AI.info

Hui Liu

Explore Hui Liu on AI.info.

• Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
• Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
• AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback
• Exposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks
• How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use
• Agentic Reasoning for Large Language Models
• When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
• Beyond Linear Surrogates: High-Fidelity Local Explanations for Black-Box Models
• You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering
• DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning
• Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs
• Domain-Specific Data Generation Framework for RAG Adaptation
• Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales