Guibin Zhang

MemGen: Weaving Generative Latent Memory for Self-Evolving Agents

AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?

Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow

Aegis: Automated Error Generation and Attribution for Multi-Agent Systems

MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems

OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment

LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems

Unraveling Hallucination in Large Reasoning Models: A Topological Perspective

Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

UniErase: Towards Balanced and Precise Unlearning in Language Models

Multi-agent Architecture Search via Agentic Supernet

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention

Energy-based Backdoor Defense Against Federated Graph Learning

HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning

Graph Sparsification via Mixture of Graphs

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration

Glocal Information Bottleneck for Time Series Imputation

Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning

EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification

TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting

Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems

AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents

MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning

Rationalizing and Augmenting Dynamic Graph Neural Networks

Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning Perspective

MIND SCRAMBLE: UNVEILING LARGE LANGUAGE MODEL PSYCHOLOGY VIA TYPOGLYCEMIA