3 citations · 4 across the 11 of their papers we have counts for
11 papers
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
Jianxiang Yu, Jiapeng Zhu, Bochen Lin +3
LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing ski…
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Jiapeng Zhu, Jianxiang Yu, Yibo Zhao +5
Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divid…
GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence
Yibo Zhao, Jiapeng Zhu, Zichen Ding +1
Retrieval-Augmented Generation (RAG) integrates external knowledge to enhance Large Language Models (LLMs), yet systems remain susceptible to two critical flaws: providing correct…
Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization
Jing Yu, Yibo Zhao, Jiapeng Zhu +4
The widespread dissemination of toxic content on social media poses a serious threat to both online environments and public discourse, highlighting the urgent need for detoxificati…
Relation-Aware Graph Foundation Model
Jianxiang Yu, Jiapeng Zhu, Hao Qian +4
In recent years, large language models (LLMs) have demonstrated remarkable capability to generalize across diverse natural language processing tasks, inspiring the development of g…
Hierarchical Vector Quantized Graph Autoencoder with Annealing-Based Code Selection
Long Zeng, Jianxiang Yu, Jiapeng Zhu +2
Graph self-supervised learning has gained significant attention recently. However, many existing approaches heavily depend on perturbations, and inappropriate perturbations may cor…
Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving
Yao Cheng, Yibo Zhao, Jiapeng Zhu +3
Large Language Models (LLMs) have demonstrated significant potential across various domains. However, they often struggle with integrating external knowledge and performing complex…
Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph
Yibo Zhao, Jiapeng Zhu, Can Xu +2
The rapid growth of social media platforms has raised significant concerns regarding online content toxicity. When Large Language Models (LLMs) are used for toxicity detection, two…
SEAGraph: Unveiling the Whole Story of Paper Review Comments
Jianxiang Yu, Jiaqi Tan, Zichen Ding +7
Peer review, as a cornerstone of scientific research, ensures the integrity and quality of scholarly work by providing authors with objective feedback for refinement. However, in t…
RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning
Jiapeng Zhu, Zichen Ding, Jianxiang Yu +3
The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in…
Class-Balanced and Reinforced Active Learning on Graphs
Chengcheng Yu, Jiapeng Zhu, Xiang Li
Graph neural networks (GNNs) have demonstrated significant success in various applications, such as node classification, link prediction, and graph classification. Active learning…