Yue Liu

PhD student@National University of Singapore·新加坡·OpenReview

研究方向

Self-supervised Learning · Graph Neural Network · Deep Graph Clustering · Large Language Model · Large Reasoning Model · Vision Language Model · AI Safety · Multi-agent System

Yue Liu

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Kimi-Dev: Agentless Training as Skill Prior for SWE-agents

AudioTrust: Benchmarking The Multifaceted Trustworthiness of Audio Large Language Models

EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents

DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models

Reinforcing Query-Level Meta-Agents

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems

DMark: Order-Agnostic Watermarking for Diffusion Large Language Models

Memory Type Matters: Enhancing Long-Term Memory in Large Language Models with Hybrid Strategies

BridgeRAG: A Framework for Reasoning over Partitioned Knowledge Graphs

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization

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

Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios

From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering

Bridging the Gap between Database Search and De Novo Peptide Sequencing with SearchNovo

FlipAttack: Jailbreak LLMs via Flipping

Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation

FlipAttack: Jailbreak LLMs via Flipping

AdvLoRA: Adversarial Low-Rank Adaptation of Vision-Language Models