QZ
Qinggang Zhang
cs.CLcs.AIcs.DBcs.LGcs.IRcs.CVcs.MAcs.MMcs.NE
On Valency
published · living versionsW_ejmzpge7·v1 · currentpublished
EvoMemState: Evolving Memory State for Personal Agents
with Zhishang Xiang, Yunbo Tang, Zhongqiao Liu, Junkai Chen +5
1 version
W_4fxtemgq·v1published
Preprints & journals
33 papers in the corpus · 2022–2026Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift2608.29543v1 · Yujia Liu, Jiayan Lin, Zijin Hong et al.2026 · 0 citationsarXiv
Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL2608.28432v1 · Jiayan Lin, Yujia Liu, Zijin Hong et al.2026 · 0 citationsarXiv
Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning2608.03123v1 · Zezheng Wu, Xinghe Cheng, Qinggang Zhang et al.2026 · 0 citationsarXiv
Zero-Mem: Zero-Token Memory Operations for LLM Agents2607.29377v1 · Yilin Xiao, Zhehan Zhu, Yujing Zhang et al.2026 · 0 citationsarXiv
HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document2607.24861v1 · Xin He, Yili Wang, Wenqi Fan et al.2026 · 0 citationsarXiv
MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation2606.00610v1 · Chuanjie Wu, Zhishang Xiang, Yunbo Tang et al.2026 · 0 citationsarXiv
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search2605.29796v3 · Yunbo Tang, Chengyi Yang, Shiyu Liu et al.2026 · 0 citationsarXiv
STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillation2605.27409v1 · Shuhan Ye, Yi Yu, Qixin Zhang et al.2026 · 0 citationsarXiv
ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement2603.03742v2 · Zijin Hong, Hao Chen, Zheng Yuan et al.2026 · 1 citationarXiv
Graph-based Agent Memory: Taxonomy, Techniques, and Applications2602.05665v1 · Chang Yang, Chuang Zhou, Yilin Xiao et al.2026 · 0 citationsarXiv
Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs2602.03578v1 · Su Dong, Qinggang Zhang, Yilin Xiao et al.2026 · 0 citationsarXiv
Augmenting Intra-Modal Understanding in MLLMs for Robust Multimodal Keyphrase Generation2512.00928v1 · Jiajun Cao, Qinggang Zhang, Yunbo Tang et al.2025 · 0 citationsarXiv
Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation2510.12460v3 · Linfeng Gao, Qinggang Zhang, Baolong Bi et al.2025 · 0 citationsarXiv
LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora2510.10114v4 · Luyao Zhuang, Shengyuan Chen, Yilin Xiao et al.2025 · 0 citationsarXiv
LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval2508.07690v2 · Luyao Zhuang, Qinggang Zhang, Huachi Zhou et al.2025 · 0 citationsarXiv
You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures2508.06105v2 · Shengyuan Chen, Chuang Zhou, Zheng Yuan et al.2025 · 5 citationsarXiv
LAG: Logic-Augmented Generation from a Cartesian Perspective2508.05509v3 · Yilin Xiao, Chuang Zhou, Yujing Zhang et al.2025 · 1 citationarXiv
Enhancing Large Language Models with Reliable Knowledge Graphs2506.13178v1 · Qinggang Zhang2025 · 0 citationsarXiv
Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs2506.10508v1 · Yilin Xiao, Chuang Zhou, Qinggang Zhang et al.2025 · 4 citationsarXiv
FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation2506.08938v2 · Qinggang Zhang, Zhishang Xiang, Yilin Xiao et al.2025 · 19 citationsarXiv
When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation2506.05690v3 · Zhishang Xiang, Chuanjie Wu, Qinggang Zhang et al.2025 · 4 citationsarXiv
Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs2504.11239v2 · Chang Yang, Ruiyu Wang, Junzhe Jiang et al.2025 · 0 citationsarXiv
Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation2502.12911v3 · Zheng Yuan, Hao Chen, Zijin Hong et al.2025 · 0 citationsarXiv
A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models2501.13958v3 · Qinggang Zhang, Shengyuan Chen, Yuanchen Bei et al.2025 · 14 citationsarXiv
LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed2411.08794v2 · Chang Yang, Xinrun Wang, Junzhe Jiang et al.2024 · 0 citationsarXiv
Neuro-Symbolic Entity Alignment via Variational Inference2410.04153v2 · Shengyuan Chen, Zheng Yuan, Qinggang Zhang et al.2024 · 0 citationsarXiv
Logical Reasoning with Relation Network for Inductive Knowledge Graph Completion2406.01140v2 · Qinggang Zhang, Keyu Duan, Junnan Dong et al.2024 · 15 citationsarXiv
Entity Alignment with Noisy Annotations from Large Language Models2405.16806v2 · Shengyuan Chen, Qinggang Zhang, Junnan Dong et al.2024 · 15 citationsNeurIPS 2024
Cost-efficient Knowledge-based Question Answering with Large Language Models2405.17337v1 · Junnan Dong, Qinggang Zhang, Chuang Zhou et al.2024 · 0 citationsarXiv
Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering2402.12728v2 · Junnan Dong, Qinggang Zhang, Huachi Zhou et al.2024 · 16 citationsarXiv
Structure Guided Large Language Model for SQL Generation2402.13284v4 · Qinggang Zhang, Hao Chen, Junnan Dong et al.2024 · 6 citationsarXiv
Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM2402.11517v3 · Zijin Hong, Zheng Yuan, Hao Chen et al.2024 · 30 citationsarXiv
Contrastive Knowledge Graph Error Detection2211.10030v1 · Qinggang Zhang, Junnan Dong, Keyu Duan et al.2022 · 47 citationsCIKM 2022: Proceedings of the 31st ACM International Conference on Information & Knowledge Management
Career total: 58 works. 33 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.