3 citations · 5 across the 6 of their papers we have counts for
7 papers
SAGE: A Statistical Acceptance Gate for Self-Evolving Agents
Yihao Wang, Linhan Xia, Rui Liu +6
Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and decision logic. This loop h…
LoCA: Forward-Only LLM Tuning after One-Shot Calibration with Local Credit Assignment
Linhan Xia, Rui Liu, Zhaofeng Zhang +3
Parameter-efficient post-training reduces the number of trainable parameters, but still requires repeated end-to-end backpropagation through the frozen backbone. Every adaptation s…
Mamba4Net: Distilled Hybrid Mamba Large Language Models For Networking
Linhan Xia, Mingzhan Yang, Jingjing Wang +4
Transformer-based large language models (LLMs) are increasingly being adopted in networking research to address domain-specific challenges. However, their quadratic time complexity…
PolyBERT: Fine-Tuned Poly Encoder BERT-Based Model for Word Sense Disambiguation
Linhan Xia, Mingzhan Yang, Guohui Yuan +4
Mainstream Word Sense Disambiguation (WSD) approaches have employed BERT to extract semantics from both context and definitions of senses to determine the most suitable sense of a…
Quantification and Validation for Degree of Understanding in M2M Semantic Communications
Linhan Xia, Jiaxin Cai, Ricky Yuen-Tan Hou +1
With the development of Artificial Intelligence (AI) and Internet of Things (IoT) technologies, network communications based on the Shannon-Nyquist theorem gradually reveal their l…
Movie Recommendation with Poster Attention via Multi-modal Transformer Feature Fusion
Linhan Xia, Yicheng Yang, Ziou Chen +2
Pre-trained models learn general representations from large datsets which can be fine-turned for specific tasks to significantly reduce training time. Pre-trained models like gener…
Depth Estimation Algorithm Based on Transformer-Encoder and Feature Fusion
Linhan Xia, Junbang Liu, Tong Wu
This research presents a novel depth estimation algorithm based on a Transformer-encoder architecture, tailored for the NYU and KITTI Depth Dataset. This research adopts a transfor…