185 citations · 186 across the 6 of their papers we have counts for
11 papers
Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
Qianli Ma, Zhiqing Tang, Fanshuai Meng +3
Small language models deployed under cost, latency, or privacy constraints cannot simply switch to larger models when reasoning fails. Multi-candidate generate-then-rerank offers a…
Lower Bounds for Smooth Nonconvex Zeroth-Order Optimization: The Price of Determinism under Low Curvature Trace
Yuxing Peng, Zhiqing Tang, Weijia Jia
Low curvature trace, an effective rank condition, is a common explanation for why randomized zeroth-order methods scale to high-dimensional tasks such as language model fine-tuning…
MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
Hanshuai Cui, Zhiqing Tang, Zhi Yao +3
Persistent memory lets long-running large language model agents reuse information across sessions and tasks. Yet errors in writable memory can persist and corrupt future behavior.…
LASER: Load-Aware Serving with Early-Exit for Reasoning LLMs at the Edge
Zhiqing Tang, Size Li, Hanshuai Cui +5
Large reasoning models (LRMs) such as DeepSeek-R1 have achieved strong performance through extended chain-of-thought (CoT) generation. However, deploying them on edge devices raise…
ConCise: Training-Free Conclusion-Chain State Compression for Cost-Efficient Multi-Step RAG Services
Kuan Yan, Zhiqing Tang, Tian Wang +1
Multi-step retrieval-augmented generation (RAG) has been widely deployed as LLM-powered web services for complex question answering, where iterative retrieval-reasoning rounds deli…
CogGuard: Cognitive and Operational Profiling for Proactive Warning in Edge Intelligent Services
Zhi Yao, Weihao Chen, Zhiqing Tang +4
Proactive warning is an important capability for edge intelligent services, where the system predicts whether a subject will successfully complete an incoming task under strict lat…
CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation
Xuedong Hu, Zhiqing Tang, Zhi Yao +2
Retrieval-augmented generation (RAG) has emerged as a pivotal technique for improving language models by incorporating external knowledge at inference time. As device-cloud collabo…
Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching
Qianli Ma, Zhiqing Tang, Hanshuai Cui +2
Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (…
Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
Xubin Wang, Zhiqing Tang, Jianxiong Guo +4
The rapid advancement of artificial intelligence (AI) technologies has led to an increasing deployment of AI models on edge and terminal devices, driven by the proliferation of the…
Joint Optimization of Prompt Security and System Performance in Edge-Cloud LLM Systems
Haiyang Huang, Tianhui Meng, Weijia Jia
Large language models (LLMs) have significantly facilitated human life, and prompt engineering has improved the efficiency of these models. However, recent years have witnessed a r…
Brainstorming Brings Power to Large Language Models of Knowledge Reasoning
Zining Qin, Chenhao Wang, Huiling Qin +1
Large Language Models (LLMs) have demonstrated amazing capabilities in language generation, text comprehension, and knowledge reasoning. While a single powerful model can already h…