16 papers
BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates
Lijian Li, Yuanpeng He, Yudian Zheng +6
Feed-forward transformer models have driven remarkable progress in 3D vision,yet their quadratic complexity renders them impractical for long video sequences. Streaming 3D reconstr…
World Requirement Model: Learning Requirement-Change Consequences from Typed Artifact Graphs
Yuanpeng He, Lijian Li, Dongming Jin +7
Requirement changes can affect connected stakeholders, constraints, components, and tests. We present World Requirement Model (WRM), which encodes this engineering context as a typ…
TreeProbe : A Tibetan Medicine Benchmark for Cultural Bias in LLMs
Jin Zhang, Linyu Li, Weili Jiang +7
Large language models are increasingly viewed as a potential means of mitigating global health inequities, yet their outputs often reflect dominant high-resource medical traditions…
Knowledge before Reasoning: EC-Reason-Bench, a Training-Free Diagnostic Benchmark for LLM Enzyme Classification
Linyu Li, Zhi Jin, Yichi Zhang +6
Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: general LLMs often get the coarse…
From Chat to Interview: Agentic Requirements Elicitation with an Experience Ontology
Dongming Jin, Zhi Jin, Yaotian Yang +5
Requirements elicitation interviews are crucial and time-consuming in requirements engineering, but heavily rely on the experience of requirements analysts. Although recent advance…
SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
Xingyan Liu, Xiyue Luo, Linyu Li +3
Deploying LLM-powered agents in enterprise scenarios such as cloud technical support demands high-quality, domain-specific skills. However, existing skill creators lack domain grou…
When Modalities Remember: Continual Learning for Multimodal Knowledge Graphs
Linyu Li, Zhi Jin, Yichi Zhang +5
Real-world multimodal knowledge graphs (MMKGs) are dynamic, with new entities, relations, and multimodal knowledge emerging over time. Existing continual knowledge graph reasoning…
ReqElicitGym: An Evaluation Environment for Interview Competence in Conversational Requirements Elicitation
Dongming Jin, Zhi Jin, Zheng Fang +4
With the rapid improvement of LLMs' coding capabilities, the bottleneck of LLM-based automated software development is shifting from generating correct code to eliciting users' req…
A Needle in a Haystack: Intent-driven Reusable Artifacts Recommendation with LLMs
Dongming Jin, Zhi Jin, Xiaohong Chen +6
In open source software development, the reuse of existing artifacts has been widely adopted to avoid redundant implementation work. Reusable artifacts are considered more efficien…
Automated Concern Extraction from Textual Requirements of Cyber-Physical Systems: A Multi-solution Study
Dongming Jin, Zhi Jin, Xiaohong Chen +5
Cyber-physical systems (CPSs) are characterized by a deep integration of the information space and the physical world, which makes the extraction of requirements concerns more chal…
UserTrace: User-Level Requirements Generation and Traceability Recovery from Software Project Repositories
Dongming Jin, Zhi Jin, Yiran Zhang +5
Software maintainability critically depends on high-quality requirements descriptions and explicit traceability between requirements and code. Although automated code summarization…
A System Model Generation Benchmark from Natural Language Requirements
Dongming Jin, Zhi Jin, Linyu Li +3
System models, a critical artifact in software development, provide a formal abstraction of both the structural and behavioral aspects of software systems, which can facilitate the…
Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding
Linyu Li, Zhi Jin, Yuanpeng He +6
As social media and the World Wide Web become hubs for information dissemination, effectively organizing and understanding the vast amounts of dynamically evolving Web content is c…
A Conceptual Framework for Requirements Engineering of Pretrained-Model-Enabled Systems
Dongming Jin, Zhi Jin, Linyu Li +1
Recent advances in large pretrained models have led to their widespread integration as core components in modern software systems. The trend is expected to continue in the foreseea…
Automatic Multi-level Feature Tree Construction for Domain-Specific Reusable Artifacts Management
Dongming Jin, Zhi Jin, Nianyu Li +3
With the rapid growth of open-source ecosystems (e.g., Linux) and domain-specific software projects (e.g., aerospace), efficient management of reusable artifacts is becoming increa…
RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models
Jin Zhang, Fan Gao, Linyu Li +4
The rise of large language models has led to significant performance breakthroughs in named entity recognition (NER) for high-resource languages, yet there remains substantial room…