shared publications:
- Yanyong Zhang
University of Science and Technology of China, Hefei, Anhui, China
37 shared publications - Yu Zhang
University of Science and Technology of China
18 shared publications - Jie Peng
University of Science and Technology of China
7 shared publications Xiaoping Chen
School of Computer Science and Technology, University of Science and Technology of China, China
7 shared publications- Xiaoping Chen
Department of Mathematics, Taizhou University, Taizhou, China
7 shared publications - Yao Li
School of Computer Science and Technology, University of Science and Technology of China (USTC), Hefei, China
7 shared publications
Latest Publications
- Open Access
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 14-27
Needle in a Haystack: Tracking UAVs from Massive Noise in Real-World 5G-A Base Station Data
- 20 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 14-27
Open AccessNeedle in a Haystack: Tracking UAVs from Massive Noise in Real-World 5G-A Base Station Data
- Open Access
Environment-Aware Adaptive Pruning with Interleaved Inference Orchestration for Vision-Language-Action Models
While Vision-Language-Action (VLA) models hold promise in embodied intelligence, their large parameter counts lead to substantial inference latency that hinders real-time manipulation, motivating parameter sparsification. However, as the environment evolves during VLA execution, the optimal sparsity patterns change accordingly. Static pruning lacks the adaptability required for environment dynamics, whereas fixed-interval dynamic layer pruning suffers from coarse granularity and high retraining overheads. To bridge this gap, we propose EcoVLA, a training-free, plug-and-play adaptive pruning framework that supports orthogonal combination with existing VLA acceleration methods. EcoVLA comprises two components: Environment-aware Adaptive Pruning (EAP) and Interleaved Inference Orchestration ($I^2O$). EAP is a lightweight adaptive channel pruning method that incorporates the temporal consistency of the physical environment to update sparsity patterns. $I^2O$ leverages the FLOPs bubbles inherent in VLA inference to schedule the pruning method in parallel, ensuring negligible impact on latency. Evaluated on diverse VLA models and benchmarks, EcoVLA delivers state-of-the-art performance, achieving up to 1.60$\times$ speedup with only a 0.4% drop in success rate, and further reaches 2.18$\times$ speedup with only a 0.5% degradation when combined with token pruning. We further validate the effectiveness of EcoVLA on real-world robots.Open AccessEnvironment-Aware Adaptive Pruning with Interleaved Inference Orchestration for Vision-Language-Action Models
While Vision-Language-Action (VLA) models hold promise in embodied intelligence, their large parameter counts lead to substantial inference latency that hinders real-time manipulation, motivating parameter sparsification. However, as the environment evolves during VLA execution, the optimal sparsity patterns change accordingly. Static pruning lacks the adaptability required for environment dynamics, whereas fixed-interval dynamic layer pruning suffers from coarse granularity and high retraining overheads. To bridge this gap, we propose EcoVLA, a training-free, plug-and-play adaptive pruning framework that supports orthogonal combination with existing VLA acceleration methods. EcoVLA comprises two components: Environment-aware Adaptive Pruning (EAP) and Interleaved Inference Orchestration ($I^2O$). EAP is a lightweight adaptive channel pruning method that incorporates the temporal consistency of the physical environment to update sparsity patterns. $I^2O$ leverages the FLOPs bubbles inherent in VLA inference to schedule the pruning method in parallel, ensuring negligible impact on latency. Evaluated on diverse VLA models and benchmarks, EcoVLA delivers state-of-the-art performance, achieving up to 1.60$\times$ speedup with only a 0.4% drop in success rate, and further reaches 2.18$\times$ speedup with only a 0.5% degradation when combined with token pruning. We further validate the effectiveness of EcoVLA on real-world robots. - 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42, 4417-4436
DynaHMRC: Decentralized Heterogeneous Multirobot Collaboration for Dynamic Tasks With Large Language Models
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 42, 4417-4436
DynaHMRC: Decentralized Heterogeneous Multirobot Collaboration for Dynamic Tasks With Large Language Models
- Open Access
- 2 December 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (4) , 1-28
PocketMap: An Interaction-centric 3D Map Serving System for Spatial Understanding on Mobile Devices
Recently, the rapid advancements of spatially intelligent applications have greatly heightened the demand for context-rich 3D maps on mobile devices. However, existing 3D maps are typically static and interaction-agnostic, making them ill-suited for dynamic user needs, leading to excessive transmission overhead. To address this, we present PocketMap, an interaction-centric 3D map serving system that delivers only the necessary content tailored to each request, considering user intent, environmental context, and available on-device resources. PocketMap adopts a multi-layered, incrementally encoded 3D map representation with varying fidelity levels, enabling adaptive map selection. Leveraging this layered map, we propose a prompt- and context-aware task performance estimator to evaluate the contribution of each map layer. A packet planner then formulates a constrained optimization problem to jointly select appropriate map layers and compression strategies. Together, these components enable on-demand, interaction-aware 3D map serving. We evaluate PocketMap across four environments and four downstream applications: object localization, 3D shape analysis, surface analysis, and image retrieval. User studies show that PocketMap improves user satisfaction by 35.5% compared to the baseline. Extensive evaluations further demonstrate a 45.1% reduction in transmission volume and a 13.7% improvement in task performance compared to the baseline.
- 2 December 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (4) , 1-28
Open AccessPocketMap: An Interaction-centric 3D Map Serving System for Spatial Understanding on Mobile Devices
Recently, the rapid advancements of spatially intelligent applications have greatly heightened the demand for context-rich 3D maps on mobile devices. However, existing 3D maps are typically static and interaction-agnostic, making them ill-suited for dynamic user needs, leading to excessive transmission overhead. To address this, we present PocketMap, an interaction-centric 3D map serving system that delivers only the necessary content tailored to each request, considering user intent, environmental context, and available on-device resources. PocketMap adopts a multi-layered, incrementally encoded 3D map representation with varying fidelity levels, enabling adaptive map selection. Leveraging this layered map, we propose a prompt- and context-aware task performance estimator to evaluate the contribution of each map layer. A packet planner then formulates a constrained optimization problem to jointly select appropriate map layers and compression strategies. Together, these components enable on-demand, interaction-aware 3D map serving. We evaluate PocketMap across four environments and four downstream applications: object localization, 3D shape analysis, surface analysis, and image retrieval. User studies show that PocketMap improves user satisfaction by 35.5% compared to the baseline. Extensive evaluations further demonstrate a 45.1% reduction in transmission volume and a 13.7% improvement in task performance compared to the baseline.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 938-952
UrgenGo: Urgency-Aware Transparent GPU Kernel Launching for Autonomous Driving
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 938-952
Open AccessUrgenGo: Urgency-Aware Transparent GPU Kernel Launching for Autonomous Driving
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 650-666
Ghost Points Matter: Far-Range Vehicle Detection with a Single mmWave Radar in Tunnel
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 650-666
Open AccessGhost Points Matter: Far-Range Vehicle Detection with a Single mmWave Radar in Tunnel
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 13217-13224
A Soft-Rigid Hybrid Robot-Assisted Feeding System With a Tendon-Driven Continuum Robot
Active delivery of food to a human mouth in a controlled and safe manner remains a key challenge for robotassisted feeding systems (RAFSs). Existing RAFS designs struggle to simultaneously achieve efficiency and safety: rigid manipulators offer fast and accurate motion but risk hazardous contact, while soft robots provide passive compliance at the cost of limited speed or workspace. To meet the specific demands of feeding tasks, we design a tendon-driven continuum robot that allows precise orientation control of the utensil while exhibiting strong passive compliance in position. Integrating it with a 6-DoF rigid robot for fast and long-range positioning, we propose a hybrid RAFS architecture that achieves safe, efficient, and accurate food delivery. Controlling a passive-compliant RAFS to acquire various food is nontrivial: physical modeling struggles with complex interactions between soft robot and food, while typical imitation learning methods lead to discontinuous or distorted movements out of the passive deformation. To handle this, we design a pose-torque learning policy that enables the soft and rigid robots to generate coherent and synchronized movements, offering a case-specific solution to the long-standing challenge of soft robot imitation learning. Experiments show that our method achieve a food acquisition success rate of 76.7%, while user tests with 14 volunteers confirm user preference, marking our RAFS as a practical step toward safe and efficient robotic feeding.
- 31 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 13217-13224
A Soft-Rigid Hybrid Robot-Assisted Feeding System With a Tendon-Driven Continuum Robot
Active delivery of food to a human mouth in a controlled and safe manner remains a key challenge for robotassisted feeding systems (RAFSs). Existing RAFS designs struggle to simultaneously achieve efficiency and safety: rigid manipulators offer fast and accurate motion but risk hazardous contact, while soft robots provide passive compliance at the cost of limited speed or workspace. To meet the specific demands of feeding tasks, we design a tendon-driven continuum robot that allows precise orientation control of the utensil while exhibiting strong passive compliance in position. Integrating it with a 6-DoF rigid robot for fast and long-range positioning, we propose a hybrid RAFS architecture that achieves safe, efficient, and accurate food delivery. Controlling a passive-compliant RAFS to acquire various food is nontrivial: physical modeling struggles with complex interactions between soft robot and food, while typical imitation learning methods lead to discontinuous or distorted movements out of the passive deformation. To handle this, we design a pose-torque learning policy that enables the soft and rigid robots to generate coherent and synchronized movements, offering a case-specific solution to the long-standing challenge of soft robot imitation learning. Experiments show that our method achieve a food acquisition success rate of 76.7%, while user tests with 14 volunteers confirm user preference, marking our RAFS as a practical step toward safe and efficient robotic feeding.
- Open Access
Ghost Points Matter: Far-Range Vehicle Detection with a Single mmWave Radar in Tunnel
Vehicle detection in tunnels is crucial for traffic monitoring and accident response, yet remains underexplored. In this paper, we develop mmTunnel, a millimeter-wave radar system that achieves far-range vehicle detection in tunnels. The main challenge here is coping with ghost points caused by multi-path reflections, which lead to severe localization errors and false alarms. Instead of merely removing ghost points, we propose correcting them to true vehicle positions by recovering their signal reflection paths, thus reserving more data points and improving detection performance, even in occlusion scenarios. However, recovering complex 3D reflection paths from limited 2D radar points is highly challenging. To address this problem, we develop a multi-path ray tracing algorithm that leverages the ground plane constraint and identifies the most probable reflection path based on signal path loss and spatial distance. We also introduce a curve-to-plane segmentation method to simplify tunnel surface modeling such that we can significantly reduce the computational delay and achieve real-time processing. We have evaluated mmTunnel with comprehensive experiments. In two test tunnels, we conducted controlled experiments in various scenarios with cars and trucks. Our system achieves an average F1 score of 93.7% for vehicle detection while maintaining real-time processing. Even in the challenging occlusion scenarios, the F1 score remains above 91%. Moreover, we collected extensive data from a public tunnel with heavy traffic at times and show our method could achieve an F1 score of 91.5% in real-world traffic conditions.
Open AccessGhost Points Matter: Far-Range Vehicle Detection with a Single mmWave Radar in Tunnel
Vehicle detection in tunnels is crucial for traffic monitoring and accident response, yet remains underexplored. In this paper, we develop mmTunnel, a millimeter-wave radar system that achieves far-range vehicle detection in tunnels. The main challenge here is coping with ghost points caused by multi-path reflections, which lead to severe localization errors and false alarms. Instead of merely removing ghost points, we propose correcting them to true vehicle positions by recovering their signal reflection paths, thus reserving more data points and improving detection performance, even in occlusion scenarios. However, recovering complex 3D reflection paths from limited 2D radar points is highly challenging. To address this problem, we develop a multi-path ray tracing algorithm that leverages the ground plane constraint and identifies the most probable reflection path based on signal path loss and spatial distance. We also introduce a curve-to-plane segmentation method to simplify tunnel surface modeling such that we can significantly reduce the computational delay and achieve real-time processing. We have evaluated mmTunnel with comprehensive experiments. In two test tunnels, we conducted controlled experiments in various scenarios with cars and trucks. Our system achieves an average F1 score of 93.7% for vehicle detection while maintaining real-time processing. Even in the challenging occlusion scenarios, the F1 score remains above 91%. Moreover, we collected extensive data from a public tunnel with heavy traffic at times and show our method could achieve an F1 score of 91.5% in real-world traffic conditions.