arXiv subjects

Changjin Li

Publications and source records attributed to Changjin Li.

4 recordsLinked to original sources

arXiv2026

AtomBridge: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments

Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent vision-language-action (VLA) models offer a promising foundation for robotic laboratories. However, scientific experiments typically involve long-horizon tasks composed of multiple atomic tasks. Existing VLA models may fail to perform composed tasks formed by reordering and composing these known atomic actions. This limitation can arise from a skill-chaining gap caused by robot-state mismatch: the terminal robot state of one skill can fall outside the valid initial-state distribution of the next. To address this challenge, we propose AtomBridge, an Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments. AtomBridge attaches at inference time to a VLA policy already fine-tuned on atomic tasks, while keeping its weights fixed. At each task boundary, it uses LLM-based transition reasoning and robotic-action code generation to insert transitional actions between consecutive tasks. This plug-and-play design mitigates the skill-chaining gap caused by robot-state mismatch without additional VLA fine-tuning or demonstrations of composed long-horizon sequences. Across scientific manipulation sequences in simulation and a real-world experimental environment, AtomBridge improves execution continuity and per-step atomic-task success. On 8-step composed tasks, AtomBridge improves full-sequence success by 10%~25%.

cs.RO↗

arXiv2025

LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models

The rapid advancement of large language models (LLMs) has not been matched by their evaluation in low-resource languages, especially Southeast Asian languages like Lao. To fill this gap, we introduce \textbf{LaoBench}, the first large-scale, high-quality, and multidimensional benchmark for assessing LLM language understanding and reasoning in Lao. LaoBench contains \textbf{17,000+} expert-curated samples across three dimensions: culturally grounded knowledge application, curriculum-aligned K12 education, and bilingual translation among Lao, Chinese, and English. It includes open-source and held-out subsets, where the held-out portion enables secure black-box evaluation via a controlled service to improve fairness and data security. We construct LaoBench with a hybrid pipeline that combines expert authoring with agent-assisted verification, ensuring linguistic accuracy, cultural relevance, and educational validity. We evaluate diverse state-of-the-art open-source and closed-source LLMs, and find that even strong multilingual models lag behind human experts, particularly in culturally grounded reasoning and translation fidelity. We hope LaoBench will catalyze research on Lao and other underrepresented Southeast Asian languages for more inclusive multilingual evaluation.

cs.CL↗

arXiv2023

PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated Images

As image generation technology advances, AI-based image generation has been applied in various fields and Artificial Intelligence Generated Content (AIGC) has garnered widespread attention. However, the development of AI-based image generative models also brings new problems and challenges. A significant challenge is that AI-generated images (AIGI) may exhibit unique distortions compared to natural images, and not all generated images meet the requirements of the real world. Therefore, it is of great significance to evaluate AIGIs more comprehensively. Although previous work has established several human perception-based AIGC image quality assessment (AIGCIQA) databases for text-generated images, the AI image generation technology includes scenarios like text-to-image and image-to-image, and assessing only the images generated by text-to-image models is insufficient. To address this issue, we establish a human perception-based image-to-image AIGCIQA database, named PKU-I2IQA. We conduct a well-organized subjective experiment to collect quality labels for AIGIs and then conduct a comprehensive analysis of the PKU-I2IQA database. Furthermore, we have proposed two benchmark models: NR-AIGCIQA based on the no-reference image quality assessment method and FR-AIGCIQA based on the full-reference image quality assessment method. Finally, leveraging this database, we conduct benchmark experiments and compare the performance of the proposed benchmark models. The PKU-I2IQA database and benchmarks will be released to facilitate future research on \url{https://github.com/jiquan123/I2IQA}.

cs.CV↗

arXiv2023

Deep Learning Methods for Real-time Detection and Analysis of Wagner Ulcer Classification System

At present, the ubiquity method to diagnose the severity of diabetic feet (DF) depends on professional podiatrists. However, in most cases, professional podiatrists have a heavy workload, especially in underdeveloped and developing countries and regions, and there are often insufficient podiatrists to meet the rapidly growing treatment needs of DF patients. It is necessary to develop a medical system that assists in diagnosing DF in order to reduce part of the workload for podiatrists and to provide timely relevant information to patients with DF. In this paper, we have developed a system that can classify and locate Wagner ulcers of diabetic foot in real-time. First, we proposed a dataset of 2688 diabetic feet with annotations. Then, in order to enable the system to detect diabetic foot ulcers in real time and accurately, this paper is based on the YOLOv3 algorithm coupled with image fusion, label smoothing, and variant learning rate mode technologies to improve the robustness and predictive accuracy of the original algorithm. Finally, the refinements on YOLOv3 was used as the optimal algorithm in this paper to deploy into Android smartphone to predict the classes and localization of the diabetic foot with real-time. The experimental results validate that the improved YOLOv3 algorithm achieves a mAP of 91.95%, and meets the needs of real-time detection and analysis of diabetic foot Wagner Ulcer on mobile devices, such as smart phones. This work has the potential to lead to a paradigm shift for clinical treatment of the DF in the future, to provide an effective healthcare solution for DF tissue analysis and healing status.

cs.CV↗