12 papers
Counterfactual Benchmarking and Training for Factuality Consistency and Order-Robust Grounded Reasoning in LLMs over Heterogeneous Knowledge
Shibo Chu, Yuze Liu, Tiehua Zhang +4
Large language models (LLMs) have increasingly supported response generation grounded in user-provided knowledge spanning heterogeneous structures. However, existing benchmarks pro…
A RAG-Enhanced Bi-Level Cognitive Orchestration Framework for LEO Satellite Networks
Yuhong Jiang, Zhishu Shen, Tong Yin +4
The rapid growth of remote sensing data in Low Earth Orbit (LEO) satellite networks is increasingly constrained by limited downlink capacity to terrestrial networks. Satellite edge…
Meta-Modal Agent: Sequential Evidence Routing for Missing-Modality Candidate Reranking
Jinze Wang, Yangchen Zeng, Tiehua Zhang +5
Missing modalities cause severe failures in multimodal recommender systems. User histories, item text, and visual evidence are frequently absent during cold-start scenarios, exactl…
ML-ECS: A Collaborative Multimodal Learning Framework for Edge-Cloud Synergies
Yuze Liu, Shibo Chu, Tiehua Zhang +5
Edge-cloud synergies provide a promising paradigm for privacy-preserving deployment of foundation models, where lightweight on-device models adapt to domain-specific data and cloud…
Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
Jinze Wang, Lu Zhang, Yiyang Cui +5
Next point-of-interest (POI) recommendation is a key component of smart urban services, yet it remains challenging under cold-start conditions with sparse user-POI interactions. Re…
A Structure-Agnostic Co-Tuning Framework for LLMs and SLMs in Cloud-Edge Systems
Yuze Liu, Yunhan Wang, Tiehua Zhang +5
The surge in intelligent applications driven by large language models (LLMs) has made it increasingly difficult for bandwidth-limited cloud servers to process extensive LLM workloa…