18 citations · 40 across the 20 of their papers we have counts for
22 papers
MMKG-R1: Constructing Multimodal Knowledge Graphs via Reinforcement Learning
Zongyu Wu, Yilong Wang, Xiaochen Wang +5
Multimodal knowledge graphs (MMKGs) organize information across different modalities to support multimodal Graph Retrieval-Augmented Generation (RAG), which aims to improve the per…
Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs
Zongyu Wu, Yilong Wang, Xiaochen Wang +5
Retrieval-augmented generation (RAG) is widely used to mitigate hallucination issues in large language models (LLMs) and multimodal large language models (MLLMs). In particular, kn…
Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers
Yu Wang, Shengyao Zhuang, Xueguang Ma +4
A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the right trade-off changes with th…
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
Minhua Lin, Juncheng Wu, Zijun Wang +14
LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing…
Position: Agentic Evolution is the Path to Evolving LLMs
Minhua Lin, Hanqing Lu, Zhan Shi +11
As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with con…
A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
Minhua Lin, Zongyu Wu, Zhichao Xu +6
The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static…
Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
Zhichao Xu, Zongyu Wu, Yun Zhou +9
Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code, recent work has begun training LLMs to dynamically pla…
AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
Fali Wang, Hui Liu, Zhenwei Dai +8
Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily i…
GPR: Empowering Generation with Graph-Pretrained Retriever
Xiaochen Wang, Zongyu Wu, Yuan Zhong +3
Graph retrieval-augmented generation (GRAG) places high demands on graph-specific retrievers. However, existing retrievers often rely on language models pretrained on plain text, l…
Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models
Zongyu Wu, Minhua Lin, Zhiwei Zhang +4
Large vision-language models (LVLMs) have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy…
Bridging Source and Target Domains via Link Prediction for Unsupervised Domain Adaptation on Graphs
Yilong Wang, Tianxiang Zhao, Zongyu Wu +1
Graph neural networks (GNNs) have shown great ability for node classification on graphs. However, the success of GNNs relies on abundant labeled data, while obtaining high-quality…
LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models
Zongyu Wu, Yuwei Niu, Hongcheng Gao +12
Large Vision-Language Models (LVLMs) have shown impressive performance in various tasks. However, LVLMs suffer from hallucination, which hinders their adoption in the real world. E…
A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness
Fali Wang, Zhiwei Zhang, Xianren Zhang +11
Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their profi…
Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
Minhua Lin, Zhengzhang Chen, Yanchi Liu +6
Time series data is ubiquitous across various domains, including manufacturing, finance, and healthcare. High-quality annotations are essential for effectively understanding time s…
Catastrophic Failure of LLM Unlearning via Quantization
Zhiwei Zhang, Fali Wang, Xiaomin Li +6
Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwant…
Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
Minhua Lin, Zhiwei Zhang, Enyan Dai +4
Graph Prompt Learning (GPL) has been introduced as a promising approach that uses prompts to adapt pre-trained GNN models to specific downstream tasks without requiring fine-tuning…
Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions?
Xianren Zhang, Xianfeng Tang, Hui Liu +4
Recent studies show LLMs struggle with complex instructions involving multiple constraints (e.g., length, format, sentiment). Existing works address this issue by fine-tuning, whic…
LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning
Junjie Xu, Zongyu Wu, Minhua Lin +2
Recent progress in Graph Neural Networks (GNNs) has greatly enhanced the ability to model complex molecular structures for predicting properties. Nevertheless, molecular data encom…
Robustness Inspired Graph Backdoor Defense
Zhiwei Zhang, Minhua Lin, Junjie Xu +3
Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable…
Test-Time Multimodal Backdoor Detection by Contrastive Prompting
Yuwei Niu, Shuo He, Qi Wei +3
While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerab…
Universal Prompt Optimizer for Safe Text-to-Image Generation
Zongyu Wu, Hongcheng Gao, Yueze Wang +2
Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts. However, these models are vulnerable to unsafe input to generate unsafe conte…
Counterfactual Learning on Graphs: A Survey
Zhimeng Guo, Teng Xiao, Zongyu Wu +3
Graph-structured data are pervasive in the real-world such as social networks, molecular graphs and transaction networks. Graph neural networks (GNNs) have achieved great success i…