arXiv subjects

Yiming Ji

Publications and source records attributed to Yiming Ji.

8 recordsLinked to original sources

arXiv2026

PDD-RRG: Posterior Diagnostic Decision for Study-level Radiology Report Generation

Automatic radiology report generation (RRG) aims to simulate the workflow of radiologists, assisting them in clinical diagnosis. However, existing methods often fall short in utilizing all information relevant to the examination, as is typically done in clinical practice. Although some works attempt to incorporate multi-view images and historical data, these additional inputs may sometimes lead to avoidable diagnostic errors on the contrary. To address these challenges, we introduce a decision-making stage after report generation for the first time and propose a Posterior Diagnostic Decision framework (PDD-RRG) to integrate potentially conflicting diagnoses. Specifically, we create various subsets of input data and utilize an existing RRG model to generate reports from different perspectives. Then the Bayesian posterior probability and the learned thresholds for each clinical observation are calculated to obtain an aggregated diagnostic conclusion, which is subsequently used to refine the generated report. Experiments on MIMIC-CXR demonstrate that our proposed PDD-RRG can effectively enhance the clinical efficacy of existing RRG models without any retraining.

cs.CV↗

arXiv2025

Magnetically Responsive Microprintable Soft Nanocomposites with Tunable Nanoparticle Loading

Magnetic remote actuation of soft materials is attractive for applications such as transforming materials and medical robots. However, due to manufacturing limitations, microscale magnetoactive devices are scarce -- light-based additive manufacturing methods, despite achieving microscale resolution, struggle with particle-induced light scattering. Moreover, large hard-magnetic microparticles restrict ultimate feature sizes, and deformation of soft-magnetic nanoparticle composites requires impractically high loading and field gradients. Among successfully fabricated microscale soft-magnetic composites, limited control over particle loading, distribution, and matrix-phase stiffness has hindered their functionality. Here, we combine two-photon polymerization with iron oxide nanoparticle coprecipitation to fabricate 3D-printed microscale nanocomposites with spatially tunable nanoparticle distribution. We control nanoparticle content by locally modulating the two-photon dose, imbuing parts with varied magnetic functionality and achieving millimeter-scale elastic deformations, demonstrated by a soft robotic gripper and a bistable bit register and sensor. Our approach enables precise control of mechanical and magnetic properties towards microscale metamaterial and robotics applications.

cond-mat.soft↗

arXiv2025

Mars Traversability Prediction: A Multi-modal Self-supervised Approach for Costmap Generation

We present a robust multi-modal framework for predicting traversability costmaps for planetary rovers. Our model fuses camera and LiDAR data to produce a bird's-eye-view (BEV) terrain costmap, trained self-supervised using IMU-derived labels. Key updates include a DINOv3-based image encoder, FiLM-based sensor fusion, and an optimization loss combining Huber and smoothness terms. Experimental ablations (removing image color, occluding inputs, adding noise) show only minor changes in MAE/MSE (e.g. MAE increases from ~0.0775 to 0.0915 when LiDAR is sparsified), indicating that geometry dominates the learned cost and the model is highly robust. We attribute the small performance differences to the IMU labeling primarily reflecting terrain geometry rather than semantics and to limited data diversity. Unlike prior work claiming large gains, we emphasize our contributions: (1) a high-fidelity, reproducible simulation environment; (2) a self-supervised IMU-based labeling pipeline; and (3) a strong multi-modal BEV costmap prediction model. We discuss limitations and future work such as domain generalization and dataset expansion.

cs.CV↗

arXiv2025

Ecological Cycle Optimizer: A novel nature-inspired metaheuristic algorithm for non-convex global optimization

This article proposes the Ecological Cycle Optimizer (ECO), a novel metaheuristic algorithm inspired by energy flow and material cycling within ecosystems. ECO draws an analogy between the dynamic process of solving optimization problems and ecological cycling. Unique update strategies are designed for the producer, consumer and decomposer, aiming to enhance the balance between exploration and exploitation processes. Through these strategies, ECO is able to approach the global optimum, simulating the evolution of an ecological system toward its optimal state of stability and balance. Moreover, a parameter sensitivity analysis is conducted on 23 classic optimization functions to determine a suitable default configuration for ECO. Furthermore, 30 competitive metaheuristic algorithms are selected to form an algorithm pool, and comprehensive experiments are conducted on the IEEE CEC-2014 and CEC-2017 test suites. Among these, five top-performing algorithms, namely ARO, CFOA, CSA, WSO, and INFO, are chosen for an in-depth comparison with the ECO on the IEEE CEC-2020 test suite, verifying the ECO's exceptional optimization performance. Finally, in order to validate the practical applicability of ECO in complex real-world engineering problems, five state-of-the-art algorithms, including FDB-AGDE, FDB-SFS, LRFDB-COA, L-SHADE, and NSM-SFS are selected for comparative experiments on five engineering problems from the CEC-2020-RW test suite, demonstrating that ECO achieves competitive performance against advanced engineering-oriented algorithms. The ECO project page is available at https://jxxsteven7.github.io/ECO-Optimizer/.

cs.NE↗

arXiv2024

Neural-Network-Driven Reward Prediction as a Heuristic: Advancing Q-Learning for Mobile Robot Path Planning

Q-learning is a widely used reinforcement learning technique for solving path planning problems. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Although many studies have reported the effectiveness of Q-learning, it still faces slow convergence issues in practical applications. To address this issue, we propose the NDR-QL method, which utilizes neural network outputs as heuristic information to accelerate the convergence process of Q-learning. Specifically, we improved the dual-output neural network model by introducing a start-end channel separation mechanism and enhancing the feature fusion process. After training, the proposed NDR model can output a narrowly focused optimal probability distribution, referred to as the guideline, and a broadly distributed suboptimal distribution, referred to as the region. Subsequently, based on the guideline prediction, we calculate the continuous reward function for the Q-learning method, and based on the region prediction, we initialize the Q-table with a bias. We conducted training, validation, and path planning simulation experiments on public datasets. The results indicate that the NDR model outperforms previous methods by up to 5\% in prediction accuracy. Furthermore, the proposed NDR-QL method improves the convergence speed of the baseline Q-learning method by 90\% and also surpasses the previously improved Q-learning methods in path quality metrics.

cs.RO↗

arXiv2024

Diffusion as Reasoning: Enhancing Object Navigation via Diffusion Model Conditioned on LLM-based Object-Room Knowledge

The Object Navigation (ObjectNav) task aims to guide an agent to locate target objects in unseen environments using partial observations. Prior approaches have employed location prediction paradigms to achieve long-term goal reasoning, yet these methods often struggle to effectively integrate contextual relation reasoning. Alternatively, map completion-based paradigms predict long-term goals by generating semantic maps of unexplored areas. However, existing methods in this category fail to fully leverage known environmental information, resulting in suboptimal map quality that requires further improvement. In this work, we propose a novel approach to enhancing the ObjectNav task, by training a diffusion model to learn the statistical distribution patterns of objects in semantic maps, and using the map of the explored regions during navigation as the condition to generate the map of the unknown regions, thereby realizing the long-term goal reasoning of the target object, i.e., diffusion as reasoning (DAR). Meanwhile, we propose the Room Guidance method, which leverages commonsense knowledge derived from large language models (LLMs) to guide the diffusion model in generating room-aware object distributions. Based on the generated map in the unknown region, the agent sets the predicted location of the target as the goal and moves towards it. Experiments on Gibson and MP3D show the effectiveness of our method.

cs.CV↗

arXiv2024

NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting

We propose NEDS-SLAM, a dense semantic SLAM system based on 3D Gaussian representation, that enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in real-time. In the system, we propose a Spatially Consistent Feature Fusion model to reduce the effect of erroneous estimates from pre-trained segmentation head on semantic reconstruction, achieving robust 3D semantic Gaussian mapping. Additionally, we employ a lightweight encoder-decoder to compress the high-dimensional semantic features into a compact 3D Gaussian representation, mitigating the burden of excessive memory consumption. Furthermore, we leverage the advantage of 3D Gaussian splatting, which enables efficient and differentiable novel view rendering, and propose a Virtual Camera View Pruning method to eliminate outlier gaussians, thereby effectively enhancing the quality of scene representations. Our NEDS-SLAM method demonstrates competitive performance over existing dense semantic SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in 3D dense semantic mapping.

cs.CV↗

arXiv2024

NNPP: A Learning-Based Heuristic Model for Accelerating Optimal Path Planning on Uneven Terrain

Intelligent autonomous path planning is essential for enhancing the exploration efficiency of mobile robots operating in uneven terrains like planetary surfaces and off-road environments.In this paper, we propose the NNPP model for computing the heuristic region, enabling foundation algorithms like Astar to find the optimal path solely within this reduced search space, effectively decreasing the search time. The NNPP model learns semantic information about start and goal locations, as well as map representations, from numerous pre-annotated optimal path demonstrations, and produces a probabilistic distribution over each pixel representing the likelihood of it belonging to an optimal path on the map. More specifically, the paper computes the traversal cost for each grid cell from the slope, roughness and elevation difference obtained from the digital elevation model. Subsequently, the start and goal locations are encoded using a Gaussian distribution and different location encoding parameters are analyzed for their effect on model performance. After training, the NNPP model is able to \textcolor{revision}{accelerate} path planning on novel maps.

cs.RO↗